Access
Install
npm install -g @google/gemini-cliShowcase


Products
Google, product by product →Google ships more than one product — each judged line competes in its own arena on the same stories as everyone else.
| Line | Arena | Rank | PA Score | Agent-ready |
|---|---|---|---|---|
| Gemini | AI Assistants | #7/9 | 17/100 | 9/100 |
| Antigravity | AI Coding Agents | #5/13 | 37/100 | 55/100 |
| Gemini CLIthis page | AI Coding Agents | #12/13 | 21/100 | 38/100 |
| Gemini Notebook (NotebookLM) | AI Research Agents | #6/6 | 7/100 | 0/100 |
| Jules | Software Factory | #7/9 | 23/100 | 29/100 |
| Agent Development Kit | Agent Frameworks & SDKs | #4/9 | 35/100 | 46/100 |
| Firebase | Backend as a Service | #3/4 | 35/100 | 43/100 |
| Angular | Frontend Frameworks | #3/5 | 28/100 | 12/100 |
Not yet judged (4 — no arena where they compete): Google AI Studio · Flow · Gemini in Chrome · Gemini Code Assist
Verified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Autonomy agents — stories about autonomy agents in this arenaAutonomy agentsevidence →
Stories about autonomy agents in this arena
Code generation — quality of generated code — correctness, style, fit to the codebaseCode generationevidence →
Quality of generated code — correctness, style, fit to the codebase
Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understandingevidence →
How deeply the tool maps your repo — cross-file context, architecture awareness, history
Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystemevidence →
Integrations, plugins, and third-party ecosystem stories
Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integrationevidence →
Meeting you in the IDE and terminal — extensions, inline flows, context
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limitsevidence →
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safetyevidence →
Keeping generated changes safe — diffs, approvals, guardrails
Story verdicts — every judged story with its evidenceStory verdicts
What’s free: 2 free · 0 paid · 0 enterprise · 28 not stated in evidence
Follow the green: where the map greys out is where Gemini CLI stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
~5/10
unlocks → Webhooks · Official SDKs · Scoped API keys · Machine-readable spec · Versioning policy · API sandbox · Full data export · Configure a reproducible cloud environment with the dependencies and setup steps my repository needs · Launch fleets of autonomous agents that work in parallel on different tasks for hours or days · Run several task attempts in parallel and compare results before choosing one · Start a task on one device and continue it later from another device or browser · View interactive diffs and share selected code as context from within my JetBrains IDE · Chat with the coding assistant directly inside my IDE for contextual help · Manage multiple agent-driven coding sessions from one unified workspace
Subscribe to events via webhooks
—0/10
Build against official SDKs
—0/10
Issue scoped/least-privilege API credentials for an agent
—0/10
Connect an agent via an official MCP server
n/an/a
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
—–
Explore an interactive API reference with runnable examples
—0/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
—0/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
!5/10
Operate the product with natural-language commands
!5/10
Plug MCP servers into this product so it can use their tools
✓8/10
Get AI-generated insights and suggestions from my data inside the product
!5/10
Set up automations that run autonomously in the background
~6/10
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Autonomy agents — stories about autonomy agents in this arenaAutonomy agents
Stories about autonomy agents in this arena
Background execution
Parallel agents
Set up always-on agents that run on schedules or triggers to maintain and fix my software autonomously
~4/10
Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation
Quality of generated code — correctness, style, fit to the codebase
Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding
How deeply the tool maps your repo — cross-file context, architecture awareness, history
Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystem
Integrations, plugins, and third-party ecosystem stories
Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration
Meeting you in the IDE and terminal — extensions, inline flows, context
Start a task on one device and continue it later from another device or browser
—0/10
Ide integration
Session management
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety
Keeping generated changes safe — diffs, approvals, guardrails
Sorted by importance (agentic first) (high → low) · 74/74 stories · click a row’s chevron for the rationale and evidence
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 8/10 | Cclaimed | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | disputed | 5/10 | Dcontradicted | |
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 5/10 | Tprobed | |
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | n/a | untested | none yet | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Cclaimed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Xcommunity | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | disputed | 5/10 | Dcontradicted | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | disputed | 5/10 | Dcontradicted | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | none | untested | none yet | |
Get automatic code review with contextual feedback on every pull request C Pr review | developer | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 3 | full | 8/10 | Xcommunity | |
Run a coding agent locally from my terminal C Terminal workflow | developer | Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration | 3 | fullfree | 8/10 | Xcommunity | |
Inspect diffs and run checks to catch problems before merging C Pr review | developer | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 3 | partial | 6/10 | Xcommunity | |
Add a project instructions file to set coding standards and conventions the agent follows C Context management | developer | Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding | 3 | disputed | 5/10 | Dcontradicted | |
Connect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context C Tool integration | developer | Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystem | 3 | partial | 5/10 | Cclaimed | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | partial | 5/10 | Cclaimed | |
Describe a feature or bug in plain language and have the agent implement or fix it across multiple files C Feature implementation | developer | Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation | 3 | disputed | 5/10 | Dcontradicted | |
Have the agent map and explain an entire unfamiliar codebase without manually selecting context files C Codebase mapping | developer | Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding | 3 | disputed | 5/10 | Dcontradicted | |
Have the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me C Maintenance automation | developer | Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation | 3 | disputed | 5/10 | Dcontradicted | |
Turn a tracked issue into a complete pull request end-to-end C Feature implementation | developer | Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation | 3 | disputed | 5/10 | Dcontradicted | |
Understand how a codebase fits together to find where to start making changes C Codebase mapping | developer | Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding | 3 | disputed | 5/10 | Dcontradicted | |
Delegate longer-running coding tasks to run in the background in an isolated cloud environment C Background execution | developer | Autonomy agents — stories about autonomy agents in this arenaAutonomy agents | 3 | partial | 4/10 | Cclaimed | |
Have the agent stage changes, write commit messages, create branches, and open pull requests C Pr review | developer | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 3 | partial | 4/10 | Cclaimed | |
Reproduce issues, narrow down root causes, and verify fixes C Issue diagnosis | developer | Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding | 3 | disputed | 4/10 | Dcontradicted | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ||
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ||
Chat with the coding assistant directly inside my IDE for contextual help C Ide integration | developer | Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
Receive inline code completions and next-edit suggestions as I type C Code completion | developer | Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation | 3 | n/a | untested | none yet | |
Run the agent non-interactively in scripts for workflow automation C Terminal workflow | developer | Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration | 2 | full | 9/10 | Cclaimed | |
Include multiple project directories in a single session for broader context C Context management | developer | Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding | 2 | full | 8/10 | Cclaimed | |
Generate a working app from a sketch, image, or PDF design C Multimodal generation | ai-native user | Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation | 2 | partial | 6/10 | Xcommunity | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 6/10 | Xcommunity | |
Control which external tools and integrations the agent is allowed to access C Safe execution | engineering-lead | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 2 | partial | 5/10 | Xcommunity | |
Debug issues and troubleshoot using natural-language queries C Debugging | developer | Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation | 2 | disputed | 5/10 | Dcontradicted | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 5/10 | Tprobed | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 5/10 | Tprobed | |
Authenticate through an enterprise identity or cloud platform for compliance and scalability G Authentication | engineering-lead | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | disputed | 4/10 | Dcontradicted | |
Authenticate with an API key instead of an account login G Authentication | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | partial | 4/10 | Cclaimed | |
Get contextual explanations and automatic fixes for security vulnerabilities C Security checks | developer | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 2 | partial | 4/10 | Cclaimed | |
Have a cloud agent build, test, and demo a feature end-to-end for my review C Background execution | ai-native user | Autonomy agents — stories about autonomy agents in this arenaAutonomy agents | 2 | partial | 4/10 | Xcommunity | |
Kick off agent tasks directly from GitHub, GitLab, Linear, or Slack C Tool integration | developer | Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystem | 2 | partial | 4/10 | Cclaimed | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 4/10 | Cclaimed | |
Set up always-on agents that run on schedules or triggers to maintain and fix my software autonomously C Scheduled automation | ai-native user | Autonomy agents — stories about autonomy agents in this arenaAutonomy agents | 2 | partial | 4/10 | Xcommunity | |
Sign in with my existing product subscription plan to use the coding agent C Authentication | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | disputed | 4/10 | Dcontradicted | |
Have the agent build and recall memory automatically across sessions C Context management | developer | Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding | 2 | disputed | 3/10 | Dcontradicted | |
Choose which underlying AI model powers my session from multiple providers C Model choice | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | none | 0/10 | ||
Configure a reproducible cloud environment with the dependencies and setup steps my repository needs C Background execution | developer | Autonomy agents — stories about autonomy agents in this arenaAutonomy agents | 2 | none | 0/10 | ||
Have the agent operate inside a sandbox when interacting with code, tools, and network resources C Safe execution | engineering-lead | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 2 | none | 0/10 | ||
Manage multiple agent-driven coding sessions from one unified workspace C Session management | engineering-lead | Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration | 2 | none | 0/10 | ||
Start a task on one device and continue it later from another device or browser C Cross device continuity | developer | Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration | 2 | none | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Launch fleets of autonomous agents that work in parallel on different tasks for hours or days C Parallel agents | ai-native user | Autonomy agents — stories about autonomy agents in this arenaAutonomy agents | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Review diffs visually and run multiple sessions side by side in a desktop app C Session management | developer | Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration | 2 | n/a | untested | none yet | |
Sign in with a personal account to get free-tier access without managing API keys G Authentication | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 1 | fullfree | 7/10 | Xcommunity | |
Equip the agent with custom skills to perform specialized tasks C Marketplace | developer | Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystem | 1 | partial | 6/10 | Xcommunity | |
Integrate third-party partner-built agent apps into my workflows C Marketplace | engineering-lead | Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystem | 1 | partial | 5/10 | Cclaimed | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 4/10 | Cclaimed | |
Debug a live running web application directly from my coding assistant C Debugging | developer | Code generation — quality of generated code — correctness, style, fit to the codebaseCode generation | 1 | partial | 3/10 | Xcommunity | |
Create a shared workspace from my docs and repos as a common source of truth for the team C Team knowledge | engineering-lead | Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystem | 1 | none | 0/10 | ||
Let the tool automatically pick the best model for each task C Model choice | developer | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 1 | none | 0/10 | ||
Opt out of having my code and prompts used for AI model training C Data governance | engineering-lead | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 1 | none | untested | none yet | |
Run several task attempts in parallel and compare results before choosing one C Parallel agents | developer | Autonomy agents — stories about autonomy agents in this arenaAutonomy agents | 1 | none | untested | none yet | |
See license and public-code matching references for AI-suggested code C Security checks | engineering-lead | Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety | 1 | none | untested | none yet | |
View interactive diffs and share selected code as context from within my JetBrains IDE C Ide integration | developer | Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration | 1 | none | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 49 stories with headroom
What would move Gemini CLI’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextChat with the coding assistant directly inside my IDE for contextual help
nonemoves PA Scoreimpact 30
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.
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
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.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
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.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
Missing: explicit data-usage/training policy documentation, opt-out mechanism, enterprise/no-training guarantee.
Agenticness — how well agents can access and operate the productPoint an agent at llms.txt or agent-oriented docs
nonemoves agent-readyimpact 30
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.
Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent
nonemoves agent-readyimpact 30
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.
Agenticness — how well agents can access and operate the productBuild against official SDKs
nonemoves agent-readyimpact 30
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.
Agenticness — how well agents can access and operate the productSubscribe to events via webhooks
nonemoves agent-readyimpact 30
Missing: any webhook registration mechanism, event subscription API, or documentation of push notifications.
Showing the top 8 of 49 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map5 surfaces · 44 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
GitHub README44 stories
- Run the product headlessly / in CI for automation
- Plug MCP servers into this product so it can use their tools
- Use an official CLI
- Drive the product through a documented public API
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Perform bulk operations across many items at once
- Define rules that trigger actions automatically on events
- Schedule recurring jobs or workflows
- Version, review, and roll back my automations
- Have a cloud agent build, test, and demo a feature end-to-end for my review
- Delegate longer-running coding tasks to run in the background in an isolated cloud environment
- Set up always-on agents that run on schedules or triggers to maintain and fix my software autonomously
- Debug a live running web application directly from my coding assistant
- Debug issues and troubleshoot using natural-language queries
- Turn a tracked issue into a complete pull request end-to-end
- Describe a feature or bug in plain language and have the agent implement or fix it across multiple files
- Have the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me
- Generate a working app from a sketch, image, or PDF design
- Understand how a codebase fits together to find where to start making changes
- Have the agent map and explain an entire unfamiliar codebase without manually selecting context files
- Have the agent build and recall memory automatically across sessions
- Include multiple project directories in a single session for broader context
- Add a project instructions file to set coding standards and conventions the agent follows
- Reproduce issues, narrow down root causes, and verify fixes
- Equip the agent with custom skills to perform specialized tasks
- Integrate third-party partner-built agent apps into my workflows
- Connect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context
- Kick off agent tasks directly from GitHub, GitLab, Linear, or Slack
- Run a coding agent locally from my terminal
- Run the agent non-interactively in scripts for workflow automation
- Do everything through the API that I can do in the UI
- Read the product's source under an open license
- Authenticate with an API key instead of an account login
- Authenticate through an enterprise identity or cloud platform for compliance and scalability
- Sign in with my existing product subscription plan to use the coding agent
- Sign in with a personal account to get free-tier access without managing API keys
- Have the agent stage changes, write commit messages, create branches, and open pull requests
- Get automatic code review with contextual feedback on every pull request
- Inspect diffs and run checks to catch problems before merging
- Control which external tools and integrations the agent is allowed to access
- Get contextual explanations and automatic fixes for security vulnerabilities
Hacker News27 stories
- Use an official CLI
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Perform bulk operations across many items at once
- Have a cloud agent build, test, and demo a feature end-to-end for my review
- Set up always-on agents that run on schedules or triggers to maintain and fix my software autonomously
- Debug a live running web application directly from my coding assistant
- Debug issues and troubleshoot using natural-language queries
- Turn a tracked issue into a complete pull request end-to-end
- Describe a feature or bug in plain language and have the agent implement or fix it across multiple files
- Have the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me
- Generate a working app from a sketch, image, or PDF design
- Understand how a codebase fits together to find where to start making changes
- Have the agent map and explain an entire unfamiliar codebase without manually selecting context files
- Have the agent build and recall memory automatically across sessions
- Add a project instructions file to set coding standards and conventions the agent follows
- Reproduce issues, narrow down root causes, and verify fixes
- Equip the agent with custom skills to perform specialized tasks
- Run a coding agent locally from my terminal
- Authenticate through an enterprise identity or cloud platform for compliance and scalability
- Sign in with my existing product subscription plan to use the coding agent
- Sign in with a personal account to get free-tier access without managing API keys
- Get automatic code review with contextual feedback on every pull request
- Inspect diffs and run checks to catch problems before merging
- Control which external tools and integrations the agent is allowed to access
Gemini code assist docs10 stories
- Plug MCP servers into this product so it can use their tools
- Use an official CLI
- Delegate longer-running coding tasks to run in the background in an isolated cloud environment
- Have the agent build and recall memory automatically across sessions
- Add a project instructions file to set coding standards and conventions the agent follows
- Run a coding agent locally from my terminal
- Read the product's source under an open license
- Authenticate through an enterprise identity or cloud platform for compliance and scalability
- Sign in with a personal account to get free-tier access without managing API keys
- Control which external tools and integrations the agent is allowed to access
llms.txt2 stories
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
3 of 15 testable claims verified · 6 contradicted → integrity 0/100
22 distinct capability claims found in Gemini CLI’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
3
Verified
6
Unverified
6
Contradicted
21
Undersold
Verified (3)
“Generates a working app from a PDF, image, or sketch using multimodal input”
Generate a working app from a sketch, image, or PDF designpartialproof ↗
“Provides automated PR review with contextual feedback and suggestions”
Get automatic code review with contextual feedback on every pull requestfullproof ↗
“No API key setup needed - sign in with a Google account”
Sign in with a personal account to get free-tier access without managing API keysfullproof ↗
Unverified (10)
“Automates operational git/PR tasks like querying pull requests and handling complex rebases”
Have the agent stage changes, write commit messages, create branches, and open pull requestspartialproof ↗
“Connects to MCP servers for extra capabilities including Imagen/Veo/Lyria media generation”
Plug MCP servers into this product so it can use their toolsfullproof ↗
“Runs non-interactively in scripts/CI for automated workflows”
Run the product headlessly / in CI for automationfullproof ↗
“Runs non-interactively in scripts/CI for automated workflows”
Run the agent non-interactively in scripts for workflow automationfullproof ↗
“Responds to @gemini-cli mentions in issues/PRs for debugging, explanations, or task delegation”
Kick off agent tasks directly from GitHub, GitLab, Linear, or Slackpartialproof ↗
“Supports including multiple project directories in one session via --include-directories flag”
Include multiple project directories in a single session for broader contextfullproof ↗
“Outputs structured JSON results via --output-format json flag”
Run the product headlessly / in CI for automationfullproof ↗
“Streams newline-delimited JSON events via --output-format stream-json flag”
Run the product headlessly / in CI for automationfullproof ↗
“Extend the CLI with custom MCP tools configured in ~/.gemini/settings.json”
Plug MCP servers into this product so it can use their toolsfullproof ↗
“Can list a user's open pull requests via @github command integration”
Kick off agent tasks directly from GitHub, GitLab, Linear, or Slackpartialproof ↗
Contradicted (6)
“Can query and edit across large codebases”
Have the agent map and explain an entire unfamiliar codebase without manually selecting context filesdisputedproof ↗
“Debugs and troubleshoots issues via natural-language queries”
Debug issues and troubleshoot using natural-language queriesdisputedproof ↗
“Supports conversation checkpointing to save and resume complex sessions”
Have the agent build and recall memory automatically across sessionsdisputedproof ↗
“Reads GEMINI.md custom context files to tailor behavior per project”
Add a project instructions file to set coding standards and conventions the agent followsdisputedproof ↗
“Lets user pick which specific Gemini model to use”
Choose which underlying AI model powers my session from multiple providersnoneproof ↗
“Offers enterprise-grade security and compliance features”
Authenticate through an enterprise identity or cloud platform for compliance and scalabilitydisputedproof ↗
Undersold (21)
Drive the product through a documented public APIpartialproof ↗
Set up automations that run autonomously in the backgroundpartialproof ↗
Perform bulk operations across many items at oncepartialproof ↗
Define rules that trigger actions automatically on eventspartialproof ↗
Have a cloud agent build, test, and demo a feature end-to-end for my reviewpartialproof ↗
Delegate longer-running coding tasks to run in the background in an isolated cloud environmentpartialproof ↗
Set up always-on agents that run on schedules or triggers to maintain and fix my software autonomouslypartialproof ↗
Debug a live running web application directly from my coding assistantpartialproof ↗
Equip the agent with custom skills to perform specialized taskspartialproof ↗
Integrate third-party partner-built agent apps into my workflowspartialproof ↗
Connect the agent to workflow tools like Jira, Slack, and Google Drive to extend its contextpartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Read the product's source under an open licensepartialproof ↗
Authenticate with an API key instead of an account loginpartialproof ↗
Inspect diffs and run checks to catch problems before mergingpartialproof ↗
Control which external tools and integrations the agent is allowed to accesspartialproof ↗
Get contextual explanations and automatic fixes for security vulnerabilitiespartialproof ↗
Claims outside our story set (4)
Real capability claims found in Gemini CLI’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Grounds answers with built-in Google Search for real-time info”
source ↗“Automatically labels and prioritizes GitHub issues via content analysis”
source ↗“Lets users report bugs directly from the CLI with a /bug command”
source ↗“Available directly in Cloud Shell without additional setup”
source ↗
Business model
Open-source (Apache 2.0) CLI; free via Google login or API key rate limits, or usage-based pay-as-you-go via Gemini API/Vertex AI for higher limits.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
