Review-gate OpenClaw 内存卫生检查与 openclaw-mem
Pack trusted context and review memory writes before long OpenClaw sessions drift or accumulate low-quality memory.
Prerequisites
OpenClaw, SQLite, local filesystem access
Installation
Use the upstream install or setup path that matches your environment:
- pip install openclaw-context-pack
- git clone https://github.com/1991513ccie-png/skills
- uv sync --locked
- uv run --python 3.13 --frozen -- \
Requirements and caveats from upstream:
- python -m venv .venv
- python benchmarks/trust_policy_synthetic_proof.py --json
Basic usage or getting-started notes:
- Run the synthetic proof: Trust-policy synthetic proof
- Pack: run pack to get a bounded bundle_text and context_pack (schema: openclaw-mem.context-pack.v1), with citations, trust policy, and trace receipts.
- openclaw-mem self-curator verify --receipt .state/self-curator/apply-runs/<run>/apply-receipt.json --json
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/phenomenoner/openclaw-mem/HEAD/README.md
Documentation
- https://phenomenoner.github.io/openclaw-mem/
