Back to directory

HermesClaw

A bridge that lets Hermes Agent, OpenClaw and OpenCode share one WeChat account at once, running two local proxy servers and a protocol bridge so each agent can be reached and switched between from the same chat.

HermesClaw

HermesClaw solves a conflict between AI agents that each natively support WeChat: Hermes Agent and OpenClaw both connect to the same messaging protocol exclusively, so starting both on one account causes one of them to drop messages with connection errors. HermesClaw becomes the single connection to that protocol itself, then runs two local proxy servers, one for each agent, plus a direct bridge for OpenCode, so every gateway believes it is talking to the real messaging API while HermesClaw actually holds the connection.

A user switches between the three AI backends from inside the same chat with short commands, or runs two or all three together on shared messages, and can also send voice messages that OpenCode acts on directly using free models. Voice, images, video and files are forwarded to whichever backend is active.

It installs with a single command and is written in Python.

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.