Engram Server runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 29 Aug 2026.
Durable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres.
What the code does
We read the source, 22 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
popen = subprocess.Popen( # noqa: S603 - argv is built from trusted internal values
return pickle.loads(blob)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Engram Server
same job, measured the same wayLocal-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.
Token-light local memory with SQLite hybrid retrieval for MCP agents.
SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.
Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
Engram Server — questions
Answers built from our own checks of this server.