V4 · Integration

ChatGPT Desktop Integration.

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.

V4 AGPL v3 MCP Connector ChatGPT: networked
How It Works

MCP connects the two.

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 MCP client · calls memory tools during conversation
SLM MCP Server stdio transport · profile-selected tools
Local SQLite Store memory facts · indexes · profile state

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.

Setup Steps

Install, add connector, verify.

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.

1

Install SuperLocalMemory

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.

terminal
pipx install superlocalmemory
slm setup
2

Add the SLM MCP server in ChatGPT Desktop

In ChatGPT Desktop, open Settings and navigate to the MCP or connectors section. Add the SLM MCP server with the following command:

MCP server command
slm mcp

If you prefer to run without a global install, use:

alternative (npx)
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.

3

Restart and verify

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.

example: verify via the CLI in parallel
slm status
# Expected: mode: A · provider: none · fact_count: 0
What You Get

Memory tools for ChatGPT Desktop.

When 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.

01 · Persistence

Cross-Session Memory

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.

02 · Cross-Tool

Shared SLM Profile

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.

03 · Storage

Local Core Path

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.

04 · Retrieval

Hybrid Recall

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.

05 · Governance

Inspectable Behavior

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.

06 · License

Open Source

SuperLocalMemory is open source under AGPL v3. Full source code is publicly available. Verify the installed release, optional dependencies, and configured providers.

Common Questions

Questions about ChatGPT Desktop memory.

SLM ships an MCP server; ChatGPT Desktop supports MCP connectors. Add the SLM MCP server as a connector in ChatGPT Desktop Settings, then restart. ChatGPT Desktop can then call the memory tools (remember, recall, get_status) during conversations. Verify tool discovery and the memory round trip in your installed release.
Available tools depend on the selected SLM MCP profile and the installed release. Core tools include remember, recall, search, and get_status. Query the live server for the current tool list — the profile may expose additional tools depending on configuration. See the MCP documentation for details.
Mode A keeps the SLM core memory-content path local. ChatGPT Desktop is a networked service — conversations and optional integrations retain their own network behavior. Assess the complete deployment: ChatGPT, SLM mode, optional providers, backups, and connectors.
Documented MCP clients can connect to the same configured SLM profile. Protocol support alone is not proof of identity, scope, lifecycle, or handoff parity — run the integration contract in each client independently.
MCP connector support in ChatGPT Desktop is version- and plan-dependent. Verify the connector Settings path and MCP support in your installed ChatGPT Desktop release before proceeding.
Get started

ChatGPT Desktop,
with persistent memory.

Install SLM, add the connector, then verify the memory round trip in ChatGPT Desktop before relying on it.

Install V4.0 MCP Protocol