# neurakeep

Local-first memory for AI agents: import documents, search facts and decisions, and review extracted memories before they stick.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 13
- Author: dominiclachance
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/dominiclachance/neurakeep
- Updated: 2026-10-20
- HTML: https://affpapa.org/en/nevibecode/mcp/neurakeep

## What it does

NeuraKeep keeps a vault on your own machine. It pulls in Markdown, plain text, JSONL and PDFs, then proposes memory entries that point back to the file they came from. Ask a question later and the answer carries its source.

Agents reach it over MCP with `memory_search`, `memory_read`, `memory_explain_sources`, `memory_save`, `memory_propose_update` and `memory_apply_update`. Saving raw text happens right away; structured facts wait for your review. The app also has a Sigma knowledge graph with clustering, search and saved layouts, though most work runs through the CLI and the UI at `http://127.0.0.1:8765/index.html`.

Building from source takes Node.js 22+ and npm: `npm install`, `npm run build:all`, then `init --root .umos`. The README shows a stdio config pointing at `dist/cli/index.js`. Exposing the HTTP endpoint beyond your machine requires `--token` or `NEURAKEEP_MCP_TOKEN`. The code is Apache-2.0; the hosted tier with SSO, team spaces and billing is a separate paid subscription and is not needed for local use.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add neurakeep -- npx -y neurakeep
```

### Codex

**Platform CLI**
```bash
codex mcp add neurakeep -- npx -y neurakeep
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "neurakeep": {
            "command": "npx",
            "args": [
                "-y",
                "neurakeep"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "neurakeep": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "neurakeep"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add neurakeep npx -y neurakeep
```

## When to use it
- trace which document a remembered fact came from
- load a folder of PDFs and Markdown into local memory
- review extracted entries before they become permanent
- keep one memory layer for several MCP clients
- search past decisions and failures instead of rereading logs

## Example prompts
- Search memory for what we decided about the auth schema
- Save this text to memory and list the proposals waiting for review
- Propose an update to the deploy fact and show which source it cites

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
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