by SafeRL-Lab
CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems
# Add to your Claude Code skills
git clone https://github.com/SafeRL-Lab/cheetahclawsLast scanned: 5/10/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-10T06:33:21.765Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": false
}cheetahclaws is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by SafeRL-Lab. CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems. It has 748 GitHub stars.
Yes. cheetahclaws passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/SafeRL-Lab/cheetahclaws" and add it to your Claude Code skills directory (see the Installation section above).
cheetahclaws is primarily written in Python. It is open-source under SafeRL-Lab on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh cheetahclaws against similar tools.
No comments yet. Be the first to share your thoughts!
English | 中文 | 한국어 | 日本語 | Français | Deutsch | Español | Português
curl -fsSL https://raw.githubusercontent.com/SafeRL-Lab/cheetahclaws/main/scripts/install.sh | bash
After installation:
source ~/.zshrc # macOS
# or: source ~/.bashrc # Linux
cheetahclaws # start chatting!
Other install methods: pip install | uv install | run from source | full details
🖥️ Prefer a native app? A desktop build (Electron) wraps the full chat UI in a window — no terminal needed. See
desktop/.
accept-edits permission mode (auto-run file edits, still ask before non-allow-listed Bash) — the middle ground between auto and accept-all; also exposes the existing plan mode in /permissions and corrects the prompt's misleading auto description. Detailslast_verified date instead of file mtime, so reading a memory can't fake-refresh a stale one (PR #150); new MemoryVerify tool is the only thing that resets the clock, the prompt tells the agent to call it after re-checking, and the injected memory manifest ranks by verified recency. Detailsdesktop/; version-string format unified to v3.5.x. Detailscheetahclaws package (from cheetahclaws import kernel), removing sys.path name-collision crashes at startup — breaking only if you import internals directly; full suite green (2449 passed). Detailscheetahclaws on PATH, and local Ollama models that emit tool calls as text now actually execute them (two fixes from #131). Details/budget $5 / /budget daily $20 cap spend per session or day, enforced before each model call. Details/context grid and 1M context for deepseek-v4-flash. DetailsFor more news, see here.
CheetahClaws: A Fast and Easy-to-Use Python native Agent Harness Infrastructure, Supporting Any Model, such as Claude, GPT, Gemini, Kimi, Qwen, Zhipu, DeepSeek, MiniMax, and local open-source models via Ollama or any OpenAI-compatible endpoint.
More animated demos (code review,
/research,/brainstorm,/lab, Telegram/WeChat/Slack bridges) live indocs/media/.
Claude Code is a powerful, production-grade AI coding assistant — but its source is a compiled ~12 MB TypeScript/Node bundle (~1,300 files, ~283K lines), tightly coupled to the Anthropic API, hard to modify, and impossible to run against a local or alternative model.
CheetahClaws reimplements the same core loop in ~90K lines of readable Python — keeping what you need, dropping what you don't, and adding multi-provider + local-model support. Full comparison: docs/guides/comparison.md.
| Dimension | Claude Code (TypeScript) | CheetahClaws (Python) |
|---|---|---|
| Language | TypeScript + React/Ink | Python 3.8+ |
| Source files / LoC | ~1,332 files / ~283K | ~315 files / ~90K (core; ~127K with tests) |
| Built-in tools / commands | 44+ / 88 | 27 / 50+ |
| Model providers | Anthropic only | 8+ (Anthropic · OpenAI · Gemini · Kimi · Qwen · DeepSeek · MiniMax · …) |
| Local models | No | Yes — Ollama, LM Studio, vLLM, any OpenAI-compatible endpoint |
| Build step | Yes (Bun + esbuild) | No — python cheetahclaws.py |
| Extensibility | Closed (compile-time) | Open — register_tool() at runtime, Markdown skills, git plugins, MCP |
| Voice input | Proprietary WebSocket (OAuth) | Local Whisper / OpenAI — works offline |
Where Claude Code wins: richer React/Ink UI, more built-in tools, enterprise features (MDM, team permission sync, OAuth/keychain), AI-driven memory extraction, single-binary production reliability.
Where CheetahClaws wins: any-model switching (--model//model, no recompile) incl. full local/offline support; a readable agent loop in one file (agent.py, ~740 lines); zero build; runtime tool registration + MCP + git plugins + Markdown skills; task dependency graph (blocks/blocked_by); two-layer context compression; offline voice; cloud session sync; bridges to Telegram/WeChat/Slack/QQ.
Who it's for: developers who want a local/non-Anthropic coding assistant, researchers studying how agentic assistants work, and teams who need a hackable baseline — without a Node.js build chain.
OpenClaw is another popular open-source assistant (TypeScript/Node). The two have different primary goals — OpenClaw is a personal life-assistant across messaging channels; CheetahClaws is a developer/coding tool.
| Dimension | OpenClaw (TypeScript) | CheetahClaws (Python) |
|---|---|---|
| Lines of code | ~245K (~10,349 files) | ~90K core (~315 files) |
| Primary focus | Personal assistant across channels | AI coding assistant / dev tool |
| Architecture | Always-on Gateway daemon + apps | Zero-install terminal REPL |
| Messaging channels | 20+ (WhatsApp · Signal · iMessage · Discord · Matrix · …) | Terminal + Telegram · WeChat · Slack · QQ bridges |
| Local / offline models | Limited | Full — Ollama · vLLM · LM Studio · any OpenAI-compatible |
| Code editing tools | Browser control, Canvas | Read · Write · Edit · Bash · Glob · Grep · NotebookEdit · GetDiagnostics |
| Mobile / Live Canvas | Yes (menu bar + iOS/Android, A2UI) | — |
| MCP support | — | Yes (stdio/SSE/HTTP) |
| Hackability | 245K lines, harder to modify | ~90K lines — agent loop in one file |
| If you want… | Use |
|---|---|
| A personal assistant on WhatsApp/Signal/Discord, mobile-first, browser automation + Canvas | OpenClaw |
| An AI coding assistant in your terminal, full offline/local models, multi-provider switching, source you can read in an afternoon | CheetahClaws |
Full comparison — both sides' wins + key design differences (agent loop, tool registration, context compression, memory): docs/guides/comparison.md.
| Feature | Details |
|---|---|
| Multi-provider | Anthropic · OpenAI · Gemini · Kimi · Qwen · Zhipu · DeepSeek · MiniMax · Ollama · LM Studio · Custom endpoint |
| Agent loop | Streaming API + automatic tool-use loop; the whole loop is in agent.py |
| 28 built-in tools | Read · Write · Edit · Bash · Glob · Grep · WebFetch · WebSearch · NotebookEdit · GetDiagnostics · Memory* · Agent/SendMessage · Skill · AskUserQuestion · Task* · SleepTimer · EnterPlanMode/ExitPlanMode · (MCP + plugin tools auto-added) |
| MCP integration | Connect any MCP server (stdio/SSE/HTTP); tools auto-registered — see [extensions guide](docs |