codex vs gemini-cli
The two are close in size: 121.6k stars for codex, 106.8k for gemini-cli. Over the days we have tracked them codex moved +23.1% and gemini-cli +0.7%, so codex is growing faster right now.
gemini-cli leads on context depth and noise control and customization and model freedom. codex does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
A lightweight, local-first terminal coding agent that you can install and run with one command while signing in to ChatGPT or using your OpenAI API key.
- Stars
- 121.6k
- Tracked growth
- +23.1%
- Maturity
- ●●●●●
- Last commit
- 5h ago
- Language
- Rust
- License
- Apache-2.0
- Cost to run
- Sign in with a ChatGPT plan or use your OpenAI API key
Terminal-first access to Gemini 3 with multimodal models, a 1M-token context window, built-in Google Search grounding, and MCP extensibility.
- Stars
- 106.8k
- Tracked growth
- +0.7%
- Maturity
- ●●●●●
- Last commit
- 9h ago
- Language
- TypeScript
- License
- Apache-2.0
- Cost to run
- Free tier (60 req/min, 1,000 req/day); usage-based billing with API key
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | codex | gemini-cli |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Diff/file only | ●●●●● Whole-repo analysis |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● None mentioned | ●●●●● Config & trusted folders |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● No customization | ●●●●● Extensible configs & extensions |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Cloud (ChatGPT/API) | ●●●●● Cloud API (your key) |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● OpenAI only | ●●●●● Gemini + Vertex |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command install | ●●●●● One-command run |
Which one to pick
Pick codex if…
Easy setup — one-command install to run a local CLI coding agent that integrates with your ChatGPT plan or OpenAI API key.
Pick gemini-cli if…
Easy setup — run instantly with npx to get Gemini 3 access in your terminal for large-context code understanding, GitHub PR review, and extensible tools.
- Context depth: Whole-repo analysis (5/5 against 1/5)
- Noise control: Config & trusted folders (3/5 against 1/5)
- Customization: Extensible configs & extensions (5/5 against 1/5)
- Model freedom: Gemini + Vertex (3/5 against 1/5)
What people want from each one
openai/codex
Hacker News: Replit's new Code LLM: Open Source, 77% smaller than Codex, trained in 1 week drew 891 points and 220 comments.
google-gemini/gemini-cli
Hacker News: It looks like the status/need-triage label was removed drew 303 points and 82 comments.
Questions people ask
Is codex better than gemini-cli?
gemini-cli leads on context depth and noise control and customization and model freedom. codex does not take any axis by a clear margin. codex is worth picking when easy setup — one-command install to run a local CLI coding agent that integrates with your ChatGPT plan or OpenAI API key.
Which of codex and gemini-cli keeps my code private?
codex: Cloud (ChatGPT/API) (3/5). gemini-cli: Cloud API (your key) (3/5).
What does each one cost to run?
codex: Sign in with a ChatGPT plan or use your OpenAI API key. gemini-cli: Free tier (60 req/min, 1,000 req/day); usage-based billing with API key.
Full profiles: openai/codex and google-gemini/gemini-cli. Everything else in CLI coding agents.