Showcase


Products
GitHub, product by product →GitHub 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 |
|---|---|---|---|---|
| GitHub | Code Hosting | #2/4 | 44/100 | 71/100 |
| GitHub Copilot | AI Coding Agents | #4/13 | 37/100 | 45/100 |
| GitHub Mobilethis page | Mobile AI Dev Tools | #2/6 | 14/100 | 12/100 |
Not yet judged (1 — no arena where they compete): GitHub Actions
Verified integrations
No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.
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
Git code — core git and code operations — cloning, branching, pushing, code browsingGit codeevidence →
Core git and code operations — cloning, branching, pushing, code browsing
Networking access — stories about networking access in this arenaNetworking accessevidence →
Stories about networking access in this arena
n/a
Offline sync — stories about offline sync in this arenaOffline syncevidence →
Stories about offline sync in this arena
n/a
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Running agents — operating agents in production — sessions, persistence, recoveryRunning agentsevidence →
Operating agents in production — sessions, persistence, recovery
Security — security posture and hardening storiesSecurityevidence →
Security posture and hardening stories
Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal sshevidence →
Terminal and SSH workflows — shells, sessions, remote access
n/a
Ux ergonomics — stories about ux ergonomics in this arenaUx ergonomicsevidence →
Stories about ux ergonomics in this arena
n/a
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where GitHub Mobile 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
—0/10
Subscribe to events via webhooks
n/an/a
Build against official SDKs
n/an/a
Issue scoped/least-privilege API credentials for an agent
n/an/a
Connect an agent via an official MCP server
n/an/a
Download a machine-readable API spec (OpenAPI or equivalent)
n/an/a
Rely on versioned APIs with a documented deprecation policy
n/an/a
Test against a sandbox environment without touching production data
n/an/a
Explore an interactive API reference with runnable examples
n/an/a
Docs for agents
Point an agent at llms.txt or agent-oriented docs
~5/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
✓7/10
Operate the product with natural-language commands
~6/10
Plug MCP servers into this product so it can use their tools
n/an/a
Get AI-generated insights and suggestions from my data inside the product
~6/10
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
Git code — core git and code operations — cloning, branching, pushing, code browsingGit code
Core git and code operations — cloning, branching, pushing, code browsing
Networking access — stories about networking access in this arenaNetworking access
Stories about networking access in this arena
Mesh network
Offline sync — stories about offline sync in this arenaOffline sync
Stories about offline sync in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Running agents — operating agents in production — sessions, persistence, recoveryRunning agents
Operating agents in production — sessions, persistence, recovery
Security — security posture and hardening storiesSecurity
Security posture and hardening stories
Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh
Terminal and SSH workflows — shells, sessions, remote access
Local dev environment
Ux ergonomics — stories about ux ergonomics in this arenaUx ergonomics
Stories about ux ergonomics in this arena
Sorted by importance (agentic first) (high → low) · 69/69 stories · click a row’s chevron for the rationale and evidence
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 | full | 7/10 | Cclaimed | |
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 | none | 0/10 | ||
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 | |
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 | n/a | untested | none yet | |
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 | partial | 6/10 | Cclaimed | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Cclaimed | |
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 | Cclaimed | |
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 | partial | 5/10 | Tprobed | |
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 | n/a | 0/10 | ||
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
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 | n/a | untested | none yet | |
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 | n/a | untested | none yet | |
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 | 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 | n/a | untested | none yet | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
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 | n/a | untested | none yet | |
Assign an issue to an AI coding agent and receive a ready-to-review pull request C Ai coding agents | ai-native user | Running agents — operating agents in production — sessions, persistence, recoveryRunning agents | 3 | full | 7/10 | Cclaimed | |
Have an AI agent analyze my pull requests and suggest code improvements from my phone C Ai coding agents | ai-native user | Running agents — operating agents in production — sessions, persistence, recoveryRunning agents | 3 | full | 7/10 | Cclaimed | |
Create pull requests on hosted Git platforms directly from my device C Repo management | developer | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 3 | partial | 6/10 | Xcommunity | |
Direct an AI agent to browse, search, edit, commit, pull, and push in a repository via conversation C Ai coding agents | ai-native user | Running agents — operating agents in production — sessions, persistence, recoveryRunning agents | 3 | partial | 6/10 | Cclaimed | |
Review pull requests from my phone while on the go C Repo management | developer | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 3 | partial | 6/10 | Xcommunity | |
Commit and push changes directly from my device C Repo management | developer | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 3 | none | 0/10 | ||
Clone Git repositories over HTTPS, SSH, or the Git protocol C Repo management | developer | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 3 | n/a | untested | none yet | |
Connect to remote servers using SSH with Ed25519, ECDSA, or RSA keys C Ssh connections | developer | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 3 | n/a | untested | none yet | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | n/a | untested | none yet | |
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 | untested | none yet | |
Get secure infrastructure access to resources wherever they live, including Kubernetes clusters C Mesh network | developer | Networking access — stories about networking access in this arenaNetworking access | 3 | n/a | untested | none yet | |
Keep my terminal session alive across network changes and device sleep C Ssh connections | power-user | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 3 | n/a | untested | none yet | |
Open multiple terminal sessions, each with its own context, appearance, and history C Ssh connections | power-user | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 3 | n/a | 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 | |
Run local UNIX commands like ls, grep, cat, tar, and curl directly in the app C Ssh connections | developer | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 3 | n/a | untested | none yet | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | n/a | untested | none yet | |
Manage and track cloud-based coding agent tasks from my phone C Ai coding agents | developer | Running agents — operating agents in production — sessions, persistence, recoveryRunning agents | 2 | full | 8/10 | Cclaimed | |
Converse with an AI agent in natural language to get insights into repositories and open pull requests C Ai coding agents | ai-native user | Running agents — operating agents in production — sessions, persistence, recoveryRunning agents | 2 | full | 7/10 | Cclaimed | |
Search and navigate code content using fuzzy matching, filters, and regular expressions C Repo management | developer | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 2 | partial | 3/10 | Xcommunity | |
Access and work with files and repositories from other apps' sandboxes on my device C Cross device sync | developer | Offline sync — stories about offline sync in this arenaOffline sync | 2 | n/a | untested | none yet | |
Amend the latest commit or undo unpushed commits to fix or split them C Repo management | power-user | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 2 | n/a | untested | none yet | |
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 | |
Connect directly to my servers without relying on a cloud relay, proxy, or VPN C Mesh network | power-user | Networking access — stories about networking access in this arenaNetworking access | 2 | n/a | untested | none yet | |
Connect to a saved host with one tap without re-entering credentials C Ssh connections | power-user | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 2 | n/a | 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 | |
Customize the font, colors, and cursor appearance of my terminal and persist the settings C Terminal customization | power-user | Ux ergonomics — stories about ux ergonomics in this arenaUx ergonomics | 2 | n/a | untested | none yet | |
Describe what I want in plain language and have the tool generate the corresponding shell command C Ai coding agents | ai-native user | Running agents — operating agents in production — sessions, persistence, recoveryRunning agents | 2 | n/a | untested | none yet | |
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 | n/a | untested | none yet | |
Edit files with a terminal-based editor and run syntax/lint checkers inside the app C Local dev environment | developer | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 2 | n/a | untested | none yet | |
Generate SSH key pairs for password-less access to my servers C Ssh connections | power-user | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 2 | n/a | untested | none yet | |
Get AI-generated commit message suggestions based on my staged changes C Ai coding agents | ai-native user | Running agents — operating agents in production — sessions, persistence, recoveryRunning agents | 2 | n/a | untested | none yet | |
Group multiple terminal sessions together and broadcast the same command to all of them C Ssh connections | power-user | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 2 | n/a | untested | none yet | |
Install additional pure-Python packages using pip directly on my device C Local dev environment | developer | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 2 | n/a | untested | none yet | |
Interactively rewrite history by deleting, editing, squashing, or reordering commits C Repo management | power-user | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 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 | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
Preview Markdown, HTML, and other rendered files with live reload C Repo management | developer | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 2 | none | untested | none yet | |
Protect my remote connections with biometric authentication like Face ID or fingerprint C Credential protection | developer | Security — security posture and hardening storiesSecurity | 2 | none | untested | none yet | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | n/a | untested | none yet | |
Resolve merge conflicts across many files at once with a dedicated tool C Repo management | developer | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 2 | none | untested | none yet | |
Route all my internet traffic through a specific device on my network using an exit node C Mesh network | power-user | Networking access — stories about networking access in this arenaNetworking access | 2 | n/a | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
Stash and unstash changes to temporarily clear my working directory C Repo management | power-user | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 2 | n/a | untested | none yet | |
Store credentials once in a secure vault and reference them from multiple hosts C Credential protection | developer | Security — security posture and hardening storiesSecurity | 2 | n/a | untested | none yet | |
Store my SSH keys in a hardware-backed secure enclave protected by biometrics C Credential protection | power-user | Security — security posture and hardening storiesSecurity | 2 | n/a | untested | none yet | |
Sync my saved hosts and connection settings across all my devices C Cross device sync | power-user | Offline sync — stories about offline sync in this arenaOffline sync | 2 | n/a | untested | none yet | |
Transfer files to and from remote hosts via scp and sftp using my configured keys C Ssh connections | developer | Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh | 2 | n/a | untested | none yet | |
Use subnet routers to reach devices outside my local network as if I were on it C Mesh network | developer | Networking access — stories about networking access in this arenaNetworking access | 2 | n/a | untested | none yet | |
Visualize the full commit graph across branches C Repo management | power-user | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 2 | none | untested | none yet | |
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 | |
Clone, update, and manage Git submodules within a repository C Repo management | power-user | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 1 | n/a | untested | none yet | |
Sign my commits with a GPG or SSH key for verification C Repo management | power-user | Git code — core git and code operations — cloning, branching, pushing, code browsingGit code | 1 | n/a | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 23 stories with headroom
What would move GitHub Mobile’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.
Agenticness — how well agents can access and operate the productDrive the product through a documented public API
nonemoves agent-readyimpact 45
Missing: any documented REST/GraphQL/OpenAPI spec for driving GitHub Mobile, SDKs, or automation endpoints tied to this product.
Git code — core git and code operations — cloning, branching, pushing, code browsingCommit and push changes directly from my device
nonemoves PA Scoreimpact 30
GitHub Mobile's evidence covers PR review, merging, Copilot agent tasks, code search, and notifications, but nowhere mentions committing or pushing local file changes/code edits from the device; one community comment even notes a competing third-party app (Working Copy) is used specifically for shipping small changes from a phone, implying GitHub's own app lacks this.
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
No evidence in the pack addresses data export, open formats, or account portability from GitHub Mobile; the app's documentation focuses on code review, Copilot, and browsing features only.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
Missing: any mention of data-training opt-out settings, Copilot data usage policy, or privacy controls specific to GitHub Mobile.
Automation depth — how much of the product can run unattendedPerform bulk operations across many items at once
nonemoves PA Scoreimpact 20
GitHub Mobile evidence focuses on individual item actions (single PR review, single issue assignment, single search) with no mention of bulk/multi-item operations; community feedback even highlights missing features and friction for single-item workflows, with nothing about batch actions across many items.
Automation depth — how much of the product can run unattendedSchedule recurring jobs or workflows
nonemoves PA Scoreimpact 20
GitHub Mobile evidence covers reviewing PRs, Copilot agent tasks, code search, and notifications on the go, but nothing describes scheduling recurring jobs or workflows (e.g., cron-like automation or scheduled actions) from the app.
Security — security posture and hardening storiesProtect my remote connections with biometric authentication like Face ID or fingerprint
nonemoves PA Scoreimpact 20
No evidence in the pack mentions biometric authentication, Face ID, fingerprint unlock, or any app-level security lock for GitHub Mobile; only general feature descriptions and unrelated community complaints are present.
Git code — core git and code operations — cloning, branching, pushing, code browsingVisualize the full commit graph across branches
nonemoves PA Scoreimpact 20
No evidence GitHub Mobile offers any commit-graph visualization across branches; docs cover PR review, Copilot features, notifications, and search but nothing about a graph/branch visualization tool, and community feedback focuses on diffs, notifications, and navigation issues instead.
Showing the top 8 of 23 — 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 map3 surfaces · 14 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
GitHub README13 stories
- 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
- Version, review, and roll back my automations
- Search and navigate code content using fuzzy matching, filters, and regular expressions
- Create pull requests on hosted Git platforms directly from my device
- Review pull requests from my phone while on the go
- Have an AI agent analyze my pull requests and suggest code improvements from my phone
- Direct an AI agent to browse, search, edit, commit, pull, and push in a repository via conversation
- Assign an issue to an AI coding agent and receive a ready-to-review pull request
- Converse with an AI agent in natural language to get insights into repositories and open pull requests
- Manage and track cloud-based coding agent tasks from my phone
Hacker News3 stories
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
2 of 7 testable claims verified · 0 contradicted → integrity 29/100
8 distinct capability claims found in GitHub Mobile’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
2
Verified
5
Unverified
0
Contradicted
7
Undersold
Verified (2)
“Review, approve, and merge code from mobile devices while away from your desk”
Review pull requests from my phone while on the gopartialproof ↗
“Global code search lets you locate snippets and navigate repositories from the home screen”
Search and navigate code content using fuzzy matching, filters, and regular expressionspartialproof ↗
Unverified (5)
“Manage and track Copilot cloud agent tasks centrally from your phone”
Manage and track cloud-based coding agent tasks from my phonefullproof ↗
“Copilot code review analyzes pull requests and suggests improvements on mobile”
Have an AI agent analyze my pull requests and suggest code improvements from my phonefullproof ↗
“Assign an issue to Copilot and receive a ready-to-review pull request, refine via comments in-app”
Assign an issue to an AI coding agent and receive a ready-to-review pull requestfullproof ↗
“Converse with Copilot in natural language to get insights into public and private repositories”
Converse with an AI agent in natural language to get insights into repositories and open pull requestsfullproof ↗
“Ask Copilot to open a new pull request via natural-language conversation”
Direct an AI agent to browse, search, edit, commit, pull, and push in a repository via conversationpartialproof ↗
Undersold (7)
Point an agent at llms.txt or agent-oriented docspartialproof ↗
Get AI-generated insights and suggestions from my data inside the productpartialproof ↗
Set up automations that run autonomously in the backgroundpartialproof ↗
Delegate tasks to a built-in AI assistant inside the productfullproof ↗
Operate the product with natural-language commandspartialproof ↗
Create pull requests on hosted Git platforms directly from my devicepartialproof ↗
Claims outside our story set (1)
Real capability claims found in GitHub Mobile’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.
“Get notified about actions needing your attention wherever you are”
source ↗
Business model
Free companion app with no separate charge; it simply inherits whatever GitHub plan the signed-in account already has.
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
Agent surface uptime llms.txt 100% (30d, checked every 6h since Sep 8 '26)
