SuperLocalMemory ships an MCP server. ChatGPT Desktop supports MCP connectors. Add the SLM MCP server as a connector and ChatGPT Desktop can call the memory tools across sessions. Verify tool availability and the full memory round trip in your installed release.
The Model Context Protocol provides a standard interface between AI clients and external tools. SLM exposes memory tools via an MCP server; ChatGPT Desktop acts as the MCP client and calls those tools during a conversation.
ChatGPT Desktop is a networked service. The SLM core keeps its memory-content path local in Mode A; ChatGPT and optional integrations retain their own network behavior. Assess each component's privacy and terms separately.
Install SLM first, then add it as an MCP connector in ChatGPT Desktop Settings. The exact menu path may vary by app version — refer to the current ChatGPT Desktop documentation for the connector setup location.
Use pipx or uv with Python 3.11–3.14. Mode A does not require a model-provider key for its core path. Run setup to initialise the local database and configuration.
pipx install superlocalmemory slm setup
In ChatGPT Desktop, open Settings and navigate to the MCP or connectors section. Add the SLM MCP server with the following command:
slm mcp
If you prefer to run without a global install, use:
npx superlocalmemory mcp
The exact Settings path and connector configuration UI depend on the installed ChatGPT Desktop release. Refer to the current ChatGPT Desktop documentation for the exact steps.
Restart ChatGPT Desktop after adding the connector. In a conversation, ask ChatGPT to call get_status from the superlocalmemory connector to confirm the server is connected. Then store a note and recall it to verify the round trip.
slm status
# Expected: mode: A · provider: none · fact_count: 0When the connector is active, ChatGPT Desktop can call SLM memory tools during conversations. Available tools depend on the selected MCP profile and the installed SLM release.
Store facts, decisions, and context during a conversation. Recalled context in later sessions is bounded — inspect scope and provenance rather than treating it as a complete restore.
The same configured SLM profile can be connected to ChatGPT Desktop, Claude Desktop, Cursor, and other documented MCP clients. Each client still needs its own integration verification.
SLM stores core memory in a local SQLite database in Mode A. ChatGPT Desktop, optional providers, and any optional SLM integrations retain their own network behavior.
SLM uses five candidate producers, fusion, and optional reranking. Query the server for the current tool list — do not rely on a fixed marketing count. Retrieved context is evidence, not verified fact.
Mode A keeps the SLM core memory-content path local. Review the network behavior of the full deployment — ChatGPT, optional providers, connectors, backups, and downloads require separate assessment.
SuperLocalMemory is open source under AGPL v3. Full source code is publicly available. Verify the installed release, optional dependencies, and configured providers.
Install SLM, add the connector, then verify the memory round trip in ChatGPT Desktop before relying on it.