Want smart insight into your inbox? Enterprise AI, only what matters to data and security leaders, sign up for our weekly newspapers. Subscribe now
AnycoderOne Open-SOS web app development environment Facial ML Development Lead was developed by embracing the lead Ahsen Khalik ,@_ On X on X), Has launched the face space on hugging.
Equipment is now available AI code sharing repository for all users of Hugging FaceLive preview, multimodal input, and one-click integrates purinogen-within a host environment, allow Indi creators without much more technical expertise, or uses a fast facial AI model to start “vib coding”, without much more technical expertise.
It also acts as an alternative to services LavableWhich allows users to type in plain English and start coding apps without formal programming knowledge.
Free vibe coding is available to all, powered by km K2
Khalik built ancoder as “one of the first vibe coding apps” as “one of the first vibe coding apps” to support 2 models of small and skilled km yet.
The main functionality of Anycoder allows users to enter a plain details to generate HTML, CSS and JavaScript. They are displayed in a live preview pane and can be edited or directly deployed. It also contains examples templates for Todo apps, dashboard, calculator, and more.
Using the open-source python development environment gradio of the Hugging Face, Anycoder allows users to describe applications in plain English or upload images and generate immediate working codes.
Khaliq made the anicouder as an individual project within the Hugging Face Ecosystem.
In a direct message conversation with this venturebeat journalist, he described it as a “Free Open Source Vibi Coding App”.
However, he also said that many open sources are supported and users can switch between them with the dropdown menu on the left fruit control sidebar, including:
- Moonshot km-k2
- Deepsek V3
- Deepsek R1
- Baidu’s Ernie-4.5-Vl
- Minimax M1
- Alibaba’s Qwen3-235B-A2222b
- Smollm3-3B
- GLM-4.1V-9B-Thinking
UI images, web search integration and code from OCR support
Using ERNIE-4.5-Vl model, Anycoder supports multimodal generation. Users can upload UI design screenshots or mockups and generate functional fronts codes from them – it can make it useful for designers or teams.
Anycoder involves a website Redesign Tool that removes the material from any public site and re -presents it with a more modern layout. It uses scraped content such as page structure, meta information and images to create a new version, optionally directed by user instructions such as “Make It Minimalist” or “Add Dark Mode”.
To support the up-to-date design trends and implementation patterns, the web discovery provides integration via Anycoder Tavily. When enabled with the API key, the platform searches for current technologies and best practices before generating code.
Users can upload images with embedded texts – such as screenshots or handwritten notes – and the anicoder removes that material using Tesseract OCR. The extracted text can then be included in the code prompt or app content.
One-clici percency to embrace face space
Anycoder allows immediate deployment of apps generated to embrace facial spaces. After certifying through oauth and giving the necessary permissions, users can deploy apps under their own hugged face account namespace. Deployment includes:
- Mobile friendly, responsible design
- Branded header/foot and readme
- Live, shared url
- Complete ownership and edit
This purposeless capacity now involves support for full python apps manufactured with gradio, which expands matters of using equipment beyond static sites. Support for streamlight is also subject to development.
For novice developers or even technical expertise people who want to increase a new project rapidly, seem like a great and compelling place to start ancoder.
