Dify
Summary
An open-source platform for building production LLM applications — visual workflows, RAG, and agents in one place.
Screenshots
Description
Dify is an open-source development platform for language-model applications. It covers the whole path from prototype to production: prompt design, retrieval pipelines, agent workflows, evaluation, and serving — with a visual builder over the top and an API underneath.
What is included
- Visual workflow builder for chaining models, conditions, code steps, and tools into reliable pipelines
- RAG pipeline with document ingestion, chunking, embedding, retrieval, and reranking configurable without writing the plumbing
- Agents with tool calling, using built-in tools or your own
- Model support across every major provider plus local runtimes, switchable per node
- Observability. Logs, traces, and annotation so you can see why a response went wrong and fix it
- Backend as a service. Every application gets an API, so the front end is yours to build
Deployment
Self-host with Docker Compose or Kubernetes — the whole platform is open source — or use the hosted cloud. Self-hosting is why it is popular with teams whose data cannot leave their infrastructure.
Free for self-hosting; the cloud has a free tier and paid plans by message volume and team size.
Reviews
Similar App Suggestions
Gumloop
A visual canvas for AI automations that anyone on the team can build, share, and run.
Browserbase
Headless browser infrastructure for AI agents — sessions, stealth, proxies, and live view, without running Chrome yourself.
Browser Use
The open-source library that lets AI agents actually use websites — clicking, typing, and reading like a person.
CrewAI
The multi-agent framework where agents have roles and collaborate as a crew — plus a platform to run them in production.
Relevance AI
Build a team of specialist AI agents — recruit, brief, and manage them like staff, with no code required.