本国帮得当前常用模式

Requirements

• Apple Silicon Mac (M1/M2/M3/M4) — required for MLX GPU inference
• 16 GB RAM minimum for the default model (Qwen3-8B-4bit, ~4.5 GB); 32 GB+ lets you run larger enrichment models
• macOS 14+
• Node.js 22+ (LTS v24 recommended) and pnpm 11+
• Bun 1.1+ as the runtime (we use pnpm to install deps; bun to run them)
• Python 3.13+ with uv
• PostgreSQL 17 with pgvector extension
• Redis (optional but recommended)
• Firecrawl API key — used for all web page scraping
• yt-dlp (optional — YouTube transcript extraction)

Quick install (recommended)

bash installer/bootstrap.sh

This runs the full chain: prerequisites (Homebrew packages, Bun, Python venv with mlx-lm), database setup, schema, and launchd services. Idempotent — safe to re-run.

Manual install

If you'd rather install the prerequisites yourself:

```bash

Bun via its official installer (no Homebrew formula). We use Bun as the

runtime (Bun.serve, Bun.spawn) but never `bun install` — that hits a

Edit .env if needed (defaults work for local setup)

3. Run setup (creates database, installs Bun + Python deps)

bash scripts/setup.sh

5. Start all services (installs as launchd daemons)

bash scripts/install-services.sh

Gradual Setup

You don't need all services running to get started:

1. Minimum: PostgreSQL + Embedding Service + MCP Server — gives you store and search
2. Add enrichment: Start the mlx-lm server — memories get auto-enriched with summaries and tags
3. Add caching: Start Redis — faster repeated searches and embedding lookups
4. Add UI: Start the web UI — browse and manage memories visually
5. Add ingestion: Set FIRECRAWL_API_KEY in .env and install the bookmarklet — save web content from your browser.

To skip enrichment entirely (e.g., while setting up), set DISABLE_ENRICHMENT=true in .env.

Install as launchd daemons (auto-start on boot)

bash scripts/install-services.sh

Uninstall all services

bash scripts/uninstall-services.sh

Quick Start

```bash

Optional, for Gmail integration via the agents/ subsystem

brew install gogcli

2. Configure environment

cp .env.example .env

4. Create a Python venv for the LLM enrichment server

python3 -m venv ~/.mlx-venv ~/.mlx-venv/bin/pip install mlx-lm

MCP Client Configuration

OpenBrain exposes both HTTP and stdio MCP transports. Configure your client to point at whichever it supports.

HTTP transport (recommended — one shared server for all clients):

{
  "mcpServers": {
    "openbrain": {
      "type": "http",
      "url": "http://localhost:6277/mcp"
    }
  }
}

stdio transport (for clients that spawn the server as a subprocess):

{
  "mcpServers": {
    "openbrain": {
      "type": "stdio",
      "command": "bun",
      "args": ["run", "/path/to/openbrain/src/stdio.ts"]
    }
  }
}

The exact config-file location depends on your client (e.g. .mcp.json in a project root, or a global config under your home directory).

Create an RSS source via the REST API:

echo '{"kind":"rss","name":"HN","config":{"feedUrl":"https://news.ycombinator.com/rss"},"intervalSeconds":3600}' \ | curl -X POST http://localhost:6277/api/sources -H 'content-type: application/json' --data @-

Homebrew packages

brew install postgresql@17 pgvector redis uv yt-dlp pnpm brew services start postgresql@17 brew services start redis