The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Hypermarrow MCP listing page.
Local-first AI memory layer for the Model Context Protocol.
hypermarrow-mcp lets any MCP-compatible client read and write your long-term memory:
record_context – remember a decision, fact, or preferencerecall_memory – retrieve the most relevant past contextconsolidate – merge duplicates and age out stale entriesfile_anchor – map a short name to a local file pathAll memory lives under ~/.hypermarrow/memory.json on your own machine. Nothing is sent to the cloud unless you explicitly set HYPERMARROW_ENDPOINT to your own backend.
Or add to your MCP client config:
Memory data is stored locally. The server only talks to the client over stdio and, optionally, to a user-configured HYPERMARROW_ENDPOINT. No telemetry, no cloud sync by default.