# Graph-MIND

Graph-MIND keeps conversation memory on your computer and lets connected AI agents retrieve useful past context in later sessions.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: goyohan0611-png
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/goyohan0611-png/graph-mind
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/graph-mind

## What it does

Graph-MIND gives AI agents one shared memory store on your computer. Conversations are kept word for word, while local retrieval combines word matches, semantic search and timestamps. When a question depends on earlier work, the server can return the relevant turns instead of the whole history.

A background capture service works with transcripts, hooks and plugins from supported clients. Semantic retrieval uses an `mpnet` embedding model in `ONNX` with `int8`, and it does not require a GPU. Secrets are masked before storage. You can move selected or complete memory with `graph-mind export FILE` and `graph-mind import FILE`. A manual MCP setup exposes the tools, but it does not save every conversation automatically.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add graph-mind -- uvx graph-mind-memory
```
uvx runs the command named after the package; if the README names another one, use uvx --from graph-mind-memory <command>

### Codex

**Platform CLI**
```bash
codex mcp add graph-mind -- uvx graph-mind-memory
```
uvx runs the command named after the package; if the README names another one, use uvx --from graph-mind-memory <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "graph-mind": {
            "command": "uvx",
            "args": [
                "graph-mind-memory"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from graph-mind-memory <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "graph-mind": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "graph-mind-memory"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from graph-mind-memory <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add graph-mind uvx graph-mind-memory
```
uvx runs the command named after the package; if the README names another one, use uvx --from graph-mind-memory <command>

## When to use it
- recover a decision from an earlier session
- share context between Claude Code and Codex
- look up a past change in a project
- keep agent memory on a local computer

## Example prompts
- Recall which database we chose for the billing service and why.
- Find what we changed in the authentication middleware last week.
- Use the saved project context when answering this question.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md