sqlite-graph-memory runs on your own machine — the client starts it, so there is no endpoint to ping. 752 installs a week from pypi. Last commit 24 Oct 2026.
Recall over your markdown notes: vector search plus your [[wikilinks]] as a graph, in SQLite.
We read the source, 23 h ago · rules 995398eba69f
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.
meta = pickle.loads(Path(meta_path or META).read_bytes())
res = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add sqlite-graph-memory -e 'BRAIN_INDEX_DIR=<BRAIN_INDEX_DIR>' -- uvx sqlite-graph-memory
{
"mcpServers": {
"sqlite-graph-memory": {
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}
[mcp_servers.sqlite-graph-memory]
command = "uvx"
args = ["sqlite-graph-memory"]
env = { BRAIN_INDEX_DIR = "<BRAIN_INDEX_DIR>" }
{
"mcpServers": {
"sqlite-graph-memory": {
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}
{
"servers": {
"sqlite-graph-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}
Put your own value in place of
<BRAIN_INDEX_DIR> (Directory holding the index. Build it once with `sgm-index /path/to/notes`).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
TURNSTATE_DB (SQLite file for recall telemetry).
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
Local hybrid keyword + vector search (SQLite FTS5 + sqlite-vec) over markdown vaults and code.
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
Memory for AI coding agents — markdown in your own git, not a vendor database. Apache-2.0.
Search and SQL on object storage: full-text, vector and hybrid search plus SQL over your data.
Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.
Answers built from our own checks of this server.