Back to directory

ClawTeam-OpenClaw

A fork of ClawTeam that coordinates a swarm of CLI coding agents, with OpenClaw as the default agent, so a single goal is split into tasks, assigned to spawned worker agents, and merged back together.

ClawTeam-OpenClaw

ClawTeam-OpenClaw lets CLI coding agents self-organize into teams instead of working alone. A leader agent calls clawteam spawn to create worker agents, each with its own git worktree, its own session, and its own identity, and workers coordinate by checking inboxes, updating tasks and reporting results back to the leader, all through CLI commands auto-injected into their prompts.

It is a fork of HKUDS/ClawTeam adapted for OpenClaw, adding a default openclaw agent, per-agent session isolation and production-hardened process backends, and also works with Claude Code, Codex, Hermes Agent, nanobot and Cursor. It uses tmux on Linux and macOS, with an automatic subprocess fallback on Windows, and a Web UI or tiled tmux view to monitor the swarm.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.