Dify
Visual platform for building, testing, and deploying LLM apps and agent workflows
View on GitHubWhat it solves
The collaboration gap between technical and non-technical team members building AI workflows: Dify lets both work in the same system without either group hitting a wall.
Overview
Dify is a visual LLM app platform, drag-and-drop workflow editor, built-in RAG pipeline, model management across 20+ providers, and one-click API deployment. It bridges the no-code and code worlds: non-technical team members can compose agent workflows visually, while engineers can extend them with custom code nodes or call the exported API from their own stack.
Key facts
- Language
- TypeScript
- License
- Apache 2.0
- Maturity
- Community canon
- Maintainer
- langgenius
- Reviewed
- 2026-06-11
Where to start
The workflow engine directory shows how nodes, edges, and variables map between the visual editor and the runtime, read this before building custom node types.
api/core/workflow/Technologies
More in this domain
LangGraph
Stateful multi-agent orchestration for LLM applications
The state management problem in multi-agent systems: how you build agents that pass context across turns without losing the execution thread.
AutoGen
Multi-agent conversation framework from Microsoft Research
How to coordinate multiple specialized agents toward a shared goal without writing low-level orchestration logic by hand.
CrewAI
Role-based multi-agent orchestration for collaborative task execution
The boilerplate problem in multi-agent setup: defining roles, delegation rules, and task routing without writing a custom orchestration graph.