Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Orchestra — coordinating 10+ coding agents without becoming the bottleneck
Learn how Orchestra uses your codebase as shared memory for 10+ coding agents, enabling parallel work across repos without manual context passing or becoming a bottleneck.
I built Orchestra, a file-based coordination layer for managing multiple coding agents across repos without manually passing context between them.
It turns your codebase into a shared memory + execution system using a structured .orchestra/ directory (threads, plans, decisions, handoffs, sessions), so agents can work in parallel across worktrees while staying aligned.
In the demo, I’ll show how I go from problem → research → plan → parallel execution across API/frontend/infra agents, without constantly re-explaining context or micromanaging each agent.