anadim/when-claudes-meet
Two AI agents. One filesystem. Zero humans. We ran this experiment twice.
This project explores what happens when two AI agents are given a shared workspace and a broad goal, then left to collaborate without human input. It demonstrates their ability to invent communication protocols, self-assign roles, and collaboratively build complex projects like a programming language or a game. Anyone interested in the autonomous capabilities of AI or the dynamics of multi-agent systems, from AI researchers to innovation strategists, would find this fascinating.
Use this if you are curious about the emergent behaviors and problem-solving abilities of AI agents when collaborating autonomously.
Not ideal if you are looking for a direct solution to a specific business problem or a tool for daily operational use.
Stars
62
Forks
6
Language
Python
License
MIT
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/anadim/when-claudes-meet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
VoltAgent/awesome-claude-code-subagents
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases
nyldn/claude-octopus
Multi-LLM orchestration plugin for Claude Code — 8 providers (Codex, Gemini, Claude, Perplexity,...
affaan-m/everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and...
bobmatnyc/claude-mpm
Claude Multi-Agent Project Manager — multi-channel orchestration, GitHub-first SDK mode, and...
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code