Synapse

Self-learning memory engine for OpenClaw agents. Analyzes agent interactions, extracts operator intelligence, updates structured profiles, and improves recal...

This skill appears to do what it says: it reads OpenClaw session/memory files and writes structured profiles locally. Before installing, consider: 1) Review and restrict file permissions on ~/.openclaw and the synapse data directory so only trusted accounts/agents can read the stored profiles. 2) If you don't want the agent to learn without explicit consent, disable or modify the 'quiet learning' behavior or require explicit triggers for learning cycles. 3) Ensure session transcripts and memory files do not contain secrets (API keys, passwords, tokens); the skill's 'do not store sensitive information' rule is advisory only. 4) Consider pointing SYNAPSE_DATA_DIR to a controlled path (or a sandbox) and periodically audit profile.json and daily logs for unexpected content. 5) Because this is instruction-only, behavior depends on the agent obeying these instructions — test in a controlled environment first. If any of these controls are not acceptable, do not enable the skill.

Type: OpenClaw Skill Name: synapse-memory Version: 1.1.0 The synapse-memory skill is an instruction-only bundle designed to enhance the OpenClaw agent's memory by structuring preferences and behavioral patterns into local JSON and Markdown files. It operates entirely within the local workspace (~/.openclaw/workspace-astra/memory/synapse/), uses native OpenClaw tools for file operations, and explicitly instructs the agent to avoid storing sensitive information like API keys or passwords. No malicious code, network calls, or exfiltration patterns were found across SKILL.md or skill.json.