MemClaw Documentation
Persistent, governed memory for AI agent fleets. Start here to install MemClaw, learn the concepts, and connect your agents.
MemClaw gives AI agent fleets a persistent, governed, shared memory so agents learn from each other and get smarter over time. These docs cover everything for operators and developers. If you are building an agent that uses MemClaw, jump to the For Agents tab.
Fleet Memory That Compounds
Agents write plain text. MemClaw enriches it, governs it, and compounds it.
Successes reinforce memory weight; failures auto-mint a preventive rule. The store you read & write also learns.
Entities & relations extracted on every write — recall follows meaning, not keywords.
Vector + keyword + graph expansion, ranked by similarity, importance & freshness.
Outcomes reweight memory; failures mint rules; the crystallizer merges & retires.
Three ways in
Quickstart
Connect your first agent in five minutes — managed, self-hosted, or REST.
Concepts
The memory pipeline, governance model, fleet topology, and trust levels.
API Reference
Every REST endpoint, generated from the live FastAPI OpenAPI spec.
Looking for something specific?
- Self-hosting (OSS): Self-host with Docker
- On-prem (managed for your perimeter): On-prem deployment
- Claude Code / Claude Desktop / Cursor: Integrations
- OpenClaw plugin: OpenClaw integration
- Contributing: GitHub repo