memory-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
memory-mcp
A unified, local memory for Claude — an MCP server that stores memories as
1024-dimensional embeddings in a single SQLite file (memory.db) and serves
them back over the Model Context Protocol.
Runtime: TypeScript, stdio transport
Store: SQLite +
sqlite-vecEmbedder: pluggable — local Ollama (default) or remote Voyage AI
Vectors:
float[1024], cosine distance
Data model (two tables, one id)
One memory is stored as two rows that share the same id:
|
|
|
|
sqlite-vec's vec0 table only holds the vector, so the readable content lives
in memories and the two are joined on memories.id = vec_memories.rowid.
content_hash (sha256 of the text) makes exact duplicates a no-op.
Related MCP server: mcp-openmemory
Setup
cd ~/memory-mcp
npm install
npm run buildLocal embeddings (default, nothing leaves the machine)
# install & run Ollama, then pull a 1024-d model:
ollama pull bge-large
ollama serve # if not already runningRemote embeddings (Voyage)
export EMBEDDER=voyage
export VOYAGE_API_KEY=... # voyage-3 = 1024-dCopy .env.example to .env to see all options.
Wire it into Claude
Add to claude_desktop_config.json (Claude Desktop) or .mcp.json (Claude Code):
{
"mcpServers": {
"memory": {
"command": "node",
"args": ["/Users/tylertabarovsky/memory-mcp/dist/server.js"],
"env": { "EMBEDDER": "ollama" }
}
}
}Tools
Tool | Args | Does |
|
| chunk → embed → store |
|
| embed query → cosine kNN → ranked hits |
|
| recent memories, optional tag filter |
|
| remove content + vector |
Capture model
This scaffold uses the explicit model: Claude calls memory_write when it
decides something is worth keeping. Simplest and least noisy. A passive/auto
capture layer can be added later on top of the same tools.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Related MCP Servers
- AlicenseAqualityDmaintenanceCross-surface persistent memory for Claude. Bridges context between Claude Chat, Code, and Cowork via local SQLite with full-text search.68 npm7MIT
- AlicenseAqualityDmaintenanceEnables Claude to remember conversations and learn over time by storing and recalling messages, memory abstracts, and recent history using a local SQLite database.470MIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent, searchable memory for Claude Code using local SQLite, semantic embeddings, and full-text search, enabling Claude to recall and retrieve context across sessions and projects without external services.23 npm4MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude Code sessions to automatically capture and retrieve architectural decisions, code changes, bug fixes, and configuration context across sessions using local SQLite storage and hybrid semantic/keyword search.95 PyPI1MIT