A shared memory and coordination layer for AI coding agents that provides a tamper-evident timeline, conflict awareness, and attribution for multi-agent coding workflows.
Gives AI coding agents persistent, evolving knowledge about a codebase, enabling them to store and retrieve observations about architecture, conventions, gotchas, and recent work context.
Enables AI coding agents to keep a persistent, locally stored board of notes across sessions, with a bounded set of active notes that automatically archive so context stays manageable.
Gives AI coding agents persistent, searchable typed memory stored as plain markdown files, allowing them to record decisions, contracts, tasks, evaluations, and session logs and update entries by id.