Gemini CLI vs OpenCode

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   No evidence Gemini CLI has any documented feature for consuming llms.txt or agent-oriented doc manifests; the only related probe shows llms.txt returning 404 on Google's own docs site, and none of the GitHub feature list or docs mention llms.txt support. GEMINI.md context files are a different, project-local mechanism, not agent-oriented web docs discovery.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”

   proof ↗⚑ flag

   OpenCode~partialprobed4/10

   OpenCode's own llms.txt file returns 404, so there is no dedicated llms.txt for agents, but probes show that docs pages are available in machine-readable Markdown form (.md suffix returns 200), which serves an analogous agent-oriented documentation function. There's no first-party statement about llms.txt support or explicit agent-doc pointing workflow. Missing for 10: an actual llms.txt endpoint, documentation instructing users to point agents at machine-readable docs, and confirmation that agents can consume the .md docs as intended.

   • [probe] “PROBE llms.txt: HTTP 404 at https://opencode.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 200 at https://opencode.ai/docs/.md import { Tabs, TabItem } from "@astrojs/starlight/components" import config from "..…”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round drawn
   Gemini CLI✓fullclaimed9/10

   Gemini CLI explicitly documents non-interactive scripting mode, structured/streaming JSON output flags for programmatic parsing, and GitHub Actions-based automation (PR reviews, issue triage, on-demand assistance), which together cover headless/CI use cases well. Missing for 10: independent hands-on confirmation specifically of CI pipeline reliability (community evidence focuses more on interactive agentic quality than CI usage).

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   proof ↗⚑ flag

   OpenCode✓fullprobed9/10

   OpenCode explicitly supports headless/CI use via `opencode run` for non-interactive execution, `opencode serve` for a headless HTTP server with OpenAPI, `--auto` for unattended permission approval, a JS/TS SDK for programmatic control, and a first-party GitHub Actions integration triggered by PR comments. This covers CLI scripting, server automation, and CI pipelines with concrete docs and an OpenAPI endpoint confirmed live. missing for 10: independent third-party validation of CI reliability at scale (community evidence mostly covers interactive TUI use, not CI-specific automation).

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “Start OpenCode with --auto to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to OpenCode
   Gemini CLI✓fullclaimed8/10

   Gemini CLI documents first-party MCP server support: configuring servers in ~/.gemini/settings.json to add custom tools, a dedicated /mcp command, and explicit mention of connecting media-generation tools like Imagen/Veo/Lyria via MCP. This is corroborated by official docs listing /mcp among CLI commands. Missing for 10: independent hands-on verification of MCP tool usage specifically (community evidence covers general agentic reliability but not MCP integration itself), and more detail on server management/discovery UX.

   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”

   proof ↗⚑ flag

   OpenCode✓fullclaimed9/10

   OpenCode has first-party documentation dedicated to adding external tools via MCP, supporting both local and remote servers, directly matching the story. This is corroborated indirectly by community discussion of OpenCode's tool/agent ecosystem, though no hands-on account specifically tests MCP server plugging. Missing for 10: independent/hands-on confirmation specifically of MCP server usage (community evidence discusses agents/tools generally but not MCP specifically).

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the Model Context Protocol, or MCP.”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round drawn
   Gemini CLI✓fullprobed9/10

   Gemini CLI is itself an official, first-party CLI product by Google with extensive documentation of its features (scripting, JSON output, MCP support, context files, non-interactive mode) and independent corroboration of active use, confirming it exists and functions as an official CLI tool for AI-native workflows. missing for 10: no fully independent third-party audit of CLI completeness beyond community anecdotes.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “gemini --include-directories ../lib,../docs”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [probe] “official CLI documented at https://developers.google.com/gemini-code-assist/docs/gemini-cli”

   proof ↗⚑ flag

   OpenCode✓fullprobed9/10

   OpenCode ships an official CLI with documented commands (opencode run, opencode serve, init, install via curl/npm) and dedicated CLI docs, corroborated by community users who actively use it as their primary daily-driver harness. Missing for 10: independent benchmarking of CLI completeness/stability beyond anecdotal community reports (some bug complaints noted but not disputing existence of an official CLI).

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “curl -fsSL https://opencode.ai/install | bash”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “npm install -g opencode-ai”
   • [probe] “official CLI documented at https://opencode.ai/docs/cli/”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round to OpenCode
   Gemini CLI~partialprobed5/10

   Gemini CLI documents CLI-level automation hooks — non-interactive scripting mode, `--output-format json`/`stream-json` for structured output, and MCP server configuration — which let an AI-native user drive it programmatically (gemini-cli-gh-6, gh-17, gh-18, gh-19). However, explicit probes for a formal public API/SDK (llms.txt, openapi.json) all returned 404, showing no dedicated documented API surface beyond the CLI itself. Missing for 10: a first-party REST/SDK API spec, official API reference docs, and independent confirmation of programmatic (non-CLI) usage.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

   OpenCode✓fullprobed8/10

   OpenCode ships a documented headless server (`opencode serve`) exposing an OpenAPI endpoint, confirmed live via probe (opencode-probe-3), plus a type-safe JS/TS SDK for programmatic control, and its CLI supports non-interactive scripted use (`opencode run`). missing for 10: independent third-party corroboration of SDK/API usage in production, and no evidence of versioning/stability guarantees or broader language SDK support beyond JS/TS.

   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server.”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “Attach a terminal to an already running OpenCode backend server started via `serve` or `web` commands.”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   Evidence shows Gemini CLI abstracts away API key management entirely (sign in with Google account) rather than offering scoped or least-privilege credential issuance for agents; no docs mention credential scoping, permission boundaries, or token minting for agent use.

   • [github] “No API key management - just sign in with your Google account”

   proof ↗⚑ flag

   OpenCode~partialclaimed3/10

   OpenCode's permission config lets you restrict which actions (edit, bash, etc.) an agent may auto-run, prompt for, or block, and enterprise SSO integration centralizes access to an internal AI gateway — both are adjacent to least-privilege agent control, but neither is a mechanism for issuing scoped API credentials/keys specifically to an agent. missing for 10: explicit scoped API-key/credential issuance for agents, credential expiry/rotation, per-agent key scoping documentation, independent verification of this capability.

   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   The evidence pack documents CLI flags, MCP server extensibility, scripting output formats, and GitHub Actions integration, but contains no mention of an official SDK (e.g., a Node/Python/Go library) for programmatically building on Gemini CLI itself. Probes for API/OpenAPI specs also returned 404s, reinforcing the absence of such artifacts.

   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

   OpenCode✓fullprobed8/10

   OpenCode documents a dedicated JS/TS SDK ('type-safe client for interacting with the server... use it to build integrations and control opencode programmatically') plus a headless server mode (`opencode serve`) exposing an OpenAPI endpoint, confirmed live by probe (openapi.json returns valid schema). This gives AI-native users official, documented programmatic access beyond the CLI/TUI. Missing for 10: independent hands-on developer reports of building against the SDK, and broader multi-language SDK coverage beyond JS/TS.

   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Gemini CLI—none0/10

   No evidence of webhook subscription or event-push capability; Gemini CLI supports non-interactive scripting, MCP tool servers, and structured JSON output, but nothing about outbound webhooks or event subscriptions. Missing for 10: any webhook registration mechanism, event subscription API, or documentation of push notifications.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”

   proof ↗⚑ flag

   OpenCode—none0/10

   Evidence shows OpenCode has a headless server (`opencode serve`) exposing an OpenAPI/HTTP endpoint and an SDK for programmatic control, but there is no mention anywhere of webhook subscriptions or event-push notifications that clients could register for.

   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server.”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Gemini CLI ships features that clearly aim at generating insights from a user's own data/codebase — querying and editing large codebases, natural-language debugging, automated PR review with contextual feedback, and issue triage (gemini-cli-gh-1, gh-3, gh-10, gh-11), and one community report praises its code review as catching bugs missed by humans (gemini-cli-comm-20). However, multiple hands-on reports directly contradict this, describing it as 'terrible at agentic stuff', getting stuck in loops, failing to edit/read files, and being 'useless as a coding assistant' that produces spaghetti code (gemini-cli-comm-10, comm-14, comm-15). missing for 10: independent benchmark confirming consistent quality of generated insights, resolution of the loop/failure reports, and evidence the insight-generation works reliably across data types beyond code.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”

   proof ↗⚑ flag

   OpenCode✓fullcommunity7/10

   OpenCode's plan/explore agents let users get AI-generated code analysis and suggested changes without modifying the codebase, directly matching the story of AI-generated insights over the user's data (their code) (opencode-docs-7, opencode-docs-60, opencode-docs-61). Community mentions confirm active use of the agent for analysis/harness work (opencode-comm-1, opencode-comm-3). Missing for 10: independent examples of insight quality/output, and no evidence of insights beyond code (e.g., broader data analytics).

   • [claimed-docs] “Use the plan agent to analyze code and review suggestions without making any code changes.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round drawn
   Gemini CLI~partialcommunity6/10

   Gemini CLI documents non-interactive scripting mode and a GitHub Action integration that runs autonomously in the background (automated PR reviews, issue triage, on-demand @gemini-cli responses), which directly supports background automations. However, independent community reports describe agentic reliability problems (getting stuck in loops, failing simple file operations, ignoring GEMINI.md context) that undercut confidence in unattended/background runs actually completing correctly. Missing for 10: independent hands-on validation that scheduled/background automations run reliably end-to-end, and more detail on failure/retry handling in autonomous mode.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “@github List my open pull requests”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

   OpenCode~partialcommunity6/10

   OpenCode ships a documented GitHub Actions integration where mentioning /opencode or /oc in a comment triggers it to autonomously work in a new branch and submit a PR, plus a headless `serve` mode and `--auto` permission flag that let it run unattended, supporting background automations. However there's no dedicated scheduling/cron mechanism, and community evidence flags reliability issues (stuck sessions, tool-call failures) that undercut confidence in unattended runs. missing for 10: scheduled/triggered automation beyond GitHub comment mentions, independent evidence of long-running unattended background jobs succeeding reliably.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Gemini CLI is itself billed as an agentic assistant with extensive task-delegation features (codebase queries, debugging, PR review/issue triage, operational automation via @gemini-cli mentions) per gemini-cli-gh-3/4/10/11/12/22. However, hands-on community reports concretely contradict reliable delegation: users report it is 'really really terrible at agentic stuff,' gets stuck in permanent loops, ignores GEMINI.md context, and in one case catastrophically deleted user files while apologizing for the failure.

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode✓fullcommunity9/10

   OpenCode's core function is exactly this: an AI coding agent you delegate tasks to via CLI/TUI/IDE/desktop ('opencode run "Explain how closures work..."'), with multiple agent personas (build, plan, explore) and multi-session parallel delegation, richly documented and corroborated by extensive hands-on community use as a daily coding harness. Missing for 10: no independent benchmark of delegation reliability across all model backends (some community reports of failed tool calls/edits with local models).

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “You can use the **Tab** key to switch between primary agents during a session.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to u…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Gemini CLI's entire premise is natural-language driven coding/agentic actions (querying codebases, debugging, automating PR/rebase tasks, custom GEMINI.md context) per gemini-cli-gh-1/3/4/9. However, multiple hands-on reports describe the NL-agent behavior failing badly in practice — getting stuck in error loops, botching file edits, ignoring GEMINI.md instructions, and in one case catastrophically deleting user data via misinterpreted commands.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode✓fullcommunity9/10

   OpenCode's core interface is natural-language driven: the CLI example `opencode run "Explain how closures work in JavaScript"` and TUI/desktop/IDE modes are all built around conversational prompts to an AI agent that then edits code, opens branches, and submits PRs. Community usage (comm-1, comm-3, comm-4, comm-11) confirms this is how real users operate it day-to-day as their primary coding harness. Missing for 10: no independent benchmark specifically validating breadth of natural-language command coverage beyond docs/anecdotes.

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to u…”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   No evidence of an interactive API reference with runnable examples; probes explicitly show no llms.txt or OpenAPI spec found, and no docs describe an interactive reference tool.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

   OpenCode~partialprobed3/10

   OpenCode exposes a raw OpenAPI spec via `opencode serve` and openapi.json, and offers an SDK for programmatic use, but there is no evidence of an actual interactive API reference UI (e.g., Swagger/Redoc-style docs) with runnable/try-it examples. Missing for 10: dedicated interactive API explorer page, runnable code examples, independent confirmation of such a UI existing.

   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   Probes explicitly show no OpenAPI/llms.txt spec is published (404s at all candidate paths), and no other evidence mentions a machine-readable API spec for Gemini CLI.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

   OpenCode✓fullprobed9/10

   The docs explicitly state that `opencode serve` runs a headless HTTP server exposing an OpenAPI endpoint, and a live probe confirms a downloadable machine-readable OpenAPI spec at https://opencode.ai/openapi.json. This directly satisfies the story of downloading a machine-readable API spec. Missing for 10: independent/community corroboration of using this OpenAPI spec in practice.

   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Gemini CLI—none0/10

   No evidence pack items describe a sandbox/test environment isolated from production data for Gemini CLI; the only mention of 'sandbox' appears in an unrelated community comment describing another tool's architecture, not Gemini CLI's own testing environment. missing for 10: dedicated sandbox mode/documentation, evidence of isolation from production data, any hands-on confirmation of safe test environments.

   ⚑ flag

   OpenCode—none0/10

   OpenCode's docs describe permission controls, --auto approval, and external_directory restrictions, but there is no evidence of a dedicated sandbox/staging environment or mechanism to test against non-production data separate from the user's actual working directory/production files. Community reports even flag security gaps in the local server (opencode-comm-18) rather than any sandboxing feature for safe testing.

   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “Use external_directory to allow tool calls that touch paths outside the working directory where OpenCode was started.”
   • [community] “When server is enabled, any web page served from localhost/127.0.0.1 can execute code; any local process can execute code without authentica…”

   proof ↗⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Gemini CLI—none0/10

   No evidence of versioned APIs or a documented deprecation policy for Gemini CLI; probes for llms.txt/openapi specs 404, and there is community evidence the tool itself was abruptly deprecated with no policy discussion (gemini-cli-comm-6/7/8), but no documentation of API versioning or deprecation commitments exists.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”
   • [community] “Welcome to the Google graveyard, Gemini CLI. Not that it will be missed much. Using it was the worst experience out of any harness.”
   • [community] “Google really can't help themselves but to have some internal re-org kill off a public thing people are actively using. It's honestly impres…”

   proof ↗⚑ flag

   OpenCode—none0/10

   OpenCode does expose programmatic surfaces (the JS/TS SDK, `opencode serve` HTTP server, and an OpenAPI spec at openapi.json), so an API-versioning/deprecation-policy axis is applicable. However, none of the evidence mentions API version numbers, backward-compatibility guarantees, or any documented deprecation policy/process for the SDK or server API.

   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Gemini CLI
   Gemini CLI~partialcommunity6/10

   Gemini CLI supports scripting/non-interactive automation, multi-directory context inclusion, structured JSON output for pipelines, and GitHub Action integrations like automated issue triage (bulk labeling/prioritization) and PR review across a repo — all pointing to bulk/batch style operations. However there's no explicit documented 'batch process N files/items' feature or example, and community reports note the agent can get stuck in loops or fail simple multi-step tasks, raising doubts about reliability at scale. Missing for 10: explicit bulk-operation examples/documentation (e.g., batch renaming, mass refactor across many files) and independent evidence confirming reliable execution at scale.

   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “gemini --include-directories ../lib,../docs”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”

   proof ↗⚑ flag

   OpenCode~partialclaimed4/10

   OpenCode's CLI (`opencode run`), SDK, and headless `opencode serve` provide programmatic hooks that could be scripted to loop over many files/tasks, and 'multi-session' lets multiple agents run in parallel on a project — but there is no documented first-class 'bulk operation' feature (e.g. batch refactor, mass file edit) or example of applying one command across many items at once. Missing for 10: explicit bulk/batch operation feature, documentation or examples of running the same task across many files/repos, independent evidence of successful large-scale batch use.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round drawn
   Gemini CLI~partialclaimed5/10

   Gemini CLI ships GitHub Action integrations that fire automatically on repo events (PR opened → automated review, issue created → automated triage, @mention → on-demand help), which is a form of event-triggered automation, plus non-interactive/scripted execution for pipelines. However there's no evidence of a general-purpose, user-defined rule/trigger engine (e.g., custom webhooks, cron-like conditions, arbitrary event types) within the CLI itself—only fixed GitHub-event integrations. Missing for 10: a generic rule-definition mechanism for arbitrary events, documentation of custom trigger conditions, and independent confirmation these automations work reliably (community notes reliability issues with agentic behavior).

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Run non-interactively in scripts for workflow automation”

   proof ↗⚑ flag

   OpenCode~partialclaimed5/10

   OpenCode supports some automatic rule-triggered behavior: GitHub integration lets a PR/issue comment mention (`/opencode` or `/oc`) automatically trigger the agent to execute tasks in a GitHub Actions runner, and the `permission` config lets you define rules for auto-approving, prompting, or blocking specific tool actions. This covers event-triggered automation in a narrow sense, but there's no general-purpose, user-defined event/rule engine (e.g., file-change hooks, cron-like triggers, custom event listeners) described in the docs. Missing for 10: a general automation/hooks system beyond GitHub comment mentions and permission gating, and independent evidence confirming reliability of these triggers in practice.

   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “OpenCode uses the permission config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “For most permissions, you can use an object to apply different actions based on the tool input.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Gemini CLI
   Gemini CLI~partialclaimed4/10

   Gemini CLI supports non-interactive scripted runs and structured JSON output, which lets users wire it into external schedulers (cron, CI) for recurring automation, and its GitHub Action integrations (issue triage, PR review) imply repeatable, trigger-based workflows. However there is no first-party 'scheduled job' or cron feature documented within the CLI itself. Missing for 10: a native recurring-job/scheduler feature, explicit docs on scheduling cadence, and independent confirmation that scripted/CI-triggered runs work reliably for recurring automation.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”

   proof ↗⚑ flag

   OpenCode—none0/10

   No evidence of any scheduling, cron-like, or recurring workflow trigger capability; OpenCode's docs cover CLI, agents, MCP, permissions, SDK, GitHub Actions triggers, and server mode but none describe scheduling or recurring automation. missing for 10: any scheduler/cron feature, recurring job configuration, or workflow trigger on a schedule.

   ⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Gemini CLI
   Gemini CLI~partialclaimed4/10

   Gemini CLI offers conversation checkpointing to save and resume sessions (gemini-cli-gh-8), which provides a rudimentary rollback/resume mechanism, but there is no evidence of versioning, diffing, or reviewing automation scripts/workflows themselves, nor a dedicated rollback command for automations. missing for 10: explicit version history for automations, review/diff tooling, and a documented rollback mechanism beyond session checkpoints.

   • [github] “Conversation checkpointing to save and resume complex sessions”

   proof ↗⚑ flag

   OpenCode—none0/10

   Evidence covers agent creation, permissions, sessions, and sharing, but there is no documentation or community mention of versioning automations, reviewing change history, or rolling back agent/workflow configurations — session share links are for reference/debugging, not version control or rollback.

   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “This command will guide you through creating a new agent with a custom system prompt and permission configuration.”

   proof ↗⚑ flag

Background execution

1. ai-native userHave a cloud agent build, test, and demo a feature end-to-end for my review

   weight 2 · round to OpenCode
   Gemini CLI~partialcommunity4/10

   Gemini CLI documents cloud-adjacent automation via its GitHub Actions integration (PR reviews, issue triage, @gemini-cli on-demand assistance, non-interactive scripting) which could kick off agentic work, but there is no vendor evidence of an autonomous cloud agent that builds, runs tests, and produces a demo end-to-end for review. Community reports also describe agentic mode getting stuck in error loops, failing at basic file edits, and even causing data loss, undercutting confidence in reliable autonomous execution. missing for 10: explicit end-to-end build+test+demo workflow, evidence of a hosted/cloud agent (vs local CLI or CI hooks) producing a reviewable demo, and independent confirmation that autonomous runs complete without failure loops.

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Run non-interactively in scripts for workflow automation”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode~partialclaimed6/10

   OpenCode's GitHub integration lets it work in a new branch and submit a PR autonomously when mentioned via `/opencode` in GitHub Actions, and its share-links/session feature lets a reviewer inspect the agent's work — together covering 'build' and 'demo for review' in a cloud context. However, there is no explicit documentation of an automated testing step as part of this workflow, and the 'cloud agent' aspect relies on self-hosted GitHub Actions runners rather than a dedicated managed cloud agent service. Missing for 10: explicit test-execution/validation step in the PR workflow, and a first-party fully-hosted cloud agent (not just Actions-runner based) with demo artifacts.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”

   proof ↗⚑ flag

2. developerDelegate longer-running coding tasks to run in the background in an isolated cloud environment

   weight 3 · round to OpenCode
   Gemini CLI~partialclaimed4/10

   Gemini CLI supports non-interactive scripting and GitHub Actions integration (@gemini-cli mentions for PR reviews, issue triage, on-demand assistance) which can run tasks in a cloud CI environment, and Cloud Shell offers a ready cloud runtime — but there's no dedicated 'run this long task in an isolated background cloud sandbox' feature akin to a hosted agent service. missing for 10: explicit isolated cloud sandbox/background execution product, evidence of long-running autonomous task delegation outside CI triggers, and independent confirmation it works reliably for extended background jobs.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”

   proof ↗⚑ flag

   OpenCode~partialclaimed5/10

   OpenCode documents GitHub integration where mentioning /opencode or /oc triggers it to work in a new branch and submit a PR, executing tasks inside the GitHub Actions runner (an isolated cloud environment), which supports background delegation of coding tasks. However, there's no dedicated general-purpose 'cloud agent' product, persistent cloud session management, or evidence of handling arbitrarily long-running tasks outside the GitHub Actions context. missing for 10: a dedicated hosted/cloud sandbox environment independent of GitHub Actions, evidence of long-running task monitoring/resumption in the cloud, and independent hands-on confirmation of this workflow succeeding.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”

   proof ↗⚑ flag

3. developerConfigure a reproducible cloud environment with the dependencies and setup steps my repository needs

   weight 2 · round drawn
   Gemini CLI—none0/10

   Evidence shows Gemini CLI can run in Cloud Shell without extra setup and supports GEMINI.md context files, but there is no evidence of a configurable, reproducible cloud environment (e.g., dependency/setup scripts, devcontainer-style config) that a developer can define for their repo. Missing for 10: any documented environment/setup-script configuration mechanism, evidence of reproducibility across runs, and independent confirmation it works as such.

   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”

   proof ↗⚑ flag

   OpenCode—none0/10

   The evidence shows OpenCode as a terminal/IDE agent with GitHub PR automation and a headless `serve` mode, but nothing describes a mechanism for developers to declare a reproducible cloud environment (base image, dependencies, setup scripts) that the agent provisions before running. Missing for 10: any devcontainer/config-file spec for cloud sandbox provisioning, dependency installation steps, or documented cloud execution environment configuration.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”

   proof ↗⚑ flag

Parallel agents

1. ai-native userLaunch fleets of autonomous agents that work in parallel on different tasks for hours or days

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   Evidence shows single-session non-interactive scripting, GitHub Actions integration for issue triage/PR review, and MCP extensibility, but nothing about launching multiple autonomous agents working in parallel for hours or days. No fleet/orchestration/multi-agent parallelism capability is documented anywhere in the pack.

   ⚑ flag

   OpenCode~partialcommunity6/10

   OpenCode documents multi-session support ('Start multiple agents in parallel on the same project'), subagents with per-agent model choice, and GitHub Actions integration where mentioning /opencode lets it execute unattended tasks and open PRs — all pointing toward parallel, semi-autonomous agent operation. However, there is no explicit documentation or evidence of orchestrating large 'fleets' of agents or of sustained autonomous operation over hours/days, and community reports note agents 'randomly stuck, especially for long/nested sessions,' undercutting long-horizon reliability. Missing for 10: dedicated fleet-management/orchestration tooling, explicit hours/days-long autonomous run support, and independent confirmation of stable long-running parallel agent execution.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

2. developerRun several task attempts in parallel and compare results before choosing one

   weight 1 · round to OpenCode
   Gemini CLI—none0/10

   No evidence in the pack describes running multiple parallel task attempts or comparing/diffing results before selecting one; features listed are single-session tools (checkpointing, MCP, scripting) with no multi-attempt/parallel comparison workflow mentioned. Missing for 10: any mention of parallel run/branching feature, a comparison UI or mechanism to pick the best of several attempts.

   ⚑ flag

   OpenCode~partialcommunity4/10

   OpenCode documents 'multi-session' support to start multiple agents in parallel on the same project (opencode-docs-17/38) and share links to sessions for reference/debugging (opencode-docs-18/37), which enables running parallel work and inspecting different sessions. However, there is no documented feature for running multiple attempts at the *same* task specifically to compare outcomes and pick a winner (e.g., no diff/compare UI or attempt-ranking workflow), and community threads discuss general session-state bugs rather than this comparison workflow. Missing for 10: explicit same-task multi-attempt spawning, a built-in comparison/diff view across attempts, and evidence of choosing/merging the best result.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”

   proof ↗⚑ flag

Scheduled automation

1. ai-native userSet up always-on agents that run on schedules or triggers to maintain and fix my software autonomously

   weight 2 · round to Gemini CLI
   Gemini CLI~partialcommunity4/10

   Gemini CLI supports non-interactive scripted runs and GitHub Actions-based triggers (PR reviews, issue triage, @mention on-demand assistance) which can approximate scheduled/triggered automation, but there is no evidence of a persistent, self-scheduling 'always-on agent' that autonomously maintains and fixes software over time. missing for 10: native scheduler/cron support, persistent agent daemon or watch-mode, evidence of autonomous multi-cycle maintenance without human triggering, and reliability data (community reports actually describe agent mode getting stuck in loops or failing tasks).

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”

   proof ↗⚑ flag

   OpenCode—none0/10

   OpenCode documents CLI/TUI/desktop agents, permission automation, GitHub Actions integration triggered by comments, and a headless server/SDK, but there is no evidence of scheduling (cron-like) or event-trigger-based always-on autonomous agents that proactively maintain/fix software without a user or PR-comment invocation. The GitHub integration is triggered by manual mentions, not autonomous scheduled monitoring. Missing for 10: scheduled/cron-based agent runs, event-driven triggers beyond manual mentions, autonomous 'always-on' background maintenance capability.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”

   proof ↗⚑ flag

Debugging

1. developerDebug issues and troubleshoot using natural-language queries

   weight 2 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Gemini CLI explicitly advertises natural-language debugging/troubleshooting (gemini-cli-gh-3, gh-12/21/23) and community reports confirm strong codebase navigation and code-review value (gemini-cli-comm-1, comm-20). However, multiple hands-on reports directly contradict reliable debugging: users describe it getting stuck in error loops, failing simple file edits, and in one case catastrophically deleting user data during a troubleshooting session (gemini-cli-comm-10, comm-11, comm-14, comm-16).

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode✓fullcommunity7/10

   OpenCode is a terminal/IDE-based coding agent that takes natural-language queries (e.g. `opencode run "Explain how closures work..."`), can explore/read codebases via a dedicated read-only agent, and auto-loads LSPs so it can surface diagnostics/errors while chatting, all of which supports NL-driven debugging and troubleshooting; community users confirm using it as a daily 'harness' with good LSP integration for real work. missing for 10: no dedicated 'debug' or troubleshooting workflow docs, and community reports of failed tool calls/unreliable file edits with some models introduce real-world friction.

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “LSP enabled Automatically loads the right LSPs for the LLM”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

Feature implementation

1. developerTurn a tracked issue into a complete pull request end-to-end

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Gemini CLI's GitHub integration supports @gemini-cli task delegation from issues/PRs, automated PR reviews, and issue triage, which vendor docs frame as enabling issue-to-PR workflows (gh-12, gh-21, gh-10, gh-22, gh-4). However, hands-on community reports describe the agent getting stuck in loops, failing basic file edits, lacking a plan mode, and producing 'spaghetti code' rather than completing tasks reliably — directly undermining claims of smooth end-to-end PR generation (gemini-cli-comm-10, gemini-cli-comm-11, gemini-cli-comm-14). Missing for 10: a documented full issue→PR walkthrough, evidence of successful autonomous PR creation from an issue, and independent confirmation resolving the agentic reliability complaints.

   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “@github List my open pull requests”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”

   proof ↗⚑ flag

   OpenCode✓fullclaimed7/10

   Docs explicitly state OpenCode can be asked to fix an issue or implement a feature, working in a new branch and submitting a PR with all changes, and it integrates with GitHub Actions via /opencode mentions to run tasks end-to-end. This directly covers issue-to-PR automation, though evidence is vendor-documented only without independent hands-on confirmation of the full issue-to-PR flow succeeding. Missing for 10: independent/community verification of a successful end-to-end issue-to-PR run, and detail on how issue tracking (e.g., linking to GitHub issues specifically) is handled beyond the GitHub Actions integration.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”

   proof ↗⚑ flag

2. developerDescribe a feature or bug in plain language and have the agent implement or fix it across multiple files

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Vendor docs/GitHub claim strong support for describing features/bugs in plain language and having the agent edit/debug across large codebases (gemini-cli-gh-1, gemini-cli-gh-3), but multiple hands-on community reports directly contradict this: users report the agent getting stuck in error loops, failing basic file edit/read operations, ignoring GEMINI.md context files, jumping straight into 'spaghetti code' without a plan mode, and in one case catastrophically deleting user data via botched commands. missing for 10: consistent hands-on success stories on multi-file feature implementation, resolution of the reported reliability/looping failures, and independent benchmarks confirming multi-file bug-fix accuracy.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode✓fullcommunity8/10

   OpenCode is explicitly a coding agent that takes plain-language instructions and edits code, with docs describing it fixing issues/implementing features and submitting PRs (opencode-docs-12), a CLI for prompting tasks (opencode-docs-22), and permission/auto-approve config for autonomous multi-file changes (opencode-docs-13/14). Community reports corroborate real-world multi-file coding use, with several users calling it their primary harness replacing Aider/Claude Code (opencode-comm-1, opencode-comm-3, opencode-comm-4, opencode-comm-11, opencode-comm-14), though some report unreliable file edits with certain local models and failed tool calls in general (opencode-comm-10, opencode-comm-12). Missing for 10: independent benchmark data on multi-file edit accuracy, and resolution of the reported local-model editing reliability issues.

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to u…”
   • [community] “OpenCode is awesome. Claude Code is nothing special at all. Last month I switched to just using OpenCode with a Codex $200/mo subscription, …”
   • [community] “I haven't been able to successfully get their CLI to reliably edit files when using local models, anybody else having the same problem?”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

Maintenance automation

1. developerHave the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   GitHub docs claim broad code-editing, debugging, and complex-rebase (merge conflict) automation capabilities (gemini-cli-gh-1, gemini-cli-gh-3, gemini-cli-gh-4), which would cover fixing lint issues and dependency/test work as part of general codebase editing, and PR review/issue triage features suggest lint-like feedback (gemini-cli-gh-10, gemini-cli-gh-11). However, multiple hands-on community reports concretely contradict reliable agentic code work: users report it getting stuck in error loops, failing simple file edit/read operations, ignoring GEMINI.md context files, producing 'spaghetti code' with no plan mode, and in one case catastrophically deleting user data during a file operation (gemini-cli-comm-10, gemini-cli-comm-11, gemini-cli-comm-13, gemini-cli-comm-14, gemini-cli-comm-16). No explicit evidence names test-writing, lint-fixing, or dependency-updating tasks specifically. Missing for 10: explicit documentation/examples of writing tests, fixing lint errors, or updating dependencies, and independent corroboration that these specific tasks work reliably.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode~partialcommunity6/10

   OpenCode is documented as a general-purpose coding agent that can edit files, run shell commands, and even autonomously fix issues and submit PRs (opencode-docs-12, opencode-docs-58), which implies it can perform tasks like writing tests, fixing lint, resolving conflicts, and updating deps as generic coding actions. However, none of the docs explicitly call out test-writing, lint-fixing, merge-conflict resolution, or dependency updates as named capabilities, and community reports note reliability gaps such as failed tool calls and unreliable file edits especially with local models (opencode-comm-10, opencode-comm-12). Missing for 10: explicit documentation or hands-on evidence of test generation, lint-fix workflows, merge-conflict resolution, and dependency-update automation.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “I haven't been able to successfully get their CLI to reliably edit files when using local models, anybody else having the same problem?”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

Multimodal generation

1. ai-native userGenerate a working app from a sketch, image, or PDF design

   weight 2 · round to Gemini CLI
   Gemini CLI~partialcommunity6/10

   Official docs explicitly claim 'Generate new apps from PDFs, images, or sketches using multimodal capabilities,' directly matching the story, but there is no independent/hands-on corroboration of this specific capability, and broader community feedback raises general concerns about agentic reliability that could affect complex generation tasks. missing for 10: independent hands-on demonstration of sketch/PDF-to-app generation, details on fidelity/limitations of this workflow.

   • [github] “Generate new apps from PDFs, images, or sketches using multimodal capabilities”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”

   proof ↗⚑ flag

   OpenCode—none0/10

   OpenCode's evidence pack shows a terminal/IDE-based coding agent with text prompts, MCP, agents, and CLI/SDK, but there is no mention anywhere of image, sketch, or PDF design input being converted into a working app — no vision/multimodal input capability is documented.

   ⚑ flag

Codebase mapping

1. developerUnderstand how a codebase fits together to find where to start making changes

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Gemini CLI advertises large-codebase querying/editing (gemini-cli-gh-1) with a 1M-token context window, custom GEMINI.md context files, and --include-directories flags for scoping (gemini-cli-gh-9, gemini-cli-gh-16), and one HN user praises its ability to 'navigate and learn' large codebases effortlessly (gemini-cli-comm-1). However, other hands-on users report the opposite: it is 'stupid at navigation in the codebase' taking 10x longer (gemini-cli-comm-15) and 'consistently ignores' the GEMINI.md context file despite claiming to use it (gemini-cli-comm-13), directly undercutting the codebase-understanding claim. Missing for 10: consistent independent corroboration of reliable codebase navigation, and no contradicting failure reports.

   • [github] “Query and edit large codebases”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [github] “gemini --include-directories ../lib,../docs”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

   OpenCode✓fullcommunity7/10

   OpenCode ships a dedicated read-only 'explore' agent for scanning codebases and a 'plan' agent that analyzes code and proposes changes without modifying files, backed by automatic LSP loading for the right language context and skills that surface repo-specific instructions; community notes call the LSP integration 'great' for understanding code. Missing for 10: no dedicated codebase-mapping/visualization feature, no independent benchmark of comprehension quality, and no first-hand user account describing successful architecture-level onboarding via these agents.

   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “Use the plan agent to analyze code and review suggestions without making any code changes.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “LSP enabled Automatically loads the right LSPs for the LLM”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory. Skills are loaded on-demand via the native `skill…”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”

   proof ↗⚑ flag

2. developerHave the agent map and explain an entire unfamiliar codebase without manually selecting context files

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Google claims large-codebase querying/editing (gemini-cli-gh-1) and Gemini CLI's 1M-token context lets it 'navigate and learn' huge codebases 'effortlessly' per one user (gemini-cli-comm-1), but other hands-on reports directly contradict this, calling it 'so stupid at navigation in the codebase it takes 10x as long' (gemini-cli-comm-15) and prone to getting 'stuck in spaghetti code' with no plan mode (gemini-cli-comm-14), plus it reportedly ignores its own GEMINI.md context file (gemini-cli-comm-13). Missing for 10: consistent independent benchmarks confirming autonomous whole-codebase mapping without file selection, and resolution of the navigation-quality contradiction.

   • [github] “Query and edit large codebases”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

   OpenCode~partialcommunity6/10

   OpenCode ships a dedicated read-only 'explore' agent explicitly for exploring codebases and a plan agent for analyzing code without edits, plus automatic LSP loading that gives it broader code awareness without manual file picking. However there's no documented feature for generating a full repo map/summary or explicit 'explain this whole codebase' workflow beyond agent tool use (e.g. grep/glob/read), and no independent hands-on evidence confirming it successfully maps a large unfamiliar codebase end-to-end. Missing for 10: explicit repo-map/codebase-summary feature, hands-on/independent confirmation of whole-codebase explanation without manual context selection.

   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “LSP enabled Automatically loads the right LSPs for the LLM”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”

   proof ↗⚑ flag

Context management

1. developerHave the agent build and recall memory automatically across sessions

   weight 2 · round to Gemini CLI
   Gemini CLI!disputedcontradicted3/10

   Gemini CLI offers static project context via GEMINI.md files and a `/memory` command, plus manual conversation checkpointing to save/resume sessions—but these are manually configured/invoked, not automatic memory building/recall across sessions. Hands-on community evidence directly contradicts even the GEMINI.md context mechanism working reliably: a user reports it 'consistently ignores my GEMINI.md file... even though it always says 1 GEMINI.md file is being used' (gemini-cli-comm-13), undermining the claimed persistent-context capability. missing for 10: evidence of automatic memory formation/recall without user action, evidence /memory command builds persistent cross-session knowledge, independent corroboration that GEMINI.md context reliably persists.

   • [github] “Conversation checkpointing to save and resume complex sessions”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

   OpenCode—none0/10

   No evidence in the pack describes any persistent memory feature that automatically builds or recalls context/knowledge across separate sessions; docs cover sessions, sharing, agents, MCP, skills, and permissions, but nothing about automatic cross-session memory persistence or recall.

   ⚑ flag

2. developerInclude multiple project directories in a single session for broader context

   weight 2 · round to Gemini CLI
   Gemini CLI✓fullclaimed8/10

   The official CLI flag `--include-directories ../lib,../docs` explicitly allows adding multiple project directories into a single session for broader context, directly matching the story. Missing for 10: independent hands-on confirmation of multi-directory usage quality/behavior beyond the flag documentation.

   • [github] “gemini --include-directories ../lib,../docs”

   proof ↗⚑ flag

   OpenCode—none0/10

   The evidence shows a permission flag (`external_directory`) that lets tool calls touch paths outside the working directory, but there is no documentation or community report describing a way to add multiple project directories into a single session for combined context. Multi-session and multi-agent features are about running parallel sessions, not merging directories into one context.

   • [claimed-docs] “Use external_directory to allow tool calls that touch paths outside the working directory where OpenCode was started.”
   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”

   proof ↗⚑ flag

3. developerAdd a project instructions file to set coding standards and conventions the agent follows

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted5/10

   Gemini CLI documents GEMINI.md custom context files for tailoring behavior/project conventions (gemini-cli-gh-9) and docs mention /memory command for managing this context (gemini-cli-docs-3). However, hands-on community feedback reports the file being ignored despite being loaded ('it consistently ignores my GEMINI.md file, both global and local, even though it always says 1 GEMINI.md file is being used' - gemini-cli-comm-13), directly contradicting reliable adherence to project instructions. Missing for 10: independent corroboration that GEMINI.md is consistently honored, more detail on precedence/hierarchy of instruction files, and resolution of the reported ignoring behavior.

   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

   OpenCode~partialclaimed5/10

   OpenCode's docs mention an `opencode init` step to set up a project (docs-21/39/56) and 'Agent skills' that let OpenCode discover reusable instructions from a repo or home directory (docs-8/28), which suggests some mechanism for project-level guidance, but no evidence explicitly describes a dedicated instructions/config file (e.g., AGENTS.md) for coding standards and conventions. Missing for 10: explicit documentation of a project instructions file format, guidance on writing coding-standards content into it, and independent/hands-on confirmation that the agent actually follows such a file.

   • [claimed-docs] “initialize OpenCode for the project by running the following command.”
   • [claimed-docs] “Next, initialize OpenCode for the project by running the following command.”
   • [claimed-docs] “initialize OpenCode for the project by running the following command”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory. Skills are loaded on-demand via the native `skill…”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory.”

   proof ↗⚑ flag

Issue diagnosis

1. developerReproduce issues, narrow down root causes, and verify fixes

   weight 3 · round to OpenCode
   Gemini CLI!disputedcontradicted4/10

   Google markets debugging/troubleshooting via natural language and a /bug reporting flow (gh-3, gh-20), and one HN user praises its ability to navigate huge codebases (comm-1). However multiple hands-on reports directly contradict root-cause/verify-fix workflows: users describe it getting stuck in error loops, rewriting files empty, ignoring GEMINI.md context, being 'terrible at agentic stuff', and in one case catastrophically deleting user data during a file operation (comm-10, comm-11, comm-13, comm-14, comm-15, comm-16). missing for 10: reliable reproduction of bugs, consistent root-cause narrowing without loops, and independent verification of fix correctness.

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Use `/bug` command to report issues directly from the CLI.”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode~partialcommunity5/10

   OpenCode's general coding-agent capabilities (shell/tool execution, LSP integration, a read-only 'explore' agent, and a 'plan' agent for analysis without changes) imply support for investigating bugs and iterating on fixes, and community feedback confirms strong LSP-based codebase navigation. However, there is no explicit documentation of a reproduce/debug/verify workflow, test running, or root-cause tooling, and community reports cite failed tool calls and agents getting stuck on long sessions, undermining reliability for this exact workflow. Missing for 10: explicit debugging/test-execution documentation, first-party guidance on reproducing bugs or verifying fixes, and independent hands-on confirmation of successful root-cause workflows.

   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

Marketplace

1. developerEquip the agent with custom skills to perform specialized tasks

   weight 1 · round to OpenCode
   Gemini CLI~partialcommunity6/10

   Gemini CLI supports extensibility through MCP servers (custom tools, media generation) and GEMINI.md context files to tailor agent behavior for specific projects, and a community mention references a built-in 'skills runtime' as part of its architecture. However, there is no dedicated first-party 'skills' marketplace or packaging system, and community reports note GEMINI.md is sometimes ignored in practice. Missing for 10: a documented first-class 'skills' framework/marketplace, independent corroboration that custom skills work reliably, and confirmation that the skills runtime mentioned in community feedback is a stable, documented feature.

   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [community] “All in all, a 140 MB Go binary with its own browser control stack, sandbox, Git, language detector, skills runtime, and subagent system. I'm…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

   OpenCode✓fullcommunity8/10

   OpenCode has a dedicated 'Agent Skills' feature that lets it discover reusable, on-demand instructions from repo or home directory via a native `skill` tool, directly matching the custom-skills story, and this is corroborated by community praise for its subagents/customizability. Missing for 10: no independent hands-on report specifically testing custom skill authoring/loading, and no detail on skill packaging/sharing ecosystem.

   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory. Skills are loaded on-demand via the native `skill…”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory.”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”

   proof ↗⚑ flag

2. engineering-leadIntegrate third-party partner-built agent apps into my workflows

   weight 1 · round drawn
   Gemini CLI~partialclaimed5/10

   Gemini CLI supports connecting external capabilities via MCP servers (e.g., Imagen, Veo, Lyria) and integrates with GitHub via @gemini-cli mentions and Actions, showing some ecosystem extensibility for third-party tools. However, there's no evidence of a curated marketplace or directory of partner-built 'agent apps' specifically designed for cross-workflow integration, only generic MCP server configuration support. Missing for 10: a documented partner/agent-app ecosystem or marketplace, case studies of third-party agent apps being integrated, and independent confirmation of smooth interoperability.

   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [github] “@github List my open pull requests”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   proof ↗⚑ flag

   OpenCode~partialclaimed5/10

   OpenCode supports MCP (local/remote servers) to add external tools, has an SDK/headless server for programmatic integrations, and GitHub Actions integration—these enable connecting third-party agent apps/tools into workflows. However, there's no evidence of a curated partner marketplace or vendor-vetted third-party 'agent apps' ecosystem beyond generic MCP/tool integration. missing for 10: a documented partner/marketplace ecosystem of pre-built third-party agent apps, case studies of integrating named partner agents, and independent verification of such integrations working smoothly.

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”

   proof ↗⚑ flag

Team knowledge

1. engineering-leadCreate a shared workspace from my docs and repos as a common source of truth for the team

   weight 1 · round drawn
   Gemini CLI—none0/10

   Gemini CLI offers per-project GEMINI.md context files and --include-directories for local context, but there is no evidence of a shared, centrally managed team workspace combining docs and repos as a common source of truth across a team.

   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [github] “gemini --include-directories ../lib,../docs”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

   OpenCode—none0/10

   OpenCode offers session share links, repo-based 'agent skills', and enterprise SSO/config, but there is no evidence of a dedicated shared workspace feature that ingests both docs and repos into a common, persistent team source of truth — these are separate, ad-hoc mechanisms rather than a unified workspace.

   ⚑ flag

Tool integration

1. developerConnect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context

   weight 3 · round drawn
   Gemini CLI~partialclaimed5/10

   Gemini CLI supports connecting MCP servers to add custom tools/capabilities (gh-5, gh-19), which is the generic mechanism that could extend context to third-party services, but the evidence never mentions Jira, Slack, or Google Drive specifically or any pre-built connectors for them. Missing for 10: named/official Jira, Slack, or Google Drive integrations or MCP servers, and any documented example of using these workflow tools with Gemini CLI.

   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”

   proof ↗⚑ flag

   OpenCode~partialclaimed5/10

   OpenCode supports MCP for adding external tools (local and remote servers), which is the generic mechanism by which one could connect Jira/Slack/Google Drive-type integrations, but there is no direct first-party or community evidence of specific Jira, Slack, or Google Drive connectors or integrations. missing for 10: named first-party or community-verified MCP servers/integrations for Jira, Slack, or Google Drive specifically, and any evidence of workflow-tool context extension beyond generic MCP support.

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the Model Context Protocol, or MCP.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP.”

   proof ↗⚑ flag

2. developerKick off agent tasks directly from GitHub, GitLab, Linear, or Slack

   weight 2 · round drawn
   Gemini CLI~partialclaimed4/10

   Gemini CLI has a documented GitHub integration (GitHub Action/App) that lets developers trigger tasks via @gemini-cli mentions in issues/PRs, automated PR reviews, and issue triage, but there is no evidence of native GitLab, Linear, or Slack integrations for kicking off agent tasks. missing for 10: GitLab integration, Linear integration, Slack integration, independent corroboration of GitHub workflow reliability

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “@github List my open pull requests”
   • [github] “Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   proof ↗⚑ flag

   OpenCode~partialclaimed4/10

   OpenCode has documented GitHub integration where mentioning /opencode or /oc in a comment triggers tasks in GitHub Actions, including issue-to-PR workflows, but there is no evidence of native GitLab, Linear, or Slack integrations for kicking off agent tasks. missing for 10: GitLab integration, Linear integration, Slack integration, independent hands-on confirmation of the GitHub Actions flow working reliably.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”

   proof ↗⚑ flag

Cross device continuity

1. developerStart a task on one device and continue it later from another device or browser

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   Gemini CLI offers local conversation checkpointing to save/resume sessions (gh-8) and can run in Cloud Shell (docs-1), but there is no evidence of cloud-synced session state that lets a developer start a task on one device/terminal and pick it up seamlessly on another device or browser. missing for 10: cross-device session sync, browser-based continuation of an existing CLI session, any documented mechanism to transfer checkpoint state between machines.

   • [github] “Conversation checkpointing to save and resume complex sessions”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”

   proof ↗⚑ flag

   OpenCode~partialcommunity6/10

   OpenCode supports remote/headless usage via `opencode serve` plus a TUI that can connect to a remote backend, share links for sessions, and a WebUI that can connect to multiple backends from anywhere (including mobile), which enables cross-device continuation of a session. However, this requires manual server setup rather than seamless native cloud sync, and community reports note bugs restoring session state and provider/model selection issues across sessions. missing for 10: first-party seamless cross-device sync without self-hosting a server, official mobile app, and clear documentation/evidence of resuming full task state (not just session sharing) across devices.

   • [claimed-docs] “This allows using the TUI with a remote OpenCode backend.”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

Ide integration

1. developerView interactive diffs and share selected code as context from within my JetBrains IDE

   weight 1 · round drawn
   Gemini CLI—none0/10

   No evidence mentions JetBrains IDE integration, interactive diffs, or sharing code context from within an IDE for Gemini CLI; evidence pack only covers terminal/CLI usage, GitHub Actions, and MCP servers.

   ⚑ flag

   OpenCode—none0/10

   Evidence only shows OpenCode integrating with VS Code, Cursor, or 'any IDE that supports a terminal' via keyboard shortcuts for split-terminal view and inserting file references; there is no mention of a JetBrains-specific plugin, interactive diff viewer, or JetBrains context-sharing UI. missing for 10: JetBrains plugin/extension documentation, interactive diff rendering inside JetBrains, JetBrains-specific 'share selected code' mechanism.

   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal. Just run `opencode` in the terminal to get started.”
   • [claimed-docs] “Use Cmd+Esc (Mac) or Ctrl+Esc (Windows/Linux) to open OpenCode in a split terminal view”
   • [claimed-docs] “Use Cmd+Option+K (Mac) or Alt+Ctrl+K (Linux/Windows) to insert file references.”
   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal.”
   • [claimed-docs] “Use `Cmd+Esc` (Mac) or `Ctrl+Esc` (Windows/Linux) to open OpenCode in a split terminal view”
   • [claimed-docs] “Use `Cmd+Option+K` (Mac) or `Alt+Ctrl+K` (Linux/Windows) to insert file references.”

   proof ↗⚑ flag

2. developerChat with the coding assistant directly inside my IDE for contextual help

   weight 3 · round to OpenCode
   Gemini CLI—none0/10

   The evidence pack describes Gemini CLI as a terminal-based agent (context files, MCP servers, Cloud Shell access) but contains no mention of an IDE extension, sidebar chat, or in-editor contextual panel that would let a developer chat with it directly inside an IDE. Community threads discuss its terminal/agentic performance, not IDE integration.

   ⚑ flag

   OpenCode✓fullcommunity8/10

   OpenCode ships an IDE extension and integrates directly in VS Code/Cursor with in-editor shortcuts (split terminal view, file-reference insertion) for contextual chat, and community users confirm using it as their daily coding harness with LSP integration inside editors. Missing for 10: independent hands-on review specifically of the IDE-extension chat UX (most community feedback is TUI/CLI-focused) and no screenshots/deep detail on in-IDE chat UI beyond shortcuts.

   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal. Just run `opencode` in the terminal to get started.”
   • [claimed-docs] “Any editor Available as a terminal interface, desktop app, and IDE extension”
   • [claimed-docs] “Use Cmd+Esc (Mac) or Ctrl+Esc (Windows/Linux) to open OpenCode in a split terminal view”
   • [claimed-docs] “Use Cmd+Option+K (Mac) or Alt+Ctrl+K (Linux/Windows) to insert file references.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”

   proof ↗⚑ flag

Session management

1. engineering-leadManage multiple agent-driven coding sessions from one unified workspace

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   Evidence shows single-session features (conversation checkpointing to save/resume one session, GEGEMINI.md context files) but nothing about running or coordinating multiple concurrent agent sessions from one unified dashboard/workspace for a lead overseeing a team's work. missing for 10: multi-session dashboard/orchestration UI, evidence of concurrent session management, any lead-oriented workspace view.

   • [github] “Conversation checkpointing to save and resume complex sessions”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”

   proof ↗⚑ flag

   OpenCode✓fullcommunity8/10

   OpenCode explicitly supports multi-session workflows ('Start multiple agents in parallel on the same project'), tabs for desktop, share links for sessions, and a headless server that a WebUI can connect to across multiple backends, which community evidence corroborates ('WebUI... can connect to multiple OpenCode backends at once'). This directly matches an engineering-lead managing multiple agent sessions from one unified workspace. Missing for 10: no first-party documentation of team/organization-level oversight (e.g., viewing/managing sessions started by other engineers) and some reported bugs in session state restoration temper reliability.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Introducing tabs for desktop. Available on macOS, Windows, and Linux.”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

Terminal workflow

1. developerRun a coding agent locally from my terminal

   weight 3 · round to OpenCode
   Gemini CLI✓fullcommunity8/10

   Gemini CLI is a terminal-native coding agent with first-party docs (gemini-cli-gh-1 through -20, gemini-cli-docs-1/2/3) describing running locally, querying/editing codebases, non-interactive scripting, and Cloud Shell availability with no extra setup, and abundant community evidence (gemini-cli-comm-1, -9, -12) confirms real-world local terminal usage. Missing for 10: independent benchmark of reliability (several community reports of agentic failures/loops, e.g. gemini-cli-comm-10, -11, -14) and no first-party install/runtime docs beyond GitHub README excerpts.

   • [github] “Query and edit large codebases”
   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “gemini --include-directories ../lib,../docs”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “The correct way of using Gemini CLI is: ABUSE IT! With 1M Context Window (soon 2M) and generous daily free quota are huge advantages.”

   proof ↗⚑ flag

   OpenCode✓fullprobed9/10

   OpenCode is explicitly a terminal-based coding agent, installable via curl/npm, run with `opencode` command in any terminal, with rich CLI docs and confirmed hands-on community usage as a daily local terminal harness. Missing for 10: no independent benchmark/security audit fully vetting the terminal experience beyond anecdotal reports (some report TUI compatibility bugs on specific setups).

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal. Just run `opencode` in the terminal to get started.”
   • [claimed-docs] “curl -fsSL https://opencode.ai/install | bash”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal.”
   • [probe] “official CLI documented at https://opencode.ai/docs/cli/”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”

   proof ↗⚑ flag

2. developerRun the agent non-interactively in scripts for workflow automation

   weight 2 · round to Gemini CLI
   Gemini CLI✓fullclaimed9/10

   Gemini CLI explicitly documents non-interactive scripting support with structured output flags (--output-format json / stream-json) and lists 'Run non-interactively in scripts for workflow automation' as a core feature; GitHub Actions integration for PR review/issue triage further evidences automation use cases. Missing for 10: independent hands-on validation specifically of scripting/automation workflows (community feedback focuses on interactive agent quality, not scripted use).

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”

   proof ↗⚑ flag

   OpenCode✓fullclaimed8/10

   The `opencode run` CLI command explicitly supports non-interactive one-shot execution (e.g. `opencode run "Explain how closures work"`), and `--auto` flag auto-approves permissions for unattended runs, plus `opencode serve` exposes a headless HTTP/OpenAPI server and JS/TS SDK for scripted/programmatic control, all fitting workflow automation. Missing for 10: independent hands-on evidence of non-interactive scripting reliability/CI use, and no dedicated exit-code/output-format docs for pipeline integration.

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “Start OpenCode with --auto to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Attach a terminal to an already running OpenCode backend server started via `serve` or `web` commands.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to OpenCode
   Gemini CLI~partialprobed5/10

   Gemini CLI supports non-interactive scripting and structured JSON/stream-JSON output (gh-6, gh-17, gh-18), suggesting most interactive capabilities can be invoked programmatically for automation. However, there's no explicit documentation confirming full feature parity between interactive sessions and scripted/API use, and probes found no formal API/OpenAPI spec (probe-1, probe-2), so completeness of parity is unverified. Missing for 10: explicit parity documentation, a formal API surface beyond CLI flags, and independent confirmation that all UI/interactive features (e.g., checkpointing, MCP tool use) are scriptable identically.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

   OpenCode~partialprobed6/10

   OpenCode ships a headless server (`opencode serve`) exposing a documented OpenAPI spec (confirmed live at openapi.json) plus a JS/TS SDK explicitly for 'building integrations and controlling opencode programmatically,' and the TUI/WebUI can drive a remote backend — community confirms this works day-to-day including from mobile. However, no evidence explicitly enumerates full feature parity (e.g., agent skill management, permission config, enterprise SSO settings) as exposed via the API/SDK, and there's no independent audit confirming 1:1 UI/API parity. missing for 10: explicit parity documentation covering all UI-only features (skills, permission prompts, enterprise SSO), independent verification of full API coverage.

   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “This allows using the TUI with a remote OpenCode backend.”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round drawn
   Gemini CLI—none0/10

   No evidence of any data export feature or open-format data portability in Gemini CLI; the tool is a local coding agent that reads/writes local files but nothing indicates exporting conversation history, settings, or usage data in an open format for user-controlled exit. Probes for llms.txt/openapi also failed, showing no structured data-access surface.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

   OpenCode—none0/10

   No evidence describes an explicit data-export feature or open-format portability guarantee for OpenCode; while it is open-source and stores config/sessions locally, there's no documented 'export all my data and leave' capability, and community threads even note telemetry sent to OpenCode's own servers with no way to disable it (opencode-comm-2), undercutting a clean data-portability story.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to OpenCode
   Gemini CLI~partialprobed5/10

   The product's source is hosted publicly at github.com/google-gemini/gemini-cli (referenced repeatedly across the evidence pack), implying open availability for reading, but no citation in the evidence pack explicitly names or confirms an open-source license (e.g., Apache/MIT) or points to a LICENSE file. Missing for 10: explicit license text/citation, confirmation of license type, and any independent corroboration of open-license terms.

   • [github] “Query and edit large codebases”
   • [github] “Use `/bug` command to report issues directly from the CLI.”
   • [probe] “official CLI documented at https://developers.google.com/gemini-code-assist/docs/gemini-cli”

   proof ↗⚑ flag

   OpenCode✓fullcommunity7/10

   OpenCode's docs explicitly describe it as "open source" and a public GitHub repo exists (opencode-gh-1), and community members confirm they read and learned from the actual source code (opencode-comm-6), corroborating that the source is genuinely accessible. missing for 10: explicit citation of the license name/type (e.g., MIT/Apache) in the evidence pack, and a first-party statement pointing to the license file itself.

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [github] “OpenCode is also available as a desktop application.”
   • [community] “OpenCode source code is even more awesome. I have learned so much from the way they have organized tools, agents, settings and prompts. mode…”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to OpenCode
   Gemini CLI—none0/10

   Gemini CLI is an open-source client, but the core product (the Gemini models/backend) is a Google-hosted cloud service accessed via Google account sign-in; no evidence anywhere in the pack describes a self-hosted or on-prem deployment option for the core model/service.

   • [github] “No API key management - just sign in with your Google account”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”

   proof ↗⚑ flag

   OpenCode✓fullprobed8/10

   OpenCode is open source and installable via CLI, with a documented `opencode serve` headless HTTP server exposing an OpenAPI endpoint, plus SDK and remote/TUI client support, enabling full self-hosting of the core agent; community evidence confirms real-world self-hosted use ('opencode serve' accessible remotely) though also flags security hardening gaps around the server. missing for 10: independent audit confirming production-grade self-hosted security, and clearer official self-hosting/deployment guide beyond the serve command docs.

   • [claimed-docs] “curl -fsSL https://opencode.ai/install | bash”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “Attach a terminal to an already running OpenCode backend server started via `serve` or `web` commands.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”
   • [community] “When server is enabled, any web page served from localhost/127.0.0.1 can execute code; any local process can execute code without authentica…”

   proof ↗⚑ flag

Authentication

1. developerAuthenticate with an API key instead of an account login

   weight 2 · round to OpenCode
   Gemini CLI~partialclaimed4/10

   The docs emphasize signing in with a Google account (gh-13) as the primary flow, but they also note that developers needing 'specific model control or paid tier access' (gh-24) have an alternative path, implying API-key-based auth exists without detailing it. There's no explicit example or setup instructions for API-key authentication itself. Missing for 10: explicit API key env-var/config documentation, first-party steps for key-based auth, and independent confirmation it works without Google login.

   • [github] “No API key management - just sign in with your Google account”
   • [github] “Developers who need specific model control or paid tier access”

   proof ↗⚑ flag

   OpenCode✓fullclaimed8/10

   OpenCode explicitly supports configuring API keys for any LLM provider as an alternative to logging in via account-based options like GitHub Copilot or ChatGPT Plus/Pro, giving developers a direct API-key auth path rather than requiring account login. Missing for 10: independent hands-on confirmation of the API key setup flow itself and details on key storage/security beyond docs claims.

   • [claimed-docs] “With OpenCode you can use any LLM provider by configuring their API keys.”
   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [claimed-docs] “OpenCode Zen is a list of tested and verified models provided by the OpenCode team.”

   proof ↗⚑ flag

2. engineering-leadAuthenticate through an enterprise identity or cloud platform for compliance and scalability

   weight 2 · round to OpenCode
   Gemini CLI!disputedcontradicted4/10

   Google claims 'Enterprise features: Advanced security and compliance' and frictionless Google-account sign-in without API key management, plus Cloud Shell availability, suggesting cloud/enterprise identity support. However, a hands-on community report shows authentication explicitly failing for Workspace (enterprise) accounts ('Failed to login. Ensure your Google account is not a Workspace account'), directly contradicting the enterprise-identity claim for a core scenario. Missing for 10: documented enterprise SSO/IAM integration details, confirmation Workspace login issue is resolved, and independent verification of compliance certifications.

   • [github] “No API key management - just sign in with your Google account”
   • [github] “Enterprise features: Advanced security and compliance”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' I have had a Workspace account since GSuite and now as a Workspace…”

   proof ↗⚑ flag

   OpenCode~partialclaimed6/10

   OpenCode has a documented enterprise config that integrates with SSO and enforces a centralized internal AI gateway, directly addressing enterprise identity/compliance needs, and supports login via GitHub Copilot/OpenAI accounts. However, there's no independent corroboration of this enterprise SSO feature in practice, no detail on supported identity providers (SAML/OIDC specifics), and community discussion focuses on telemetry/security concerns rather than confirming enterprise auth workflows. Missing for 10: independent/hands-on validation of SSO integration, details on supported IdPs, and evidence of enterprise customers actually using this for compliance/scalability.

   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”
   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”

   proof ↗⚑ flag

3. developerSign in with my existing product subscription plan to use the coding agent

   weight 2 · round to OpenCode
   Gemini CLI!disputedcontradicted4/10

   Gemini CLI advertises frictionless Google-account sign-in with no API key management (gh-13), suggesting subscribers could just log in and go, but hands-on community reports concretely contradict this: a Gemini Pro subscriber found that paying for 'Gemini' doesn't unlock Gemini CLI usage, requiring a separate 'Gemini Code Assist Standard/Enterprise' plan, and another user explicitly asks for one unified subscription across CLI, Code Assist, Jules, etc. like Claude's Max plan. Missing for 10: evidence that an existing Google One/Gemini Advanced subscription actually raises CLI usage limits, and resolution of the reported subscription fragmentation.

   • [github] “No API key management - just sign in with your Google account”
   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber but I learn I should be a 'Gemini Code Assist Standard or Enterpri…”
   • [community] “Again, with the complicated subscription. Please just give us a monthly subscription for developers that I can pay whatever, and then use Ge…”
   • [github] “Developers who need specific model control or paid tier access”

   proof ↗⚑ flag

   OpenCode✓fullcommunity8/10

   OpenCode docs explicitly support signing in with existing subscriptions—GitHub Copilot and ChatGPT Plus/Pro—rather than requiring separate API keys, and community comments confirm using subscriptions (e.g., Codex $200/mo) inside OpenCode. Missing for 10: independent hands-on verification of the Copilot/ChatGPT login flow itself and broader coverage of other subscription providers beyond these two.

   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [claimed-docs] “GitHub Copilot Log in with GitHub to use your Copilot account”
   • [claimed-docs] “ChatGPT Plus/Pro Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [community] “OpenCode is awesome. Claude Code is nothing special at all. Last month I switched to just using OpenCode with a Codex $200/mo subscription, …”

   proof ↗⚑ flag

4. developerSign in with a personal account to get free-tier access without managing API keys

   weight 1 · round drawn
   Gemini CLI✓fullcommunity7/10

   GitHub docs explicitly state 'No API key management - just sign in with your Google account' (gemini-cli-gh-13), directly matching the story, and Cloud Shell docs describe zero-setup access. Community reports don't dispute personal-account sign-in itself (the failure noted is specific to Workspace accounts, an edge case outside 'personal account'), though some users voice confusion over how free vs paid tiers interact. Missing for 10: independent/hands-on confirmation of the free-tier quota limits and clearer documentation distinguishing personal free-tier access from paid Code Assist tiers.

   • [github] “No API key management - just sign in with your Google account”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber but I learn I should be a 'Gemini Code Assist Standard or Enterpri…”
   • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' I have had a Workspace account since GSuite and now as a Workspace…”

   proof ↗⚑ flag

   OpenCode✓fullcommunity7/10

   OpenCode's docs explicitly offer 'Log in with GitHub to use your Copilot account' and 'Log in with OpenAI to use your ChatGPT Plus or Pro account,' letting a developer authenticate with an existing personal subscription instead of managing provider API keys, and OpenCode Zen is noted to include a free coding model. Missing for 10: independent/hands-on user reports specifically confirming this login flow (community comments focus on API keys/local models, not the Copilot/ChatGPT login path), and clarity on any usage limits tied to the free tier.

   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [claimed-docs] “GitHub Copilot Log in with GitHub to use your Copilot account”
   • [claimed-docs] “ChatGPT Plus/Pro Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [community] “OpenCode source code is even more awesome. I have learned so much from the way they have organized tools, agents, settings and prompts. mode…”

   proof ↗⚑ flag

Model choice

1. developerLet the tool automatically pick the best model for each task

   weight 1 · round drawn
   Gemini CLI—none0/10

   Evidence shows manual model selection ('Choose specific Gemini models' for 'developers who need specific model control') rather than automatic task-based model selection; no evidence of the CLI auto-choosing the optimal model per task.

   • [github] “Model selection: Choose specific Gemini models”
   • [github] “Developers who need specific model control or paid tier access”

   proof ↗⚑ flag

   OpenCode—none0/10

   Evidence shows OpenCode supports many providers/models and lets users manually assign a model per agent or switch via Tab, but nothing indicates the tool automatically selects the optimal model for a given task — community feedback even confirms model/provider choice is manual and sometimes annoying to manage across sessions.

   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”
   • [claimed-docs] “You can use the Tab key to switch between primary agents during a session.”
   • [claimed-docs] “75+ LLM providers through Models.dev, including local models”

   proof ↗⚑ flag

2. developerChoose which underlying AI model powers my session from multiple providers

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   Evidence shows Gemini CLI only supports choosing among Google's own Gemini models (gh-14, gh-24), not switching between different AI providers (e.g., OpenAI, Anthropic); community complaints (comm-2, comm-3, comm-19) reinforce that it's locked to Google's ecosystem/billing. There is no evidence of multi-provider model selection, so the story as written (choosing from multiple providers) is not delivered.

   • [github] “Model selection: Choose specific Gemini models”
   • [github] “Developers who need specific model control or paid tier access”
   • [community] “The killer feature of Claude Code is that you can just pay for Max and not worry about API billing. Until Gemini does that, I'm sticking wit…”
   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber but I learn I should be a 'Gemini Code Assist Standard or Enterpri…”
   • [community] “Again, with the complicated subscription. Please just give us a monthly subscription for developers that I can pay whatever, and then use Ge…”

   proof ↗⚑ flag

   OpenCode✓fullcommunity9/10

   OpenCode explicitly supports configuring any LLM provider via API keys, lists 75+ providers through Models.dev including local models, offers a curated OpenCode Zen model list, and supports logging in with GitHub Copilot or ChatGPT Plus/Pro accounts. Community evidence corroborates real-world use with multiple providers (Claude, Gemini, local llama.cpp, Qwen) and per-agent model selection. Missing for 10: some community reports note model/provider switching across sessions can be buggy or annoying, a minor UX caveat.

   • [claimed-docs] “With OpenCode you can use any LLM provider by configuring their API keys.”
   • [claimed-docs] “OpenCode Zen is a list of tested and verified models provided by the OpenCode team.”
   • [claimed-docs] “75+ LLM providers through Models.dev, including local models”
   • [claimed-docs] “Any model 75+ LLM providers through Models.dev, including local models”
   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Gemini CLI—none0/10

   No evidence in the pack mentions data residency, regional storage options, or configurable data location controls for Gemini CLI; only enterprise 'security and compliance' features are mentioned generically without specifics.

   ⚑ flag

   OpenCode—none0/10

   No evidence anywhere in the pack of a region/residency selection feature for data storage; OpenCode's docs focus on provider choice, self-hosting, and enterprise SSO, none of which address data residency. In fact, community reports indicate telemetry is always sent to OpenCode's own servers with no way to disable it, further suggesting the user lacks control over where certain data goes.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Gemini CLI—none0/10

   No evidence in the pack addresses data usage/training opt-out policies, privacy controls, or terms governing whether user data trains Google's models; only unrelated feature/community commentary is present. Missing for 10: explicit data-usage/training policy documentation, opt-out mechanism, enterprise/no-training guarantee.

   ⚑ flag

   OpenCode—none0/10

   The evidence pack contains no documentation of any setting, policy, or opt-out mechanism for preventing user data/code from being used to train AI models (OpenCode's docs focus on providers, agents, permissions, IDE integration, etc., none addressing training-data usage). Community evidence actually suggests the opposite direction of concern: telemetry is sent to OpenCode's own servers even with locally-hosted models with no way to disable it, which further undermines confidence that user data is protected from being retained/used.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Gemini CLI—none0/10

   No evidence pack items address data retention controls, deletion mechanisms, or privacy settings for Gemini CLI; only enterprise 'security and compliance' is vaguely mentioned without specifics. Missing for 10: documentation on data retention policy, user-controlled deletion mechanism, opt-out of data collection, and any privacy settings UI/CLI flags.

   ⚑ flag

   OpenCode—none0/10

   No documentation describes any data retention or deletion controls, and community evidence indicates the opposite: OpenCode sends telemetry to its own servers even with local models, with no environment variables or flags to disable it, suggesting no user-facing data controls exist.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round to OpenCode
   Gemini CLI—none0/10

   No evidence in the pack mentions telemetry settings, opt-out flags, or usage-data collection policy for Gemini CLI. Missing for 10: any documentation of a telemetry/usage-tracking toggle, privacy settings, or opt-out mechanism.

   ⚑ flag

   OpenCode!disputedcontradicted2/10

   OpenCode's docs make no mention of a telemetry opt-out setting, and a community report explicitly states OpenCode sends telemetry to its own servers even with locally hosted models, with no environment variables, flags, or config options to disable it. This is a first-party-vs-hands-on-evidence conflict: no documented opt-out mechanism exists, and independent evidence claims none is available. missing for 10: any official docs describing a telemetry toggle/opt-out, first-party acknowledgment of telemetry collection, and any evidence the reported issue was fixed.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”

   proof ↗⚑ flag

Data governance

1. engineering-leadOpt out of having my code and prompts used for AI model training

   weight 1 · round drawn
   Gemini CLI—none0/10

   No evidence in the pack addresses data usage, training opt-out policies, or privacy controls for Gemini CLI; only feature lists and general community sentiment are present. missing for 10: any documentation of data usage/training policy, opt-out settings or enterprise privacy controls, and independent confirmation of such settings working.

   ⚑ flag

   OpenCode—none0/10

   No documentation exists describing a training-data opt-out or data-use policy for prompts/code; in fact community evidence indicates OpenCode sends telemetry to its own servers with no way to disable it, even when using local models, suggesting the opposite of user control over data usage.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

Pr review

1. developerHave the agent stage changes, write commit messages, create branches, and open pull requests

   weight 3 · round to OpenCode
   Gemini CLI~partialclaimed4/10

   Evidence shows Gemini CLI can automate git-related operational tasks like querying pull requests and handling complex rebases, and its GitHub Action can do automated PR reviews and issue triage, but there's no explicit documentation of the agent staging changes, writing commit messages, creating branches, or opening new pull requests itself. Missing for 10: explicit commit-message generation, branch creation, and PR-opening workflow evidence, plus independent confirmation these work reliably.

   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “@github List my open pull requests”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   proof ↗⚑ flag

   OpenCode~partialclaimed6/10

   Docs explicitly describe GitHub integration where OpenCode 'will work in a new branch and submits a PR with all the changes' and can execute tasks via mentions in GitHub Actions, covering branch creation and PR opening; permission config also governs whether actions like git operations auto-run or prompt. However, there's no explicit mention of staging changes or generating commit messages as a distinct capability, and no independent/community evidence corroborates the PR-creation workflow in practice. missing for 10: explicit documentation of commit message generation/staging step, independent hands-on verification of the branch+PR workflow.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”

   proof ↗⚑ flag

2. developerGet automatic code review with contextual feedback on every pull request

   weight 3 · round to Gemini CLI
   Gemini CLI✓fullcommunity8/10

   Gemini CLI's GitHub Actions integration explicitly provides automated PR code review with contextual feedback and suggestions, plus on-demand @gemini-cli assistance in PRs, and community reports corroborate favorable code review quality compared to competitors. Missing for 10: independent hands-on verification of the PR-review workflow specifically (most community feedback covers general CLI agentic use rather than the PR-review action itself), and no detail on configurability/false-positive rates.

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “@github List my open pull requests”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”

   proof ↗⚑ flag

   OpenCode~partialclaimed4/10

   OpenCode has a GitHub Actions integration (mention /opencode or /oc in a comment) and a read-only 'plan' agent that can review/suggest changes without modifying code, which can be used for PR feedback, but this requires an explicit manual mention rather than automatically triggering contextual review on every PR. Missing for 10: documented automatic/triggerless review on every new PR, evidence of inline contextual comments on diffs, and independent confirmation of this review workflow in practice.

   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”

   proof ↗⚑ flag

3. developerInspect diffs and run checks to catch problems before merging

   weight 3 · round to Gemini CLI
   Gemini CLI~partialcommunity6/10

   Gemini CLI supports GitHub PR review automation with contextual feedback (gemini-cli-gh-10) and issue triage, plus community reports confirm it catches bugs reviewers missed (gemini-cli-comm-20), supporting diff inspection and pre-merge checks. However, there's no dedicated diff-viewing UI or built-in test/lint-running check suite documented, and community reports raise concerns about reliability, security prompts, and agentic mistakes (gemini-cli-comm-14, gemini-cli-comm-17). missing for 10: dedicated diff-inspection UI/commands, built-in CI/test-running integration, and stronger independent corroboration of reliability for pre-merge checks.

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “However, it does seem that Gemini pays less attention to security than Claude Code. Gemini will happily open in my root directory. Claude Co…”

   proof ↗⚑ flag

   OpenCode~partialclaimed4/10

   OpenCode offers a read-only 'plan' agent for reviewing suggested changes without applying them and a permission system that can prompt before actions run, plus GitHub PR/Actions integration for submitting changes — these provide some review-safety scaffolding. However there is no documented diff-viewing UI or built-in test/lint/check-running capability before merge. Missing for 10: explicit diff inspection tooling, integrated test/lint/CI check execution, and independent evidence that these safety mechanisms actually prevent bad merges.

   • [claimed-docs] “Use the plan agent to analyze code and review suggestions without making any code changes.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”

   proof ↗⚑ flag

Safe execution

1. engineering-leadControl which external tools and integrations the agent is allowed to access

   weight 2 · round to OpenCode
   Gemini CLI~partialcommunity5/10

   Gemini CLI supports configuring MCP servers via ~/.gemini/settings.json and exposes /tools and /mcp commands to inspect and manage available tools, giving engineering leads some control over which integrations are enabled. However, evidence lacks any centralized admin/policy control, allowlist/denylist enforcement, or org-wide governance mechanism for restricting tool access across a team, and community reports note weak security defaults (e.g. opening root directories without prompting). missing for 10: org-level/admin enforcement of tool allowlists, granular permission scoping per tool/integration, independent verification that access controls are robust rather than just configurable per-user.

   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”
   • [community] “However, it does seem that Gemini pays less attention to security than Claude Code. Gemini will happily open in my root directory. Claude Co…”

   proof ↗⚑ flag

   OpenCode✓fullclaimed8/10

   OpenCode's permission system lets leads set actions to auto-run, prompt, or block per tool/input, and MCP servers (external tools) are explicitly added/configured (docs-4/23/41). Enterprise config also lets orgs force use of an internal AI gateway and SSO, further restricting what integrations agents can reach (docs-33/50). Missing for 10: independent/hands-on confirmation that permission rules reliably block disallowed MCP tool calls in practice, and finer detail on allow/deny lists for specific external tool names beyond the general permission object.

   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “OpenCode uses the permission config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with --auto to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “For most permissions, you can use an object to apply different actions based on the tool input.”
   • [claimed-docs] “Use external_directory to allow tool calls that touch paths outside the working directory where OpenCode was started.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the Model Context Protocol, or MCP.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP.”
   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”
   • [claimed-docs] “Through the central config, OpenCode can integrate with your organization’s SSO provider for authentication.”

   proof ↗⚑ flag

2. engineering-leadHave the agent operate inside a sandbox when interacting with code, tools, and network resources

   weight 2 · round drawn
   Gemini CLI—none0/10

   The evidence pack contains no vendor documentation of a sandboxed execution mode for code/tool/network interactions—only a vague 'Enterprise features: Advanced security and compliance' bullet with no detail. Community evidence actually points the other way: reviewers note Gemini CLI 'happily opens in my root directory' without any directory-trust prompt, unlike Claude Code, and one report describes it destructively running file-system commands, suggesting a lack of sandboxing guardrails rather than presence of them.

   • [github] “Enterprise features: Advanced security and compliance”
   • [community] “However, it does seem that Gemini pays less attention to security than Claude Code. Gemini will happily open in my root directory. Claude Co…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

   OpenCode—none0/10

   OpenCode's documentation only describes a permission system (auto-approve/prompt/block) and an 'external_directory' toggle for path access — not an isolated sandbox for code execution, tool calls, or network access. Community evidence (opencode-comm-18) even flags that the local server mode allows any local process or webpage to execute code without authentication, the opposite of sandboxed isolation, and there is no first-party claim of container/VM-based sandboxing to dispute.

   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “Use external_directory to allow tool calls that touch paths outside the working directory where OpenCode was started.”
   • [community] “When server is enabled, any web page served from localhost/127.0.0.1 can execute code; any local process can execute code without authentica…”

   proof ↗⚑ flag

Security checks

1. engineering-leadSee license and public-code matching references for AI-suggested code

   weight 1 · round drawn
   Gemini CLI—none0/10

   No evidence anywhere in the pack of license attribution, public-code matching, or provenance references for AI-suggested code; features listed cover code editing, review, MCP, PR automation, etc. but nothing about license/originality detection.

   ⚑ flag

   OpenCode—none0/10

   No evidence of any license or public-code matching/attribution feature for AI-suggested code in OpenCode's docs or community reports; the product focuses on agent workflows, permissions, and MCP integration but nothing about code provenance or license scanning.

   ⚑ flag

2. developerGet contextual explanations and automatic fixes for security vulnerabilities

   weight 2 · round to Gemini CLI
   Gemini CLI~partialclaimed4/10

   Gemini CLI offers general debugging/explanation via natural language (gh-3, gh-12) and automated PR review with 'contextual feedback and suggestions' (gh-10), plus vague 'enterprise advanced security and compliance' (gh-15), which could incidentally surface and explain security issues, but there is no evidence of a dedicated vulnerability-scanning or automatic-fix feature specifically for security flaws. Missing for 10: explicit vulnerability detection/scanning capability, documented automatic remediation of security issues, and independent verification that PR reviews catch/fix security vulnerabilities specifically.

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Enterprise features: Advanced security and compliance”

   proof ↗⚑ flag

   OpenCode—none0/10

   OpenCode is a general coding agent with plan/explore/build agents and permission controls, but no evidence describes any security-vulnerability scanning, contextual vulnerability explanations, or automatic security fix generation as a feature. Community evidence even highlights unresolved security reports and vulnerabilities in OpenCode itself, not a capability to detect/fix vulnerabilities in user code.

   ⚑ flag