GH Repository · langgenius
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
- stars
- 156,086
- 30-day movement
- +520173/day
- Related entries
- 60
- Connections
- 5
node/pnpmagent-appdeepseekskillsagentic-workflowagentic-aiaillmpythonclaudelow-codeagentmakegptnextjsnodemcpagentic-frameworkworkflowgenaiTypeScriptautomationopenaino-code
Dify is a collaborative workspace for building agentic workflows and RAG pipelines with support for many AI models and tools. It can be deployed on cloud, VPC, or self-hosted, letting teams carry a prototype through to production on the same stack.
You want a single low-code/no-code platform to design, run, and deploy LLM agents and RAG applications without assembling separate infrastructure.
Use it to
- Build agentic workflows visually
- Assemble RAG pipelines over your data
- Prototype with GPT, Claude, or DeepSeek models
- Deploy to cloud, VPC, or self-hosted environments
- Collaborate with a team on one workspace
For Teams building LLM apps without heavy coding
- Role
- agent-app
- Language
- TypeScript
- Licence
- custom (licence file present)
- Forks
- 24,646
- Open issues
- 387
- Last push
- 2026-09-17
- Latest release
- 0.2.1 · 2023-05-15
topicsagentic-workflowraglow-codellmself-hostedautomation