# Dify — Open-Source LLM App Development Platform

> Visual platform for building AI applications with workflow orchestration, RAG pipelines, agent capabilities, and model management. Supports 100+ models. 85,000+ GitHub stars.

## Install

Save as a script file and run:

## Quick Use

```bash
# Docker one-line deploy
git clone https://github.com/langgenius/dify.git
cd dify/docker
cp .env.example .env
docker compose up -d
```

Open `http://localhost/install` to set up your admin account. Start building AI apps visually.

---

## Intro

Dify is an open-source LLM application development platform with 85,000+ GitHub stars that provides a visual interface for building AI workflows, RAG pipelines, and agent applications. It supports 100+ models from OpenAI, Anthropic, local Ollama instances, and more. Instead of writing boilerplate code for every AI app, Dify gives you a drag-and-drop canvas to orchestrate LLM calls, knowledge retrieval, tool use, and conditional logic. Best for teams building production AI applications who want rapid prototyping with enterprise-grade features. Works with: Claude, GPT-4, Gemini, Llama, Mistral, and 100+ models. Setup time: under 5 minutes with Docker.

---

## Core Features

### Visual Workflow Builder
Drag-and-drop canvas for building AI workflows:
- LLM nodes (any model)
- Knowledge retrieval nodes (RAG)
- Tool nodes (API calls, code execution)
- Conditional branches
- Variable passing between nodes

### RAG Pipeline
Built-in document ingestion and retrieval:
- Upload PDF, DOCX, TXT, Markdown, HTML
- Automatic chunking and embedding
- Multiple embedding models supported
- Hybrid search (keyword + semantic)
- Citation tracking in responses

### Agent Mode
Create AI agents with tool access:
- Web search
- Code interpreter
- API calling
- Custom tools via OpenAPI spec

### Model Management
Switch between 100+ models without code changes:

| Provider | Models |
|----------|--------|
| OpenAI | GPT-4o, GPT-4, GPT-3.5 |
| Anthropic | Claude Opus, Sonnet, Haiku |
| Google | Gemini Pro, Flash |
| Local | Ollama, vLLM, LocalAI |
| Azure | Azure OpenAI |

### Enterprise Features
- SSO authentication
- Workspace management
- Usage analytics
- API rate limiting
- Audit logging

### Key Stats
- 85,000+ GitHub stars
- 100+ supported LLM models
- 1,800+ contributors
- Used by 200,000+ organizations
- Self-hosted or cloud options

### FAQ

**Q: What is Dify?**
A: Dify is an open-source platform for building AI applications visually, with drag-and-drop workflow orchestration, RAG pipelines, and agent capabilities supporting 100+ LLM models.

**Q: Is Dify free?**
A: Yes, the community edition is open-source under Apache 2.0. Enterprise edition available for teams needing SSO, audit logs, and premium support.

**Q: Can I self-host Dify?**
A: Yes, deploy with Docker in under 5 minutes. All data stays on your infrastructure.

---

## Source & Thanks

> Created by [LangGenius](https://github.com/langgenius). Licensed under Apache 2.0.
>
> [dify](https://github.com/langgenius/dify) — ⭐ 85,000+

Thanks to the LangGenius team for democratizing AI application development.

---

<!-- ZH -->

## 快速使用

```bash
git clone https://github.com/langgenius/dify.git
cd dify/docker
cp .env.example .env
docker compose up -d
```

打开 `http://localhost/install` 设置管理员账号，开始可视化构建 AI 应用。

---

## 简介

Dify 是一个开源 LLM 应用开发平台，GitHub 85,000+ stars。提供可视化界面构建 AI 工作流、RAG 管道和 Agent 应用，支持 100+ 模型。拖拽式画布编排 LLM 调用、知识检索、工具使用和条件逻辑。适合需要快速原型和企业级功能的 AI 应用开发团队。支持 Docker 一键部署。

---

## 来源与感谢

> Created by [LangGenius](https://github.com/langgenius). Licensed under Apache 2.0.
>
> [dify](https://github.com/langgenius/dify) — ⭐ 85,000+

---
Source: https://tokrepo.com/en/workflows/061e23c5-890b-455a-9d30-d066e5f98948
Author: AI Open Source