# Self-Hosted AI Starter Kit — Local AI with n8n

> Docker Compose template by n8n that bootstraps a complete local AI environment with n8n workflow automation, Ollama LLMs, Qdrant vector database, and PostgreSQL. 14,500+ stars.

## Install

Save in your project root:

## Quick Use

```bash
git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git
cd self-hosted-ai-starter-kit
cp .env.example .env
docker compose --profile cpu up
```

For GPU acceleration:
- **NVIDIA**: `docker compose --profile gpu-nvidia up`
- **AMD**: `docker compose --profile gpu-amd up`
- **Apple Silicon**: `docker compose up` (uses CPU, or connect to local Ollama)

Access n8n at `http://localhost:5678/` after startup.

---

## Intro

Self-Hosted AI Starter Kit is an official open-source Docker Compose template by n8n that bootstraps a complete local AI development environment in one command. With 14,500+ GitHub stars and Apache 2.0 license, it bundles n8n (400+ integrations), Ollama (local LLMs), Qdrant (vector database), and PostgreSQL into a pre-configured stack. Start building AI workflows, RAG pipelines, and chatbots on your own hardware — no cloud APIs needed, full data privacy guaranteed.

Best for: developers and teams who want a self-hosted AI workflow platform with zero cloud dependencies.
Works with: n8n, Ollama, Qdrant, PostgreSQL, any Ollama-supported model.
Setup time: under 5 minutes.

---

## Self-Hosted AI Starter Kit — Architecture & Components

### Included Services

| Service | Purpose | Port |
|---------|---------|------|
| **n8n** | Low-code workflow automation with 400+ integrations and AI components | 5678 |
| **Ollama** | Run LLMs locally (Llama 3, Mistral, CodeLlama, etc.) | 11434 |
| **Qdrant** | High-performance vector database for embeddings and RAG | 6333 |
| **PostgreSQL** | Persistent data storage for n8n workflows and credentials | 5432 |

### What You Can Build

1. **RAG Chatbots** — Upload documents, embed with Ollama, store in Qdrant, query via n8n chat interface
2. **AI Workflow Automation** — Trigger AI tasks from emails, webhooks, schedules, or 400+ app integrations
3. **Document Processing** — Extract, summarize, and classify documents using local LLMs
4. **Code Generation** — Use CodeLlama for automated code review and generation workflows
5. **Data Analysis** — Connect databases to LLMs for natural language data queries

### GPU Support

| Platform | Command | Notes |
|----------|---------|-------|
| CPU only | `docker compose --profile cpu up` | Slower but works everywhere |
| NVIDIA GPU | `docker compose --profile gpu-nvidia up` | Requires NVIDIA Docker runtime |
| AMD GPU | `docker compose --profile gpu-amd up` | Linux only |
| Apple Silicon | `docker compose up` | CPU mode, or use local Ollama |

### Included Workflow Templates

The starter kit comes with pre-built n8n workflow templates:
- AI chatbot with document RAG
- Email classification and auto-response
- Webhook-triggered AI processing

### Configuration

Key `.env` settings:
```bash
# n8n settings
N8N_ENCRYPTION_KEY=your-encryption-key
N8N_USER_MANAGEMENT_JWT_SECRET=your-jwt-secret

# Ollama model (pulled on first start)
OLLAMA_MODEL=llama3

# PostgreSQL
POSTGRES_PASSWORD=your-password
```

### FAQ

**Q: What is the Self-Hosted AI Starter Kit?**
A: A Docker Compose template by n8n that sets up a complete local AI environment with n8n (workflow automation), Ollama (local LLMs), Qdrant (vector DB), and PostgreSQL in one command.

**Q: Is it free?**
A: Yes, fully open-source under Apache 2.0. All included services are free and self-hosted.

**Q: What hardware do I need?**
A: Minimum 8GB RAM for CPU mode. For GPU acceleration, an NVIDIA or AMD GPU with Docker support. Apple Silicon Macs work with CPU mode.

---

## Source & Thanks

> Created by [n8n-io](https://github.com/n8n-io). Licensed under Apache 2.0.
>
> [self-hosted-ai-starter-kit](https://github.com/n8n-io/self-hosted-ai-starter-kit) — ⭐ 14,500+

Thank you to the n8n team for making self-hosted AI infrastructure accessible with one command.

---

<!-- ZH -->

## 快速使用

```bash
git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git
cd self-hosted-ai-starter-kit
cp .env.example .env
docker compose --profile cpu up
```

GPU 加速：NVIDIA 用 `--profile gpu-nvidia`，AMD 用 `--profile gpu-amd`。
启动后访问 `http://localhost:5678/`。

---

## 简介

Self-Hosted AI Starter Kit 是 n8n 官方开源的 Docker Compose 模板，一条命令搭建完整的本地 AI 开发环境。拥有 14,500+ GitHub Star 和 Apache 2.0 许可证，打包了 n8n（400+ 集成）、Ollama（本地大模型）、Qdrant（向量数据库）和 PostgreSQL。在自己的硬件上构建 AI 工作流、RAG 管道和聊天机器人——无需云 API，数据完全私有。

适合人群：想要零云依赖的自托管 AI 工作流平台的开发者和团队。
包含组件：n8n、Ollama、Qdrant、PostgreSQL。
安装时间：5 分钟以内。

---

## 包含服务

| 服务 | 用途 | 端口 |
|------|------|------|
| n8n | 低代码工作流自动化，400+ 集成 | 5678 |
| Ollama | 本地运行大模型 | 11434 |
| Qdrant | 向量数据库 | 6333 |
| PostgreSQL | 持久化存储 | 5432 |

### 你可以构建的
- RAG 聊天机器人、AI 工作流自动化、文档处理、代码生成、数据分析

### FAQ

**Q: Self-Hosted AI Starter Kit 是什么？**
A: n8n 官方的 Docker Compose 模板，一条命令搭建 n8n + Ollama + Qdrant + PostgreSQL 的完整本地 AI 环境。

**Q: 免费吗？**
A: 完全免费开源（Apache 2.0），所有服务均可自托管。

---

## 来源与感谢

> Created by [n8n-io](https://github.com/n8n-io). Licensed under Apache 2.0.
>
> [self-hosted-ai-starter-kit](https://github.com/n8n-io/self-hosted-ai-starter-kit) — ⭐ 14,500+

---
Source: https://tokrepo.com/en/workflows/92d3cc62-6199-4b1c-a7f1-1b73a1da86a0
Author: TokRepo精选