#133133rd of 142 in Agent frameworks and SDKs
clawteam
CLI that lets a leader agent spawn and coordinate CLI coding agents
- Stars
- 5.6k
- License
- MIT
- Last commit
- May 2026
- Last release
- Mar 2026
- Language
- Python
4,759 on 21 Apr 20265,551 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
ClawTeam is a Python CLI (Typer) that lets a leader agent spawn worker agents such as Claude Code, Codex, nanobot or any CLI agent. Each worker gets its own git worktree, tmux window and identity. Coordination runs through CLI commands for tasks with dependencies and inbox messages, over a filesystem transport or optional ZeroMQ P2P, with a tmux board or web dashboard to watch progress.
Who it is for: Developers running several CLI coding agents in parallel on one codebase
Strengths
- Works with any CLI agent that runs in a directory, including Claude Code, Codex and nanobot
- Each worker is isolated in a git worktree with real branches and diffs
- No database or queue needed: filesystem and tmux, with optional ZeroMQ P2P
- TOML team templates, e.g. a 7-agent hedge-fund team launched with one command
Weaknesses
- Requires tmux and a separately installed, working agent CLI; no Docker image
- Headline results (8 H100 autoresearch run) are self-reported and need external GPUs
- Leader behavior depends on the underlying agent following the injected skill and prompts
- Last release v0.2.0 is from March 2026, while commits continue
What it needs
- no GPU
- Needs Python 3.10+, tmux, git, a CLI coding agent (claude, codex, nanobot), ZeroMQ (optional, P2P)
- Models: Claude Code, Codex, nanobot, OpenClaw, Cursor
- port 8080
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent frameworks and SDKs
See all 142| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 96 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 92 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 92 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitReact and Angular SDK for adding agent chat and generative UI to apps | 90 out of 100 |