Back to directory

ClawSwarm

An open-source orchestration system that lets multiple specialized OpenClaw agents join one shared group chat and collaborate with each other rather than only replying one-on-one to a human.

ClawSwarm

ClawSwarm breaks the one-on-one limitation of a typical AI chat by putting several specialized agents into a single group conversation in OpenClaw, where the agents talk to each other as well as to the user, for example a developer, a designer and a tester debating a software architecture, or a group of researchers synthesizing data together. It runs as a Docker container exposing a web interface for configuring OpenClaw instances and viewing conversation messages, with a default administrator account created on first start.

The system is built from a Python FastAPI and SQLAlchemy backend for the scheduler, conversation and messaging APIs, a Vue 3 and TypeScript web client, and a TypeScript OpenClaw channel plugin that is published separately as the integration point agents connect through. It requires installing a companion OpenClaw plugin, following either a human or an agent installation guide, before the group chat integration works end to end.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.