Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Claude Code Multi-Agent Coordination
Shows running multiple Claude Code agents in containers using MCP, using context for real tasks like browser automation, coordinated via natural‑language prompts and shared logs.
This talk showcases how we run multiple Claude Code agents using an open-source MCP (Model Context Protocol) setup — not as a demo, but as production infrastructure.
Each agent runs inside a container, with file-mounted context, state, and config. They operate on real tasks (browser automation, LinkedIn browsing, competitive research) and coordinate via pure natural language prompts — just like humans chatting.
All logs and exchanges are streamed into a shared chatroom, enabling review, human intervention, or agent-to-agent negotiation. No plugin wrappers. No forced APIs. Just prompt-level orchestration that works.
This project orchestrates multi-agent Claude Code via desktop app/API, using Deno/Electron.
This multi-agent AI code orchestration workspace uses Deno, React, and Electron.