Visual workflow builder
Build AI apps and workflows with a drag-and-drop interface so teams can move from idea to implementation without assembling every piece manually.
Dify is an agentic workflow builder for creating, deploying, and managing AI apps, agents, and RAG pipelines. It supports cloud and self-hosted use, with free, paid, education, and enterprise paths.
Dify is an agentic workflow builder for developing, deploying, and managing autonomous agents, RAG pipelines, and related AI applications. The homepage positions it as a way for teams to build production-ready agentic workflows with a visual interface and supporting backend services.
The product combines workflow design, model selection, retrieval-augmented generation, tools, integrations, and observability in one platform. The site also frames Dify for different deployment and buying contexts, including cloud service, self-hosted community edition, education, partner, and enterprise use.
Pricing information shows a free Sandbox tier, paid Professional and Team plans, and a contact-sales path for enterprise needs. The education page adds a free option for students and educators and a self-hosted community edition for controlled campus deployment.
Build AI apps and workflows with a drag-and-drop interface so teams can move from idea to implementation without assembling every piece manually.
Work with global large language models and compare performance across open-source and proprietary providers, including options listed on the pricing page.
Connect data sources into RAG pipelines by extracting, transforming, and indexing information into vector databases for LLM use.
Link external APIs, databases, and services through native MCP integration, including support for HTTP-based MCP services with pre-authorized and auth-free modes.
Expand applications with tools and plugins, then publish workflows or agents as a standard MCP server for use across MCP clients.
Use the platform’s observability and backend-as-a-service approach to manage production workflows without building every operational layer from scratch.
Build agentic applications with a visual workflow that can be deployed and managed from the same platform, rather than stitching together separate tools for orchestration and operations.
Prepare internal knowledge assistants by extracting source data, transforming it, and indexing it into vector databases for RAG-based retrieval.
Connect existing services through MCP, APIs, databases, and plugins when the AI application needs to interact with external systems.
Use the cloud service for quick setup, or choose the self-hosted community edition when the requirement is controlled on-campus deployment.
Start with the free Sandbox or a lower-tier paid plan, then move up as app count, team size, message volume, or workflow throughput increases.
Dify is built for teams that want to design, deploy, and manage agentic workflows, RAG pipelines, and AI applications from one platform. The source also shows plans for students and educators, independent developers and small teams, medium-sized teams, and enterprise buyers.
The pricing page shows a free Sandbox tier, paid Professional and Team plans, and a contact-us flow for enterprise options. It also says students and educators can use Dify for free.
The homepage describes drag-and-drop creation of AI apps and workflows, access to multiple global LLMs, RAG pipelines, tools, agent strategies, observability, and MCP-based integrations. The pricing page also lists support for OpenAI, Anthropic, Llama2, Azure OpenAI, Hugging Face, and Replicate.
The source does not provide a complete integrations catalog, but it does mention native MCP integration, support for HTTP-based MCP services, and the ability to publish a workflow or agent as a standard MCP server.
The education page indicates Dify Cloud Service for ready-to-use tools and Dify Community Edition for free self-hosted deployment on campus. The pricing page also distinguishes between cloud plans and self-hosted pricing.
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI.
AakarDev AI helps teams manage AI provider access, project-level setups, logs, and analytics from one dashboard. It supports BYOK workflows and lists providers including OpenAI, Google Gemini, Anthropic, Groq, Mistral AI, and Perplexity AI.
Arduino VENTUNO Q is an edge AI computer for AI and robotics applications. It combines AI inference and deterministic control on a single board and is designed to work with Arduino App Lab.
Devin is an AI coding agent and software engineer that helps developers and engineering teams plan and execute complex software tasks. It is available through desktop, cloud, JetBrains, and CLI surfaces, with plans for individuals, teams, and enterprises.
Open Computer Use is an open-source Computer Use service wrapped as MCP for macOS, Linux, and Windows. It helps AI agents and MCP clients run desktop automation workflows through client setup commands or manual MCP configuration.
Struere is an AI-native platform for turning spreadsheet data into structured operational software with dashboards, alerts, and automations. It is aimed at teams that want to replace manual spreadsheet workflows without building custom tools from scratch.