dify-official-plugins: Extending Dify with AI Models, Tools, and Agent Strategies

Summary
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.
At a glance
- Added to OSRepos
- August 18, 2026
- Last analyzed
- August 18, 2026
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
Dify is an open-source platform dedicated to developing LLM-powered AI applications, enabling developers and businesses to efficiently build, deploy, and manage AI-driven solutions. The dify-official-plugins repository serves as the central hub for all official models and tools, which have been migrated from the main Dify repository starting with Dify v1.0.0 in February 2025. These plugins are made available on the Dify Marketplace, offering a wide range of functionalities to Dify users.
Installation
For Python plugins within this repository, dependency management is handled using pyproject.toml and uv.lock. To update or add new dependencies, declare them in pyproject.toml, then run uv lock to generate or update the uv.lock file. Both files should be committed. To reproduce a locked environment, navigate to the plugin directory and execute uv sync --frozen. Legacy plugins that have not yet migrated to uv.lock may still utilize requirements.txt for dependency declarations.
Examples
The dify-official-plugins repository provides several types of plugins to extend Dify's functionality:
- Models: These plugins transform AI model management within Dify, allowing users to configure, update, and utilize various models across chatbots, agents, chatflows, and workflows.
- Tools: Tools add specialized capabilities to Dify applications, enhancing agents and workflows with domain-specific features for tasks like data analysis, content translation, and custom integrations.
- Agent Strategies: Designed for the new Agent Nodes in Dify chatflows and workflows, these strategies provide reasoning mechanisms for autonomous tool selection and multi-step execution. Examples include Chain-of-Thoughts, Tree-of-Thoughts, Function call, and ReAct.
- Extensions: Extensions facilitate external integrations via HTTP webhooks, enabling the creation of custom APIs to manage complex workflows, process data, or connect with external services.
Why Use `dify-official-plugins`?
Leveraging the dify-official-plugins repository offers significant advantages for Dify users. It provides a centralized, officially maintained source for enhancing Dify's core capabilities with a diverse array of models, tools, and advanced agent strategies. By utilizing these plugins, developers can streamline the creation of sophisticated AI applications, ensure compatibility with the Dify platform, and benefit from ongoing updates and support directly from the Dify team. The availability of these plugins on the Dify Marketplace further simplifies discovery and integration into your projects.
Links
Explore Dify and its ecosystem further through these official resources:
Source repository
Open the original repository on GitHub.
17 counted GitHub visits
Related repositories
Similar repositories that may be relevant next.

web-design: A Claude Code SKILL for Spec-First Web Page Design
October 3, 2026
The web-design project is a Claude Code SKILL designed to streamline the creation of beautiful and consistent web pages. It emphasizes a 'spec first, code second' approach, ensuring design principles are established before development begins. This tool helps generate UI, visuals, motion, and responsiveness that are consistent across pages and easily editable.

OOMWOO: Build Your Own Open-Source, Hackable Robot Vacuum Cleaner
October 2, 2026
OOMWOO is an ambitious open-source project enabling users to build their own robot vacuum cleaner using Raspberry Pi, 3D printing, and ROS2. It emphasizes local operation, hackability, and integration with Home Assistant, providing a high-quality, customizable home appliance. This project aims to deliver a fully open hardware, software, and firmware solution for autonomous home cleaning.

Shepherd: Reversible Execution Traces for Programmable Meta-Agents
October 2, 2026
Shepherd is a Python runtime substrate designed for agent work requiring inspection, reversibility, and supervision. It records agent runs as durable, inspectable execution traces, enabling meta-agents to observe, fork, replay, and revert any operation. This framework couples agents and environments using a copy-on-write fork, offering significant performance benefits and robust permission enforcement.

Agent Anvil: CI-First Evaluation Harness for Tool-Using AI Agents
October 1, 2026
Agent Anvil is a robust, CI-first evaluation harness designed for AI agents that utilize tools. It meticulously runs scenario suites, captures detailed traces of agent behavior, and provides semantic grading to identify issues. The platform excels at clustering failures and suggesting concrete fixes for prompts, tools, and guardrails, ensuring agents behave safely and effectively.