# Dify
Dify is an open-source platform for building applications and agents on large language models (LLMs), combining a visual workflow editor, retrieval-augmented generation (RAG) pipelines, agent capabilities, model management, and observability features in a single product developed by LangGenius.[1](https://github.com/langgenius/dify/) Open-sourced in May 2023, the company says it has since grown into one of GitHub's most-starred repositories and a commercial platform used by enterprises including Maersk and Novartis.[2](https://ai.miraheze.org/wiki/Dify.ai)
| Key fact | Detail |
|---|---|
| What it is | Open-source LLM app and agent workflow platform: visual workflows, RAG, agents, model management, observability[1](https://github.com/langgenius/dify/) |
| First release | Open-sourced on GitHub on May 15, 2023[2](https://ai.miraheze.org/wiki/Dify.ai) |
| Developer | LangGenius, founded 2023 by Luyu Zhang and John Wang[2](https://ai.miraheze.org/wiki/Dify.ai) |
| Adoption (vendor-reported) | 100,000 GitHub stars in June 2025, 145,000+ by mid-2026; 1.4 million machines; 2,000+ teams, and 280 enterprises on commercial versions[2](https://ai.miraheze.org/wiki/Dify.ai) • [3](https://www.businesswire.com/news/home/20260309511426/en/Dify-Raises-%2430-million-Series-Pre-A-to-Power-Enterprise-Grade-Agentic-Workflows) |
| Funding | $30 million Series Pre-A at a $180 million valuation, March 2026; roughly $41.5 million total[3](https://www.businesswire.com/news/home/20260309511426/en/Dify-Raises-%2430-million-Series-Pre-A-to-Power-Enterprise-Grade-Agentic-Workflows) • [2](https://ai.miraheze.org/wiki/Dify.ai) |
| License | Apache-2.0-derivative with an added condition requiring a commercial license for multi-tenant deployments[4](https://dify.ai/?utm=theseaitools) • [2](https://ai.miraheze.org/wiki/Dify.ai) |
| Cloud pricing | Free Sandbox tier; paid tiers at $590 and $1,590 per workspace per year (September 2026)[5](https://dify.ai/dify-cloud) |
| Models | Hundreds of proprietary and open-source LLMs from dozens of providers, plus any OpenAI API-compatible model[1](https://github.com/langgenius/dify/) |
## What Dify is
Dify sits between two other ways of building on foundation models. At one end are code frameworks such as [LangChain](https://www.edgepedia.org/langchain), where developers write the orchestration themselves; at the other are no-code chatbot builders. Dify provides a visual interface for assembling AI workflows, a RAG pipeline for grounding model answers in an organization's documents, agent capabilities, model management, and observability features including integrations with Opik, Langfuse, and Arize Phoenix.[1](https://github.com/langgenius/dify/)
A developer can build chatbots, agents, and document-question-answering applications without writing orchestration code, then publish the result as a webapp, a website embed, an API endpoint, or an MCP ([Model Context Protocol](https://www.edgepedia.org/model-context-protocol)) server.[5](https://dify.ai/dify-cloud) The RAG pipeline covers the full path from document ingestion to retrieval, with out-of-box text extraction from PDFs, PPTs, and other common formats.[1](https://github.com/langgenius/dify/)
## Origins and launch history
LangGenius was founded in 2023 by Luyu Zhang and John Wang; Zhang is chief executive and previously served as product director of CODING.[2](https://ai.miraheze.org/wiki/Dify.ai) The company open-sourced Dify on GitHub on May 15, 2023.[2](https://ai.miraheze.org/wiki/Dify.ai)
From that start, the project grew into a global platform. According to the company, Dify ranks among GitHub's most-starred open-source repositories of all time and runs on more than 1.4 million machines worldwide.[3](https://www.businesswire.com/news/home/20260309511426/en/Dify-Raises-%2430-million-Series-Pre-A-to-Power-Enterprise-Grade-Agentic-Workflows)
## How it works
**Visual workflows.** Applications are assembled as graphs of nodes in a visual editor. Agents are defined through LLM Function Calling or the ReAct pattern, and Dify ships 50-plus built-in tools they can call, such as [Google Search](https://www.edgepedia.org/google-search), DALL·E, Stable Diffusion, and [WolframAlpha](https://www.edgepedia.org/wolframalpha).[1](https://github.com/langgenius/dify/) A debugging feature, Debug as Multiple Models, runs up to 4 models simultaneously so developers can compare chatbot outputs side by side.[6](https://docs.dify.ai/en/cloud/use-dify/build/chatbot)
Model-provider abstraction. Dify is model-agnostic: model providers are installed through an Integrations > Model Provider interface, and users can connect OpenAI, Anthropic, Google, xAI, and other providers, swapping them at any time.[7](https://docs.dify.ai/en/quick-start) • [5](https://dify.ai/dify-cloud) The repository describes integration with hundreds of proprietary and open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any [OpenAI API](https://www.edgepedia.org/openai-api)-compatible models.[1](https://github.com/langgenius/dify/)
**Deployment.** Self-hosting is a single-command Docker deploy, and the enterprise offering includes a Helm chart for [Kubernetes](https://www.edgepedia.org/kubernetes) deployments.[4](https://dify.ai/?utm=theseaitools)
## By the numbers
- GitHub stars: surpassed 100,000 in June 2025 and exceeded 145,000 by mid-2026.[2](https://ai.miraheze.org/wiki/Dify.ai)
- Footprint: runs on more than 1.4 million machines across over 175 countries.[2](https://ai.miraheze.org/wiki/Dify.ai)
- Commercial customers: more than 2,000 teams and 280 enterprises on commercial versions, named by the company as Maersk, ETS, Anker Innovations, and Novartis in its March 2026 funding announcement; a secondary source adds [Panasonic](https://www.edgepedia.org/panasonic), RICOH, Deloitte, and NTT to that list.[3](https://www.businesswire.com/news/home/20260309511426/en/Dify-Raises-%2430-million-Series-Pre-A-to-Power-Enterprise-Grade-Agentic-Workflows) • [2](https://ai.miraheze.org/wiki/Dify.ai) The two lists overlap but do not match, so the full customer roster is not settled.
- Funding: $30 million Series Pre-A at a $180 million valuation, announced March 2026, led by HSG with participation from GL Ventures, Alt-Alpha Capital (described as a spin-out from [Bessemer Venture Partners](https://www.edgepedia.org/bessemer-venture-partners)), 5Y Capital, Mizuho Leaguer Investment, and NYX Ventures; total funding is approximately $41.5 million.[3](https://www.businesswire.com/news/home/20260309511426/en/Dify-Raises-%2430-million-Series-Pre-A-to-Power-Enterprise-Grade-Agentic-Workflows) • [2](https://ai.miraheze.org/wiki/Dify.ai)
## Versions, licensing and pricing
**Version milestones.** Version 1.0.0, released in February 2025, introduced a plugin system that decoupled models, tools, and agent strategies from the core codebase, along with a Dify Marketplace that launched with more than 120 plugins.[2](https://ai.miraheze.org/wiki/Dify.ai) Version 1.6.0 added two-way Model Context Protocol support, letting Dify act as both an MCP client and an MCP server.[2](https://ai.miraheze.org/wiki/Dify.ai) Version 1.9.0, released in 2026, introduced the Knowledge Pipeline and a queue-based graph execution engine.[2](https://ai.miraheze.org/wiki/Dify.ai) Version 1.8.1 added [Indonesian language](https://www.edgepedia.org/indonesian-language) support and expanded Jinja2 template variable support for LLM prompts.[8](https://github.com/langgenius/dify/releases/tag/1.8.1)
**License.** Dify's core is distributed under what the official site calls an Apache-2.0-derivative license.[4](https://dify.ai/?utm=theseaitools) The additional condition requires a commercial license for multi-tenant service deployments, which has drawn criticism from open-source purists and is described as the platform's principal competitive weakness.[2](https://ai.miraheze.org/wiki/Dify.ai)
**Pricing.** Dify Cloud's free Sandbox tier includes 1 team workspace, 1 team member, 5 apps, and 50 knowledge documents, with 200 AI credits for calling models from providers such as OpenAI, Anthropic, and Gemini.[5](https://dify.ai/dify-cloud) • [7](https://docs.dify.ai/en/quick-start) The two paid tiers are listed at $590 and $1,590 per workspace per year.[5](https://dify.ai/dify-cloud) The Enterprise edition is custom-priced and adds SSO/SAML, role-based access control, audit logs, SOC 2 Type II, and ISO 27001 compliance.[4](https://dify.ai/?utm=theseaitools)
## Reception, incidents and criticism
According to the company, Dify has grown into a widely adopted platform for agentic workflow development since launching in 2023.[3](https://www.businesswire.com/news/home/20260309511426/en/Dify-Raises-%2430-million-Series-Pre-A-to-Power-Enterprise-Grade-Agentic-Workflows) Among open-source builders, [Flowise](https://www.edgepedia.org/flowise), which is built on LangChain and exposes its components as drag-and-drop nodes, is positioned as the most accessible entry point, but it lacks Dify's enterprise features, team collaboration, and production-grade operational tooling.[2](https://ai.miraheze.org/wiki/Dify.ai) The sources provide no head-to-head comparison with LangChain, n8n, or CrewAI beyond this Flowise note.
On security, the v1.8.1 release notes record a fixed cross-site scripting (XSS) vulnerability in the block-input and support-var-input components (issue #24835), alongside fixes for critical database session binding errors, workflow publishing problems, and UUID v7 conflicts.[8](https://github.com/langgenius/dify/releases/tag/1.8.1)
The main recorded criticism concerns the license rather than the software: the multi-tenant restriction has drawn criticism from open-source purists, and the same source calls this Dify's principal competitive weakness.[2](https://ai.miraheze.org/wiki/Dify.ai)
## References
1. langgenius/dify — GitHub repository. https://github.com/langgenius/dify/
2. Dify.ai — Miraheze wiki overview. https://ai.miraheze.org/wiki/Dify.ai
3. Dify Raises $30 million Series Pre-A to Power Enterprise-Grade Agentic Workflows. Business Wire, March 2026. https://www.businesswire.com/news/home/20260309511426/en/Dify-Raises-%2430-million-Series-Pre-A-to-Power-Enterprise-Grade-Agentic-Workflows
4. Dify official site — deployment and compliance. https://dify.ai/?utm=theseaitools
5. Dify Cloud — pricing page. https://dify.ai/dify-cloud
6. Dify documentation — Build a chatbot. https://docs.dify.ai/en/cloud/use-dify/build/chatbot
7. Dify documentation — Quick start. https://docs.dify.ai/en/quick-start
8. Dify v1.8.1 release notes. https://github.com/langgenius/dify/releases/tag/1.8.1
---
*Topic: Encyclopedia › Technology and the built world › Computing and digital systems › Modern AI: foundation models, generative AI, and the AI industry › AI companies, people, and products › AI products and assistants › AI agents and developer tools*
*Initially written Sep 17, 2026 · Edited: Oct 11, 2026; Oct 15, 2026; Oct 21, 2026*
*Copyright 2026 EdgeChat AI, a subsidiary of Biostate AI.*
License: Edgepedia Community License 1.0, https://www.edgepedia.org/edgepedia/license