MemPalace Memory System for OpenClaw

MemPalace memory system for OpenClaw/XClaw/WorkBuddy. Archive AI conversations to local long-term storage with semantic search. Commands: /mem-arc (archive),...

This skill appears to implement a usable local memory/archive system, but it is not a zero-risk drop-in. Before installing: 1) Run it inside a Python virtual environment (venv) so pip installs don't modify your system Python. 2) Set MEMPALACE_SKILL_ROOT to the skill directory (or MEMPALACE_PALACE_PATH) to force data to stay under the skill folder — otherwise defaults will write to ~/.mempalace. 3) Inspect the omitted/large files (mcp_server.py, the shell and PowerShell hooks) to confirm there is no unwanted network listener or extra commands executed. 4) Do not point the miner at wide or root-level folders — only pass the specific conversation/memory directory you want archived to avoid indexing sensitive files. 5) If you are uncomfortable with automatic cron scheduling, decline or disable auto-archive until you verify behavior. Additional information that would raise confidence: confirmation that mcp_server is disabled by default and the full contents of the hook scripts; otherwise treat this package as functionally coherent but operationally risky.

Type: OpenClaw Skill Name: mempalace-openclaw Version: 1.6.0 The skill bundle implements a local long-term memory system using ChromaDB and SQLite, but it contains several high-risk behaviors. The `SKILL.md` file instructs the AI agent to perform shell commands including `pip install` for dependencies and recursive directory scanning via `mempalace mine` (implemented in `mempalace/miner.py`). Furthermore, `mempalace/entity_registry.py` makes outbound HTTP requests to the Wikipedia API (`en.wikipedia.org`) for entity disambiguation. While these actions are aligned with the stated purpose and partially disclosed in the documentation, the combination of package installation, network access, and broad file system indexing constitutes a significant security risk.