agent-mesh

prathamesh-git9/agent-mesh

★ 0 stars Python AI/LLM Updated today

Event-driven multi-agent backend: consumer groups, at-least-once delivery with idempotency, dead-letter recovery, and fan-in that degrades on partial failure instead of hanging. OpenAI and Grok behind one provider interface, plus an MCP server.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agent-mesh": {
      "command": "uvx",
      "args": [
        "agent-mesh"
      ]
    }
  }
}

Or install with pip: pip install agent-mesh

README Excerpt

Most multi-agent demos are synchronous chains: one call waits for the next call, and one slow or failing agent stalls or voids the whole run. They often have no retry boundary, no isolation between specialist roles, and no reliable way to reconstruct what happened after a bad run. agent-mesh is an event-driven backend for coordinating specialist agents through

Tools (2)

GETPOST

agent-mesh

Quick Install

README Excerpt

Tools (2)

Related AI/LLM Servers