You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed arti
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|
Submission declined on 13 March 2026 by Pythoncoder (talk). This draft appears to contain text generated by a large language model (such as ChatGPT). You cannot use LLMs to generate article content.
Declined by Pythoncoder 4 months ago.LLM-generated pages with certain obvious signs of being machine generated may be deleted without notice. Instead, only summarize in your own words a range of independent, reliable, published sources that discuss the subject. See the advice page on large language models for more information. |
| Dify | |
|---|---|
| File:Dify Logo.png | |
| Developers | LangGenius, Inc. |
| Release | March 2023 |
| Written in | Python, TypeScript |
| Platform | Web, cloud computing, self-hosted |
| Type | AI application development platform |
| Website | https://dify.ai |
Dify is an open-source platform for building and operating applications based on large language models (LLMs). It is developed by LangGenius, Inc., headquartered in Menlo Park, California, and was first released in March 2023. The software is written in Python and TypeScript, and runs either as a managed cloud service or as a self-hosted installation.
By early 2026, the platform had been deployed on more than 1.4 million machines across more than 175 countries. Enterprise customers at that time included Maersk, Novartis, Deloitte, ETS, and Anker Innovations.[1]
Dify centers on a visual workflow editor where developers connect modular nodes — covering LLM calls, document retrieval, conditional branching, and HTTP requests — to compose multi-step AI pipelines. Finished applications can run as standalone chat interfaces or serve as API endpoints consumed by other systems.[1]
The platform includes a built-in retrieval-augmented generation (RAG) pipeline for connecting applications to custom knowledge bases, and supports large language models from multiple providers — among them OpenAI, Anthropic, and locally hosted models served through Ollama. Model credentials and routing are configured from a shared settings panel rather than hard-coded into individual workflows.[2]
The self-hosted Community Edition is distributed under a custom license based on the Apache License 2.0, with additional restrictions on multi-tenant commercial redistribution. A separate enterprise edition is available with additional features and dedicated support.
LangGenius, Inc. was founded in early 2023, and Dify launched in March of that year. Its source code was published on GitHub under the project's open-source license in the same period.
The platform grew substantially during 2024. TechCrunch, in a March 2025 article ranking open-source startups by GitHub star growth, placed LangGenius third overall, reporting that the Dify repository had grown 326 percent over the course of 2024 — from roughly 13,000 stars to nearly 57,000 — and had since climbed past 84,000.[3] In April 2024, LangGenius released an AI Workflow feature — available in both the cloud and self-hosted editions — adding visual support for multi-step automation pipelines.
LangGenius released version 1.0.0 of Dify in 2025. That year the company opened a Japanese subsidiary, LangGenius K.K., in Tokyo. Enterprise adoption in Japan accelerated through a series of commercial partnerships: in October 2025, ITOCHU Techno-Solutions Corporation (CTC) announced it would resell Dify Enterprise to its clients, setting a target of ¥3 billion in related sales over three years;[4] NTT DATA Corporation and Japan Information Processing Company (JIP) chose Dify Enterprise as the technical foundation for a jointly developed SaaS AI agent service.[5] Japanese technology publications reported on these developments and the broader growth of Dify within enterprise AI projects.[6][7]
In March 2026, LangGenius raised $30 million in a Series Pre-A round at a post-money valuation of $180 million. The round was led by HSG, with participation from GL Ventures, Alt-Alpha Capital (a Bessemer Venture Partners spin-out), 5Y Capital, Mizuho Leaguer Investment, and NYX Ventures.[8][2]
Category:Free and open-source software Category:Artificial intelligence software Category:Cloud computing Category:Software as a service
Informasi ini disarikan dari Wikipedia dan disajikan kembali untuk tujuan edukasi. Konten tersedia di bawah lisensi CC BY-SA 3.0. Kami tidak bertanggung jawab atas ketidakakuratan data yang bersumber dari kontribusi publik tersebut.
- provide significant coverage: discuss the subject in detail, excluding routine coverage like product launches, staff appointments, or financial reports and listings in databases or listicles;
- are reliable: from reputable outlets with editorial oversight;
- are independent: not connected to the subject, such as press releases, the subject's own website, or sponsored content.
Please add references that meet all three of these criteria. If none exist, the subject is not yet suitable for Wikipedia.