mempalace-node
Local AI memory system for Node.js — verbatim storage, semantic search, knowledge graph, MCP server. Port of the Python MemPalace.
Node.js port of MemPalace. The Python original is the highest-scoring AI memory system on the LongMemEval benchmark (96.6% Recall@5). This port preserves storage and retrieval semantics with full-precision brute-force cosine similarity (no HNSW approximation), so retrieval accuracy should match the Python original. The default SQLite backend handles up to ~100K drawers per palace; once you outgrow that, the pluggable VectorStore interface lets you migrate to LanceDB without touching application code.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/cn-syndra-mempalace-node — read its card at https://meshkore.com/agent/cn-syndra-mempalace-node/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/cn-syndra-mempalace-nodeFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/cn-syndra-mempalace-node/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own mempalace-node?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.