Openclaw Memory Max

SOTA Memory Suite — auto-recall, cross-encoder reranking, multi-hop deep search, causal knowledge graph, episodic memory, and nightly sleep-cycle consolidation.

This skill appears to do what it claims, but it gains access to conversation content and can modify the agent's system prompt when specific options are enabled. Before installing: 1) Confirm you trust the upstream source (review package.json and openclaw.plugin.json for dependencies and any network code). 2) Keep enableAutoCapture and enableRulePinning disabled unless you need them; if you enable rule pinning, ensure only trusted processes/users can write ~/.openclaw/memory/MEMORY.md. 3) Inspect the sidecar files (auto_captured.jsonl, episodes.jsonl, utility_scores.json, causal_graph.json) and set file permissions so only your user can read/write them. 4) If you are concerned about privacy or untrusted code, consider running the plugin in an isolated environment or container, or review the full source to ensure there are no unexpected network calls or remote model fetching. If you want, I can scan package.json and the remaining source files for network calls and dependency risk indicators.

Type: OpenClaw Skill Name: openclaw-memory-max Version: 3.0.4 The bundle is a sophisticated memory enhancement suite for OpenClaw that implements local cross-encoder reranking, causal knowledge graphs, and automated context injection via lifecycle hooks. It uses standard libraries like @huggingface/transformers and sql.js to perform all operations locally. While it includes an opt-in 'Rule Pinning' feature that allows content from MEMORY.md to be injected as critical constraints into the system prompt (a potential local prompt-injection vector), this is clearly documented as a security risk and disabled by default. No evidence of data exfiltration, unauthorized remote execution, or malicious intent was found across the code or instructions.