Vibe Coding Discoverdify
View on GitHubBuild 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.
Dify is an open-source LLM app platform combining a visual agentic workflow builder, RAG pipeline, prompt IDE, agent runtime, and LLMOps. It supports hundreds of models, MCP servers, and tools, and self-hosts via Docker with APIs for integration.
Use Cases
Build agentic AI workflows on a visual canvasShip RAG pipelines with PDF/PPT document ingestionCreate autonomous agents with sandboxed code and file handlingConnect MCP servers and marketplace tools to agentsExpose LLM apps as backend APIsMonitor and improve prompts and datasets in production (LLMOps)Prototype chat apps from a prompt IDESelf-host or deploy AI apps on cloud/VPC
Built With
- Language
- TypeScript
- Frameworks
- Next.js · React · Tailwind CSS · FastAPI · Flask · Celery · PostgreSQL · Redis · Docker · TypeScript · Python · Go
Tags
llm · agents · agentic-workflow · rag · low-code · no-code · workflow-builder · mcp · llmops · observability · prompt-ide · self-hosted · multi-model · baas · tool-calling · orchestration