Self-hosted governed project memory for coding agents, recording decisions, checkpoints, evidence, review state, and agent activity in PostgreSQL with pgvector while keeping maintainer control over what becomes reusable memory or instruction-grade guidance.
Persistent memory and human approval for any AI agent.
Give your AI agents the ability to remember across sessions and ask humans for approval before sensitive actions. Works with Claude, Cursor, OpenClaw, and any MCP-compatible client.
A neutral memory quality-gate for AI agents — a gate, not a store. It provides one shared memory of you that every AI agent reads from and writes to, kept honest at write time.
