Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

GitHub - addyosmani/chatty: ChattyUI - your private AI chat for running LLMs in the browser

Jun 09, 2024 - github.com
Chatty is a private AI that uses WebGPU to run large language models (LLMs) in your browser, offering a feature-rich AI experience. It ensures in-browser privacy as all AI models run locally on your hardware, and it works offline once the initial model download is complete. Other features include chat history management, support for new open-source models, responsive design, intuitive UI, markdown and code highlight, chat with files, custom memory support, export chat messages, voice input support, response regeneration, and light & dark mode.

The project aims to bring the functionality of popular AI interfaces like ChatGPT and Gemini into an in-browser experience. It is supported by default in Chrome and Edge, and can be enabled in Firefox. The application is built using the WebLLM project, HuggingFace, open source LLMs, and LangChain, and is created and maintained by Addy Osmani & Jakob Hoeg Mørk. It requires a GPU with enough memory to run the models efficiently. Contributions to the project are welcome.

Key takeaways:

  • Chatty is a private AI that uses WebGPU to run large language models (LLMs) natively and privately in your browser, offering a feature-rich in-browser AI experience.
  • All AI models run locally on your hardware, ensuring data privacy. Once the initial download of a model is processed, it can be used without an active internet connection.
  • Chatty supports new open-source models, has a responsive design, intuitive UI, markdown & code highlight, chat with files, custom memory support, export chat messages, voice input support, regenerate responses, and light & dark mode.
  • The project aims to bring the familiarity and functionality from popular AI interfaces such as ChatGPT and Gemini into an in-browser experience.
View Full Article

Comments (0)

Be the first to comment!