# Mnema — Shared Brain for You and Your AI Agents

Mnema gives AI agents MCP access to shared docs, decisions, and step-by-step flows. Run it on your own infrastructure or connect a hosted endpoint.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: nbkdoesntknowcoding
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/nbkdoesntknowcoding/mnema/tree/HEAD/apps/api
- Updated: 2026-10-06
- HTML: https://affpapa.org/en/nevibecode/mcp/mnema-shared-brain-for-you-and-your-ai-agents

## What it does

Mnema stores project knowledge in a shared workspace and exposes it to MCP clients. An agent can read a document, follow a flow, and suggest a change for approval. The core includes folders, search, a collaborative editor, document history, and export, while the knowledge graph and meeting features belong to separate commercial modules.

Self-hosting requires Docker and Docker Compose. Run `./scripts/self-host-init.sh` to create secrets and `.env`, then start the stack with `docker compose up -d --build`; it includes Postgres, Redis, API, collaboration, workers, and web services. The local UI uses `http://localhost:4321`, and clients connect through `http://localhost:8080/mcp`. A self-hosted deployment will not start without Docker and Docker Compose. `VOYAGE_API_KEY` enables semantic search and `GEMINI_API_KEY` enables autocomplete; both stay off until configured.

## Requirements
- Remote server: `https://api.theboringpeople.in/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mnema https://api.theboringpeople.in/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add api --url https://api.theboringpeople.in/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "api": {
            "url": "https://api.theboringpeople.in/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "api": {
            "type": "http",
            "url": "https://api.theboringpeople.in/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http api https://api.theboringpeople.in/mcp
```

## When to use it
- give agents access to project documentation
- keep team decisions in a shared workspace
- guide an agent through a repeatable workflow
- let an agent propose edits to stored documents

## Example prompts
- Read the project decision about this issue and explain what the team chose.
- Walk through the release flow step by step and tell me what comes next.
- Find the relevant workspace document and draft a proposed update for it.

## Similar
- [second-brain](https://affpapa.org/en/nevibecode/skills/second-brain.md) — skill · 2800 installs
- [second-brain-lint](https://affpapa.org/en/nevibecode/skills/second-brain-lint.md) — skill · 2500 installs
- [company-brain](https://affpapa.org/en/nevibecode/skills/company-brain.md) — skill · 357 installs
- [second-brain MCP](https://affpapa.org/en/nevibecode/mcp/second-brain-mcp.md) — MCP server · ★ 6
- [karpathytalk-community](https://affpapa.org/en/nevibecode/skills/karpathytalk-community.md) — skill · 597 installs
- [principle-separate-before-serializing-shared-state](https://affpapa.org/en/nevibecode/skills/principle-separate-before-serializing-shared-state.md) — skill · 5100 installs

---
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