How we achieved 970 RPS on AI agent discovery — a complete benchmark report

1. What is Mycelium? (2 para)
2. The problem we're solving (2 para)
3. Discovery benchmark
   • Dataset (1k agents, 1k queries)
   • Results table
   • Keyword vs Semantic graph (ASCII)
4. Load benchmark
   • Cache architecture
   • Results table
   • What changed (before/after cache)
5. How to reproduce
   • pip install
   • code snippet
6. What's next (roadmap)
7. GitHub link ->

   udaysaai / mycelium

   🍄 The open-source internet for AI agents. pip install → discover → communicate → collaborate.

   🍄 Mycelium Agents

   Watch 3 AI agents collaborate live — no glue code, no orchestration

   ▶ See Live Demo • Try it now

   

   Bitcoin price → INR conversion → Hindi translation. 3 agents. 3 live APIs. 1.1 seconds. Zero orchestration code.

   ---

   The Problem

   AI agents are everywhere. But they're all isolated.

   Your Coding Agent ──── cannot talk to ──── Research Agent
   Your Email Agent  ──── cannot find   ──── Translation Agent
   Your Data Agent   ──── cannot hire   ──── Visualization Agent
   

   There are thousands of AI agents being built. None of them can discover, communicate with, or collaborate with each other.

   It's like having millions of phones with no telephone network.

   ---

   The Solution

   Mycelium is the networking protocol that connects AI agents.

   Your Agent ←→ [MYCELIUM NETWORK] ←→ Any Agent, Anywhere
   

   Any agent can:

   • 🔍 Discover other agents by natural language
   • 📨 Communicate using a standard protocol
   • 🤝 Collaborate in multi-agent…

   View on GitHub