0cb9ee5c58
- Landing: replace nonexistent `mempalace remember` CLI demo with real
`mempalace mine ./notes`
- Landing: soften unverifiable absolutes ("forever available",
"100% recall by design", "<50 ms", "90%+ compression",
"two-thousand-year-old", "tens of thousands of entries")
- MCP tool count: 19 → 29 across mcp-integration, claude-code, openclaw,
and modules; expand tool overview with Drawers, Tunnels, and System
categories to match mcp_server.py
- Wake-up token range: ~170–900 → ~600–900 in cli/api-reference/python-api
to match cli.py help text and concept docs
- Gemini CLI: move `--scope user` before target name and add `--`
separator so `-m mempalace.mcp_server` isn't parsed as Gemini flags
1.3 KiB
1.3 KiB
OpenClaw Skill
MemPalace provides an official skill for OpenClaw, making it trivial to give your ClawHub agents complete access to the palace's declarative memory and knowledge graph.
Installation
The skill is built right into the integrations/openclaw directory of MemPalace.
You can add MemPalace as an MCP server to OpenClaw via the CLI:
openclaw mcp set mempalace '{"command":"python3","args":["-m","mempalace.mcp_server"]}'
Or by directly editing your OpenClaw configuration:
{
"mcpServers": {
"mempalace": {
"command": "python3",
"args": ["-m", "mempalace.mcp_server"]
}
}
}
How It Works
Once connected, OpenClaw agents receive all 29 tools along with the Memory Protocol—a strict behavioral guide indicating they should:
- Never guess: Query
mempalace_searchormempalace_kg_querybefore confidently answering. - Keep an agent diary: Maintain continuity between sessions by writing to
mempalace_diary_write. - Manage the Knowledge Graph: Update declarative facts when things change using
mempalace_kg_addandmempalace_kg_invalidate.
By connecting OpenClaw to MemPalace, you get both autonomous code execution and persistent, high-recall memory in the same workflow.