OpenClawBrain

Learned memory graph for AI agents. Policy-gradient routing over document chunks with self-learning, self-regulation, and autonomous correction. Pure Python...

This skill appears to be a coherent memory-graph tool, but before installing: 1) understand it will read and chunk your workspace files and persist mutable state to a local JSON (./brain/state.json) and run a daemon listening on a Unix socket — review where that file and socket will live and who/what can access them; 2) if you plan to use the OpenAI embedder/LLM, you will need to supply an API key (the skill bundle did not declare any required env vars like OPENAI_API_KEY); 3) the skill supports agent-initiated 'self_learn' (automatic updates to the graph) — only enable autonomous invocation if you trust the agent's behavior and data handling; 4) verify the openclawbrain PyPI package and its source (there is no homepage/source URL in the registry) before running pip install; and 5) if you need higher assurance, request the package source or a signed release and review daemon/socket access controls. If any of these points are unacceptable, treat the skill as untrusted.

Type: OpenClaw Skill Name: openclawbrain Version: 12.2.1 The OpenClaw AgentSkills skill bundle for 'openclawbrain' appears benign. The `SKILL.md` provides documentation and usage instructions for a learned memory graph system, including CLI commands for initialization, querying, learning, and daemon management. All operations described, such as local file system access for state management, local IPC via Unix sockets for the daemon, and optional network calls to OpenAI for embeddings, are consistent with the stated purpose of the skill. There are no instructions for data exfiltration, persistence, unauthorized remote control, or any other malicious activity. Potential vulnerabilities related to unsanitized user input passed to CLI arguments (e.g., in `query` or `content`) would be a flaw in the agent's execution or the `openclawbrain` tool itself, not an intentional malicious instruction within this skill bundle's documentation.