What it does
Dify is a platform for building apps powered by AI language models. You drag and connect steps on a visual canvas to create a workflow, such as a chatbot that answers from your company documents or an assistant that completes tasks with online tools.
It works with hundreds of AI models from many providers, as well as models you host yourself. It can read PDFs, slide decks and other documents so your app can answer questions about them (a method called RAG, short for retrieval-augmented generation). It also includes "agents" that can run commands and use tools to finish open-ended tasks.
Dify keeps logs so you can see how your app performs over time, and every app comes with an API (a doorway that lets other programs use it). You can use the hosted Dify Cloud or install it on your own server.
Who it's for
Teams and individuals who want to build AI apps and automations with little or no code.
Can I use it without coding?
With some setup. There is a hosted cloud version. Running it yourself uses Docker and a few commands. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- Runs on
- Server, Cloud, Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Try the hosted Dify Cloud without managing a server, or host it yourself.
- To self-host, install Docker and start Dify with Docker Compose.
- Open the Dify dashboard in your browser to finish setting it up.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
- No standard license listed. Check the GitHub page before using it for business.
- More on staying safe
Where people are talking about it
- Dify, a visual workflow to build/test LLM applicationsHacker News · Apr 2024