Together AI’s LlamaCoder Generates Apps from a Simple Prompt

With the launch of Llama 3.1 405B, Together AI introduced LlamaCoder, an open-source web application capable of generating complete apps from a single prompt. The tool has quickly gained popularity among developers, with its GitHub repository receiving over 2,000 stars and being cloned hundreds of times in just one month.

Empowering Developers with Open Source AI

Together AI, a leader in AI acceleration cloud technology, enables developers and businesses to design, develop, and manage the entire lifecycle of generative AI applications using open-source models like Llama. To showcase the capabilities of Llama 3.1 405B, the company created LlamaCoder, a web app that allows users to generate functional applications by simply providing a text prompt.

Since its release, LlamaCoder has become a viral sensation. In just over a month, the app has generated more than 200,000 applications. “Developers are loving it,” says Hassan El Mghari, a software engineer at Together AI. “It was incredible to see people generating quiz apps, pomodoro timers, budgeting apps, and more and making it their own—simply with prompting. It really shows the power of Llama 3.1 405B.”

Breaking New Ground in AI Development

Llama 3.1 405B stands out as the first open-source model capable of excelling in coding-specific applications. Together AI has also developed additional apps using Llama 3.1, such as LlamaTutor, which helps users learn new subjects, and TurboSeek, an AI-powered search engine. Llama models have set new benchmarks for open-source large language models (LLMs), competing with closed-source models while incorporating safety features for responsible development. These capabilities are driving rapid adoption among developers and enterprises.

A Platform for Diverse Use Cases

Over 150,000 developers and companies rely on the Together platform for various applications, including gaming, customer support, benchmarking, and summarization. The platform’s flexibility allows users to maintain ownership of their customized models and easily download them for different use cases.

El Mghari explains that the Together Inference Engine is designed to bring innovations from research to production quickly. It incorporates advancements such as FlashAttention-3 kernels, RedPajama-based speculators, and cutting-edge quantization techniques, enabling developers to build and deploy generative AI applications on Llama 3.1 models with high performance and cost efficiency.

The Power of Open Source

According to El Mghari, many companies have transitioned from closed-source providers to Together AI, drawn by the benefits of open-source models. “Open source AI has been a game changer for the AI community,” he says. “It is in the best interest of all developers and will lead to the fastest advancement and innovation. And beyond all of that, it enables organizations to truly own their data, their models, and have that full flexibility instead of getting locked in.”

The rise of open-source AI like LlamaCoder demonstrates the potential for collaborative innovation in the tech community. As more developers and companies adopt these tools, the future of AI development looks promising, with opportunities for faster, more flexible, and more transparent advancements.