Live Demo — fully client-side

Semantic memory, running entirely in your browser

A real vector database (sqlite-vec compiled to WebAssembly) and a real embedding model (all-MiniLM-L6-v2, ONNX) run on this page. Store memories, search them by meaning — nothing is uploaded, ever.

Preparing…
Add a memory
Semantic search

Search enables once the embedding model (~23 MB) finishes loading. It is fetched from this site only — no CDN, no third parties.

Stored memories

    Verify it yourself: open your browser's network tab. After the initial same-origin asset load, this page makes no further requests — embedding, storage and search all happen locally. Reloading the page discards everything.

    This is the real stack, shrunk to a page

    The demo uses the same components as the self-hosted MCP Memory Service — just without persistence, consolidation, or multi-client access.

    In this demo
    sqlite-vec (WASM, in-memory)
    →
    In the service
    sqlite-vec backend with persistent storage, WAL, hybrid cloud sync
    In this demo
    all-MiniLM-L6-v2 ONNX in the browser
    →
    In the service
    the same ONNX embedding model, server-side — no GPU, no API keys
    In this demo
    one page, one session
    →
    In the service
    MCP + REST + OAuth 2.1 for 20+ AI clients, knowledge graph, consolidation
    pip install mcp-memory-service
    Back to mcpmemory.services View the source