Command
Read AgentBook state and events, or manage AgentBook rules.
Persistent memory and operational continuity for AI coding agents — append-only event ledger (AgentBook), rolling summaries, self-model, belief knowledge, and turn-1 frontpage injection for deterministic cold-start.
Command
Read AgentBook state and events, or manage AgentBook rules.
Command
Review belief knowledge, run a belief scan, and preview promotions.
Command
Build a context brief for the current task from prior sessions.
Command
Create or inspect durable checkpoints of expensive-to-reconstruct state.
Command
Show context pressure and audit compaction behavior.
Command
List, set, or update tracked goals for this project.
Command
Run memory governance — dedup detection, candidate and archive reports, merges.
Command
Write a concrete handoff summary before stopping or transferring work.
Command
Search project memory and assemble focused evidence for the current task.
Command
Preview re-entry context and onboarding for resuming work.
Command
Inspect the live self-model and living-state capability snapshot.
Command
Show the surviving work-ledger entries across sessions.