Generic MCP client integrations

Documented stdio MCP setup for Cursor, Codex CLI, Windsurf, Hermes, and other MCP clients.

Parent repository GitHub

Type: integration workflow
Repository: mnemosyne-oss/mnemosyne
Readiness: Usable for local Claude Code memory with caveats; production sync, remote models, sensitive-memory retention, and benchmark claims require additional validation.
Keywords: 6

Location

Repository path

docs/integrations/README.md

Invocation

Configure command `mnemosyne` with args `["mcp"]` in the host's MCP configuration.

Setup

Installation / activation

The host launches the configured stdio server.

Keywords

CursorCodexWindsurfHermesMCPstdio

Repository context

mnemosyne-oss/mnemosyne

MIT-licensed, local-first Python memory layer for AI agents that stores memories in SQLite and exposes remember, recall, and forget capabilities to Claude Code through a documented stdio MCP server; it also offers a Python SDK, CLI, optional local embeddings and consolidation, temporal triples, memory banks, import/export, and optional encrypted cross-instance sync.

AI agent memoryClaude Code integrationLocal-first infrastructureSemantic retrievalKnowledge graphsDeveloper toolingData synchronizationMulti-agent systems

Open full repository research