OSS TanbouOverview
Dify is an LLM application development platform that brings AI workflows, RAG pipelines, agents, model management, and observability into one interface. It can run in the cloud or be self-hosted, with APIs for integration into existing business logic.
Based on official documentation; not hands-on tested · Content checked:
Connect models, retrieval, and tools in visual workflows
A visual canvas assembles AI workflows with multiple model providers, RAG from document ingestion through retrieval, Function Calling or ReAct agents, prompt comparison, and log and performance observation. Corresponding APIs expose the platform's capabilities to other applications.
Sources: [1]
For moving LLM applications from prototype to operation
It is a candidate for teams building internal assistants, retrieval-backed applications, or multi-step agents while comparing models and tools. Dify Cloud, a self-hosted Community Edition, and organization-focused offerings provide different operating models.
Sources: [1]
Review resources, external models, and additional license terms
The self-hosted minimum is two CPU cores and 4 GiB of RAM, and the README workflow assumes Docker Compose 2.24.0 or later. Cost and data handling for model and retrieval providers remain separate design decisions. The Dify Open Source License is based on Apache 2.0 with additional conditions, so commercial and redistribution scenarios require review of the license text.
Sources: [1]
Official sources
- [1]Dify README(2026-09-13)
Supplemental curator note
Selected for growing beyond modest early English-language buzz through multilingual repository, documentation, site, and reusable workflow surfaces.
Growth trends
Last 30 days
155,555 Stars
Trend data is still being collected.
Built with
- TypeScript
- Python
- Next.js
Categories and tags
Tags
GitHub Topics
- ai
- gpt
- llm
- openai
- python
- agent
- nextjs
- workflow
- genai
- automation
- low-code
- mcp
GitHub dataView detailed GitHub data
- Stars
- 155,555
- Forks
- 24,570
- Watchers
- 836
- Open issues
- 364
- Contributors
- 454
- Primary language
- TypeScript
- License
- Not determined
- Repository last updated
- Sep 12, 2026
Explore next
- n8n204,119 Stars
A fair-code platform combining a visual canvas and code for service integrations, workflows, and AI agents.
TypeScript - Ollama180,764 Stars
A runtime for downloading and running open models on a computer or server through a CLI and local API.
Go - Transformers165,220 Stars
A Python framework for inference and training with pretrained text, vision, audio, and multimodal models.
Python - AUTOMATIC1111 Stable Diffusion WebUI164,915 Stars
A Gradio UI for Stable Diffusion image generation, editing, model selection, extensions, and APIs.
Python - LangChain146,205 Stars
A Python framework that connects models, tools, retrieval systems, and other components for LLM applications and agents.
Python
Report incorrect information
Tell us if any listing information is incorrect or outdated.