Local-first MCP Work Model for coding agents: retrieves scored memory, records commitments, and credits outcomes from tests, reviews, replies, or owner approval. Public repo includes Apache-2.0 integration glue; the local engine binary is proprietary.
Enables orchestration of autonomous coding agents (Claude Code, Cursor, etc.) through an objective-native planning board with hash-chained audit trail. Humans define outcomes, agents claim and execute tasks via MCP.
Local-first deterministic project memory for AI coding agents, with context packs, decisions, gates, risks, scoped claims and explicit checkpoints in project-owned files.