Skip to content

openclaw-mem

Trust-aware context packing for OpenClaw.

This docs site is organized around one core idea:

  • keep prompt packs small
  • keep selection inspectable
  • keep trust tiers and provenance visible
  • keep stale / untrusted / hostile content from quietly polluting future answers

This docs site is organized around a practical product journey:

  1. what problem is being solved,
  2. how trust-aware packing addresses it,
  3. where to verify the proof quickly,
  4. and how to adopt with a low-risk rollout path.

Two-plane framing:

  • Query plane (default): recall + trust-aware context packing with citations and receipts.
  • Action plane (optional): recommendation-only hygiene and maintenance review queues (no silent writeback to durable memory).
  1. Prove it locally (5 minutes)Trust-aware pack proof
  2. Run sidecar on existing OpenClaw (default)Choose an install path
  3. Promote to optional mem engine when neededMem Engine reference

Start here

Proof artifacts

Product shape

openclaw-mem is intentionally split into two layers:

  • Sidecar (default) — capture, ingest, local recall, pack receipts, graph query/drift checks, hygiene review
  • Mem Engine (optional) — memory-slot backend for hybrid recall and bounded automation

Start with the inspectable sidecar, then add the engine only when you need it.

Most common next stops

Deeper reference

Releases