Back to directory

mq9

A message broker built specifically for multi-agent systems that unifies agent registration, capability-based discovery, and reliable asynchronous messaging, with native support for the A2A agent-to-agent protocol.

mq9

mq9 is infrastructure for multi-agent systems that solves two problems general-purpose tools do not address well together: how agents find each other and how they communicate reliably when tasks are long-running, agents come and go, and communication is not simple request-response. It provides an AgentCard data model, capability-based semantic discovery, persistent per-agent mailboxes, many-to-many agent topology, and long-task state retention, unified in one broker with shared storage, networking, and cluster coordination.

It natively supports the A2A protocol through a Python SDK facade over the official a2a-sdk, letting a developer build a compliant A2A agent in a small amount of code. The broker itself is a separate protocol inside the RobustMQ project, while this repository holds SDKs for Python, Java, Go, Rust, and JavaScript, a LangChain toolkit, demos, and the project's documentation site.

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.