A local, domain-agnostic workflow runtime that compiles decision graphs into durable, governed execution for agents, with recovery, operator control, and evidence-backed completion.

Design grounded graphs of governed improvement loops.

🕸️ Field guide, open dataset & interactive atlas for graph-structured multi-agent systems and programmable AI-agent organizations.

Progress-aware execution for durable, grounded, token-efficient coding agents.

Build graph-structured multi-agent systems with this collection of research papers, datasets, and design patterns for programmable AI organizations.