Dify is an open-source LLMOps platform for building AI apps with visual workflows, RAG, agents, and model management. 130K+ stars. Apache 2.0.
This block should tell both the user and the agent what to copy, install, and apply first.
# Docker Compose (quickest)
git clone https://github.com/langgenius/dify.git
cd dify/docker
cp .env.example .env
docker compose up -d
# Open http://localhost/installDify is an open-source LLMOps platform combining AI workflow builder, RAG pipeline, agent capabilities, model management, and observability in one platform. With 130,000+ GitHub stars and Apache 2.0 license, it provides a visual workflow canvas, supports hundreds of LLM models, built-in RAG with document indexing, AI agents with tool use, prompt IDE, and enterprise features. Self-host with Docker or use Dify Cloud.
Best for: Teams building production AI applications with visual workflows and RAG Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
Q: What is Dify? A: Open-source LLMOps platform with 130K+ stars. Visual workflows, RAG, agents, model management. Apache 2.0.
Q: How do I install Dify? A: git clone, cd docker, docker compose up -d. Access at localhost/install.
langgenius/dify — 130,000+ GitHub stars
TaskWeaver is a Microsoft code-first agent framework for data analytics tasks. 6.1K+ stars. Planning, stateful execution, DataFrames, plugins. MIT.
AIChat is a CLI for 20+ LLM providers with shell assistant, RAG, agents, and function calling. 9.7K+ stars. MIT/Apache 2.0.
Khoj is a personal AI app for chat, search, and knowledge management. 33.8K+ stars. Multi-LLM, docs, Obsidian, WhatsApp, custom agents. AGPL-3.0.