Dify Open Source Projects
Dify is an approach to building applications powered by large language models, combining model access with tools for prompts, data retrieval, and workflow orchestration. It helps teams move from experiments to usable applications by making it easier to connect models to private information, structure multi-step tasks, and expose capabilities through APIs or chat interfaces. These platforms can reduce the amount of custom infrastructure needed while keeping application logic configurable.
Open source offerings in this area include visual workflow builders, retrieval-augmented generation tools, model and tool integrations, and agent frameworks. When choosing one, consider license terms, project maturity, maintenance activity, deployment requirements, model compatibility, and how well it fits existing systems. These tools are useful to developers, product teams, and organizations building or operating LLM applications.
2 repositories · updated September 25, 2026
Graphon: A Python Graph Execution Engine for Agentic AI Workflows
Graphon is an innovative Python-based graph execution engine designed for building agentic AI workflows. It provides a robust framework for orchestrating complex AI tasks, featuring event-driven execution, graph validation, and shared runtime state. This evolving repository already includes a functional engine, built-in nodes, and end-to-end examples for developers.
dify-official-plugins: Extending Dify with AI Models, Tools, and Agent Strategies
The `dify-official-plugins` repository hosts a collection of official plugins for Dify, an open-source platform for developing LLM-powered AI applications. These plugins, including models, tools, agent strategies, and extensions, enhance Dify's capabilities and are maintained by the official Dify team. They are designed to help developers efficiently build, deploy, and manage AI-driven solutions.