XMemo
io.github.yonro/xmemo
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Install surfaces
How XMemo runs, per the official MCP registry entry.
- npm
@xmemo/[email protected] - streamable-http
https://xmemo.dev/mcp
Governed execution
How KLA gates calls to XMemo once it is connected.
A published policy defines which XMemo actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agent frameworks and model providers you already run. See integrations.