The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Install
git clone https://github.com/google/agentmeshInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Agent Mesh
Agent Mesh is a private network for AI agents. A node runs next to an agent and gives it three things: a way to publish tools and models to the network, a way to find and call what other nodes publish, and an identity every other node can verify. Nodes connect directly when they can and through relays when they cannot, so the network works across laptops, containers, clusters and phones behind NAT.
Note: We have updated the name to Agent Mesh to better align with the goals of the project in the ecosystem.
Two properties hold everywhere:
- Nothing is reachable by default. A node exposes no services until its configuration says so, and no node may call a service the mesh policy has not granted. Grants are evaluated on service names, never on addresses.
- Identity comes from your identity provider. A node enrolls with an OpenID Connect token or a one-time bootstrap token, and the control plane turns that into a short-lived, offline-verifiable credential bound to the node's own key.
Try it
curl -sL https://google.github.io/agentmesh/install.sh | bash # agentmesh-node, mcp-client and friends
agentmesh-node join https://bananas.sam-mesh.dev # one-time login
agentmesh-node run --daemonize # local MCP server on 127.0.0.1:8080
agentmesh-node skill install # teach your agent to use it
Your agent now has tools that discover and call services across the mesh,
and an OpenAI-compatible endpoint that routes model requests to whoever
serves the model. bananas.sam-mesh.dev is a shared developer testnet with
no uptime promise; the quick start
walks through it, and your own mesh
runs a control plane on your laptop in one command.
To run a control plane of your own without installing anything, open a
GitHub codespace with the released binaries and run make testnet. It
starts on a public https URL that your laptop and phone can enroll into,
on your GitHub account's free quota:
The Codespaces guide has the steps, what persists and what stops.
What is in a mesh
| Program | Role |
|---|---|
agentmesh-control-plane |
Verifies who is joining, issues each node a signed credential, and holds the policy that says who may call what. |
agentmesh-router |
A well-known peer that nodes connect to first. Relays traffic between nodes that cannot reach each other and hosts the discovery table. |
agentmesh-node |
Runs next to your agent or service. Enrolls, connects, serves your local backends to the mesh, and exposes the mesh to your agent as a local MCP server and OpenAI-compatible API. |
agentmesh-one |
The control plane, a router and a web console in one binary, for laptops and small deployments. |
Documentation
google.github.io/agentmesh/docs is built from site/.
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.