Back to directory

SAM

A private, identity-verified peer-to-peer network for AI agents, where each node publishes tools and models to the mesh and can discover and call what other nodes expose, with nothing reachable unless explicitly granted.

SAM

SAM runs a node alongside an agent, giving it a way to publish tools and models to a 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.

Two properties hold everywhere: nothing is reachable by default, since a node exposes no services until its configuration says so and no node may call a service the mesh policy has not granted, with grants evaluated on service names rather than addresses; and identity comes from a configured identity provider, since 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.

The mesh exposes an OpenAI-compatible endpoint that routes model requests to whichever node serves the requested model, and also acts as a local MCP server for an agent. A control plane, router and web console can run in one binary for a laptop or small deployment, or a user can join a shared developer testnet.

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.