google-gemini/gemini-cli
GitHubAn open-source AI agent that brings the power of Gemini directly into your terminal.
- Stars:
- 108.7k
- Language:
- TypeScript
- Default branch:
- main
- Last scored:
At a glance
- Rank
- #105 of 401
- Top 26% · #29 of 82 TypeScript repos
- Checks passed
- 10 of 17
- Full list below
- Best set up for
- Gemini CLI
- Score 82.4
- Needs most work for
- Cursor
- Biggest fix: Cursor rules (.cursor/rules) (+11.5 pts)
What it has
What it's missing
What to fix first
Showing fixes for Claude Code
- 1AGENTS.md / CLAUDE.mdAdd an AGENTS.md covering project goals, layout, setup commands, and conventions. Aim for 800+ chars of real guidance (not boilerplate).+13.2 pts
- 2Test suiteAdd a tests/ (or test/, __tests__/, spec/) directory with runnable tests. Document how to run them in AGENTS.md.+3.9 pts
- 3Manageable sizeIf possible, split into smaller modules or carve out a focused entry path. Document where to start in AGENTS.md.+3.3 pts
Score for each AI agent
Each agent weighs the checks by its own docs. Under each score are its top three. How each agent is scored →
Does google-gemini/gemini-cli have agent instructions?
An AGENTS.md (or CLAUDE.md) at the root tells AI coding agents how to build, test and work in the repo. A few agents also read a file of their own.
- AGENTS.md / CLAUDE.md
- None at the root (no AGENTS.md, CLAUDE.md, AGENT.md, .claude/CLAUDE.md or .claude/AGENTS.md)
- Agent-specific files
GEMINI.md(new tab) (4,609 characters)No .cursor/rules, .openhands/setup.sh, .aider.conf.yml or .agents/skills- Repos that have one
- 62 of 82 TypeScript repos · 221 of 401 repos on the leaderboard · See examples →
Get a starter AGENTS.md
From the files the checks found. Fill in the commands, then commit it at the root.
# AGENTS.md
Guidance for AI coding agents working in google-gemini/gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal. Written mainly in TypeScript.
## Where things are
- Dependencies are declared in `package.json`.
- Test files are spread through the tree, e.g. `evals/test-helper.test.ts`.
- Lint and format rules are configured in `eslint.config.js`.
- Type checking is configured in `tsconfig.json`.
- CI is defined in `.github/workflows`; read it for the exact install, lint and test steps.
- Commit hooks are set up in `.husky`; don't skip them.
- Common tasks are targets in `Makefile`.
- Follow the conventions in `CONTRIBUTING.md`.
## Commands
<!-- Fill in the exact commands CI runs. -->
- Install: TODO
- Test: TODO
- Lint: TODO
All 17 checks · 10 passed
How google-gemini/gemini-cli compares
- vs leaderboard average
- 9.4 pts above
- Average 66.8
- vs TypeScript average
- 5.0 pts above
- Average 71.2
- Stars among TypeScript repos
- #12 of 82
Missing here, and how many repos have it
- Skills (.agents/skills) · passed by 17% of leaderboard repos, 30% of TypeScript repos
- Cursor rules (.cursor/rules) · passed by 4% of leaderboard repos, 13% of TypeScript repos
Passes checks most repos miss
- Reproducible dev env · only 22% of repos pass it
- GEMINI.md · only 1% of repos pass it
- Pre-commit / git hooks · only 29% of repos pass it
One fix for the most agents: AGENTS.md / CLAUDE.md would raise the score for all 9 agents, by up to 13.3 points.
Similar repos
Same language and host as this repo, closest in overall score.
- cline/cline76.5TypeScript · 71.3k ★
- tldraw/tldraw76.5TypeScript · 51.2k ★
- simstudioai/sim76.4TypeScript · 30k ★
- TypeScript · 9.3k ★
- colinhacks/zod75.8TypeScript · 44.3k ★
- hsnice16/tula75.3TypeScript · 0 ★
Same topics, any language
Repos tagged with the same GitHub topics, most shared first.
- n8n-io/n8n83.6TypeScript · CLI, mcp client, mcp server
- Aider-AI/aider63.2Python · CLI, gemini
- TanStack/ai69.2TypeScript · AI agents, gemini
- Python · AI agents, gemini
- TypeScript · AI agents, CLI
- TypeScript · AI agents, CLI
Add a badge to your README
Paste this at the top of the README. It shows the score, and links back to this page.
[](https://agentfriendlycode.com/repo/github/google-gemini/gemini-cli)Check the score on every pull request
A GitHub Action posts one comment per pull request with how the score changed and why.