Persistent AI memory backend with semantic search and knowledge graph.
Stores episodic, semantic, and procedural memories in SQLite and retrieves the most relevant ones using vector similarity and graph traversal.
All embeddings run locally, with no API keys required.
Server Config
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"@engram-ai-memory/mcp@latest"
]
}
}
}