CozoDB Memory MCP Server provides a local-first memory solution for AI agents, integrating hybrid search capabilities, time-travel queries, and intelligent retrieval in a single binary without reliance on cloud services.
From the registry: Local-first memory system for AI agents with hybrid search and graph reasoning
Please install the `cozo-memory` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Node.js 20 or higher recommended. 1.7GB RAM minimum for default bge-m3 model.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["cozo-memory"]
- optional environment variables:
- `EMBEDDING_MODEL`: Embedding model name. Default bge-m3. Use Xenova/all-MiniLM-L6-v2 for lower-spec machines. (example: `Xenova/all-MiniLM-L6-v2`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.EMBEDDING_MODELrequiredSpecifies the embedding model to be used for processing.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.