Git Repository Guide

Dify

Dify

AI/ML Self-hostable Apache-2.0

When to use this

Use this when you want to build production LLM apps with a visual UI instead of code — chatbots, knowledge bases, AI workflows. Self-host on your own server or use their cloud. The most complete all-in-one platform in its category.

YouTube Tutorials

Click any card to watch on YouTube

What is Dify?

Dify is an open-source LLM application development platform. It combines an intuitive visual interface with a powerful backend to help you build, deploy, and monitor AI applications without writing application-layer code.

Key Capabilities

  • Visual Workflow Builder — Drag-and-drop nodes to create complex AI pipelines. LLM calls, code execution, HTTP requests, conditional branching.
  • RAG Pipeline — Built-in document ingestion, chunking, embedding, and retrieval. Upload a PDF and have a chatbot answer questions about it in minutes.
  • Agent — Configure tool-using agents that can browse the web, run code, call APIs.
  • Model Provider Agnostic — Works with OpenAI, Anthropic, Mistral, Ollama (local), and 50+ providers.
  • API & SDK — Every app you build gets an API endpoint you can call from any codebase.
  • Observability — Built-in logs, prompt history, and performance monitoring.

Quick Start with Docker Compose

git clone https://github.com/langgenius/dify
cd dify/docker
docker compose up -d

Open http://localhost to access the dashboard.

Dify vs. Flowise

Dify is more enterprise-complete — better RAG, observability, and team features. Flowise is lighter and faster to get started. Both are excellent choices.