Persistent memory for Claude Code, Cursor and Codex over your own markdown notes: MCP server + Graph RAG on one SQLite file. Vector retrieval, hand-curated wikilink graph, cross-encoder rerank, zero-token per-turn ledger. pip install sqlite-graph-memory. Ships memory-bench v0.1.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add sqlite-graph-memory --env BRAIN_INDEX_DIR='<BRAIN_INDEX_DIR>' -- uvx sqlite-graph-memory~/.codex/config.toml
[mcp_servers.sqlite-graph-memory]
command = "uvx"
args = ["sqlite-graph-memory"]
env = { BRAIN_INDEX_DIR = "<BRAIN_INDEX_DIR>" }
# codex mcp add sqlite-graph-memory --env BRAIN_INDEX_DIR='<BRAIN_INDEX_DIR>' -- uvx sqlite-graph-memory~/.cursor/mcp.json
{
"mcpServers": {
"sqlite-graph-memory": {
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"sqlite-graph-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"sqlite-graph-memory": {
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"sqlite-graph-memory": {
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"sqlite-graph-memory": {
"command": "uvx",
"args": [
"sqlite-graph-memory"
],
"env": {
"BRAIN_INDEX_DIR": "<BRAIN_INDEX_DIR>"
}
}
}
}Environment variables
BRAIN_INDEX_DIR
Replace the placeholders with your own credentials and keep them out of version control.