Discover. Extend. Build.

Tool for integration with e2b.dev.

PaddleOCR plugin provides several capabilities from PaddleOCR, including text recognition, document parsing, and more

The next generation of real-time intelligent search engine for AI provides multi-channel and full-network content in a user-friendly format for your applications.

A plugin that allows you use alipay tools

Current OpenAI language, embedding, moderation, and audio models.

OpenRouter is a powerful platform that provides access to a diverse set of language models, including both commercial and open-source options.

a collection of subscription and paid tools

OceanBase database query tool.

AgentQL API integration for web data extraction.

Brave Search offers programmatic web search capabilities, providing private, high-quality search results in various formats with comprehensive sources and an intuitive structure.

Models provided by Ant Group, such as Ling-3.0-flash, Ling-2.6-1T, and Ring-2.6-1T.

The Agora Conversational AI extension enables developers to build voice assistants powered by Dify Agent.

Data visualization based on LLM and natural language interaction.

An intelligent data analysis tool based on LLM and natural language interaction, featuring built-in data query and data visualization, as well as report generation capabilities.

DupDub

TTS tools provided by Fish Audio.

AI-friendly hyper application platform for no-code enterprise applications and hyper-automation workflows

A connector that connects kintone application with Dify

Connect to Oracle database and execute SQL queries using Thin Mode.

Connect to Oracle database and execute SQL statements.

PPIO is a cloud infrastructure provider offering a wide range of AI model services and cost-effective GPU computing services.

SiliconFlow provides access to various models (LLMs, text embedding, reranking, STT, TTS), configurable via model name, API key, and other parameters.

A Dify tool plugin that integrates with the remote Cloudsway intelligent search API to provide web search functionality.

A powerful AI-native search engine and web content extraction tool that provides highly relevant search results and raw content extraction from web pages.

Build Dify applications using Weaviate for Vector, Generative search and more

GMI Cloud

Apify is the largest marketplace of tools for web scraping, automation, and data for AI.

Bocha is a Chinese search engine for AI, you can get enhanced search details from billions of web documents, including weather, news, wikis, healthcare, train tickets, images, and more.

Real-time web search for AI agents powered by Octen. Fast, fresh, and relevant — search the web with ultra-low latency and get LLM-ready results.

AI-powered web automation that turns natural language into browser actions

AI agent governance for Dify. Cryptographically sign agent actions into an audit trail, verify signatures, and require multi-party authorization for high-risk actions. Powered by Asqav.

Programmable inbox for Atomic Mail in Dify Agent and Workflow apps. Register or connect credentials, read and send mail, and use JMAP escape-hatch calls. Use the Help tool and README for setup details, and after register configure hourly inbox polling as an Agent turn.

OpenAI-compatible serverless models on the Qubrid AI Platform.

SkillWard is a Skill & MCP Security Scanner that identifies potential risks before AI Agent Skills and MCP projects are published or deployed. Beyond static analysis and LLM evaluation, it executes suspicious Skills in isolated Docker sandboxes, replacing uncertain warnings with runtime evidence.

Designed specifically for downstream tasks of large language models (LLMs), this service can recognize text from documents or images and intelligently restore the reading order of the content, outputting a standardized Markdown format. It supports OCR recognition across more than 10 common document layouts and over 52 languages, enabling LLMs to more efficiently utilize document content in scenarios such as understanding, generation, and question answering.

xParse is designed for LLM downstream tasks, accurately recognizes content in PDF/Word/Excel/images and converts to standard formats (markdown, json). Excels at complex document understanding and restoration. Free 1000 pages/day for developers.

Generate licensed music, video soundtracks, and frame-accurate sound effects with the Sonilo API. Bring your own Sonilo API key.

Shisa AI models for Japanese and English LLM, speech recognition, and speech synthesis.

Official DeepSeek models, including deepseek-v4-flash and deepseek-v4-pro.

Tongyi

Call Volcengine Ark endpoints (Endpoint ID) from Dify. Supports LLM, text embedding, and speech-to-text.

Model providers compatible with OpenAI's API standard, such as LM Studio or llama.cpp Service.

Ollama

Current OpenAI language, embedding, moderation, and audio models.

Models provided by Tencent Hunyuan, such as hunyuan-standard, hunyuan-standard-256k, hunyuan-pro, hunyuan-role, hunyuan-large, hunyuan-large-role, hunyuan-turbo-latest, hunyuan-large-longcontext, hunyuan-turbo, hunyuan-vision, hunyuan-turbo-vision, hunyuan-functioncall and hunyuan-lite.

SiliconFlow provides access to various models (LLMs, text embedding, reranking, STT, TTS), configurable via model name, API key, and other parameters.

Google's Gemini model.

Xorbits Inference

Anthropic's powerful models.

Azure OpenAI Service Model

OpenRouter is a powerful platform that provides access to a diverse set of language models, including both commercial and open-source options.

Minimax AI models for LLM, text embedding, and text-to-speech

ZHIPU AI

Embedding and Rerank Model Supported

A blazing fast inference solution for text embeddings models.

Models provided by ModelScope

The models of Amazon Bedrock

vllm provider for extra_body support https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#id5

ComfyUI is a tool for generating images which can be deployed locally.

Chart Generator is a tool for generating statistical charts like bar chart, line chart, pie chart, etc.

The SiliconFlow plugin provides current image generation, image editing, and video generation tools.

Activating humanity's potential through generative AI

Azure DALL-E art

Stable Diffusion is a tool for generating images which can be deployed locally.

A dify plugin for generating visual charts, wrapped based on AntV visualization solutions, supporting 25+ common types of visual charts. It allows users to create various types of charts through dify tools.

YouTube

Gemini Image Generation and Editing

TongYi AIGC: Supports full-featured image and video generation using the latest Alibaba Tongyi models (HappyHorse1.1, wan2.7, qwen-image2.0, Z-image, wan2.6,wan2.5, wan2.2, and wanx2.1).

A tool for generating QR code (quick-response code) image.

Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.

GetImg API integration for image generation and scraping.

Doubao Image/Video API integration for AI image generation by Volcengine.

Seedream AIGC: Supports full-featured image and video generation across the series, powered by the latest Doubao Dream models (Seedance-2.5, Seedance-2.0, Seedance-2.0-mini, Seedream-5.0 Pro/Lite, Seedream-4.5, Seedream-4.0, Seedance-1.5-pro and Seedance-1.0-pro-fast).

The image/video generation API provided by ZhipuAI, support cogview and cogvideox models.

Process and convert video and audio files using FFmpeg. Provides tools for getting video information, converting formats, trimming, compressing and extracting audio.

Innovative AI for Image Generation

AI text-to-image and image-to-image generation plugin powered by ModelScope Qwen-Image

CogView art

Get transcripts from YouTube videos

An image generation plugin for the Dify platform, supporting text-to-image conversion, sketch refinement, and automated creative poster generation.

AI text-to-image generation plugin powered by Juxin API with Gemini 3 Pro Image Preview model

Kling AIGC: Support full-generation and editing operations for images and videos, using the latest Kling models (3-Omini, O1, kling-v3, kling-v2.6, and kling-v2.5).

Hailuo AIGC: Supports full pipeline operations for image and video generation, editing, etc., powered by the latest MiniMax models (MiniMax-H3, MiniMax-Hailuo-2.3, MiniMax-Hailuo-2.3-fast, MiniMax-Hailuo-02, T2V-01-Director, and image-01).

A tool for sending emails with SMTP support, including attachments, CC, and BCC.

Comprehensive Notion integration allowing you to search, retrieve, create, and update pages, databases, and comments directly from your Dify applications. Query databases with filters, manage database properties, and organize your Notion workspace efficiently.

Connect to Microsoft Excel 365 for spreadsheet operations

Interact with Slack - send and manage messages, channels, users, reactions and files via the Slack Web API, or post via an Incoming Webhook.

Integrate Microsoft Outlook with Dify - read, send and organize email, and manage calendar events.

Jira is a software product developed by Atlassian that allows bug tracking, issue tracking and agile project management.

DingTalk group robot

Wecom group bot

Feishu Spreadsheet, requires the following permissions: sheets:spreadsheet.

Feishu base, requires the following permissions: bitable:app.

Feishu cloud document, requires the following permissions: docx:document、drive:drive、docs:document.content:read.

Feishu Task, requires the following permissions: task:task:write、contact:user.id:readonly.