Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.
registry version 0.36.1
Python
uvx turbo-quant-memoryPython
uvx turbo-quant-memory@0.36.1
Pick your client — the config below is generated for this server (local stdio). Copy respects the “Pin version” switch above.
claude_desktop_config.json
{
"mcpServers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}{
"mcpServers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory@0.36.1"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}Format verified against the official Claude Desktop docs ↗.
terminal
claude mcp add --env TQMEMORY_SECRETS_PASSPHRASE=<YOUR_TQMEMORY_SECRETS_PASSPHRASE> turbo-quant-memory -- uvx turbo-quant-memory
claude mcp add --env TQMEMORY_SECRETS_PASSPHRASE=<YOUR_TQMEMORY_SECRETS_PASSPHRASE> turbo-quant-memory -- uvx turbo-quant-memory@0.36.1
Format verified against the official Claude Code docs ↗.
.cursor/mcp.json
{
"mcpServers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}{
"mcpServers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory@0.36.1"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}Format verified against the official Cursor docs ↗.
.vscode/mcp.json
{
"servers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}{
"servers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory@0.36.1"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}Format verified against the official VS Code docs ↗.
mcp_config.json
{
"mcpServers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}{
"mcpServers": {
"turbo-quant-memory": {
"command": "uvx",
"args": [
"turbo-quant-memory@0.36.1"
],
"env": {
"TQMEMORY_SECRETS_PASSPHRASE": "<YOUR_TQMEMORY_SECRETS_PASSPHRASE>"
}
}
}
}Format verified against the official Windsurf docs ↗.
Defined in the server's official registry manifest. Required secrets are shown as <YOUR_…> placeholders in the configs above.
TQMEMORY_FTS_LANGUAGE — Snowball stemmer for the BM25 lane. Use Russian for Cyrillic-dominant corpora.TQMEMORY_EMBEDDING_BACKEND — Embedder backend. Default fastembed (ONNX); sentence-transformers needs the [torch] extra.TQMEMORY_MIGRATE_ON_STARTUP — Set to 1 to apply pending schema migrations automatically on startup.TQMEMORY_SECRETS_PASSPHRASE secret — Argon2id passphrase for the secrets vault on headless hosts. Omit to use the OS keyring.⭐ 9 stars · 最近更新于 46 天前 · MIT license
Distributed as Python, listed under Knowledge & Memory. Review our MCP security guide before granting access to real data.
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/Lexus2016/turbo_quant_memory. Any third-party service it calls may require its own API key and account.
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Publish this server? Link back with a badge on your README or site — copy either snippet.
Markdown
[](https://mcpnav.net/server/turbo-quant-memory/)
HTML
<a href="https://mcpnav.net/server/turbo-quant-memory/"><img src="https://mcpnav.net/badge/turbo-quant-memory.svg" alt="Listed on MCPNav" height="20"></a>