Chatty is your private AI that leverages WebGPU to run extended language models (LLMs) natively and privately in your browser, giving you the most feature-rich in-browser AI experience.

Features

• In-browser privacy: All AI models run locally (client-side) on your hardware, ensuring that your data is processed only on your PC. No server-side processing!
• Offline: Once the initial download of a template has been processed, you will be able to use it without an active Internet connection.
• Chat History: Access and manage your chat history.
• Supports new open source templates: Chat with popular open source templates such as Gemma, Llama2 & 3 and Mistral!
• Responsive design: If your phone supports WebGl, you’ll be able to use Chatty just like you would on a desktop computer.
• Intuitive User Interface: Inspired by popular AI interfaces such as Gemini and ChatGPT to improve user experience similarity.
• Markdown and Code Highlighting: Posts returned as markdown will be displayed as such and posts containing code will be highlighted for easy access.
• Chat with files: Upload files (pdf and all supported non-binary files – even code files) and ask models about them – completely local! Your documents are never processed outside of your local environment, thanks to XenovaTransformerEmbeddings& MemoryVectorStore
• Custom memory support: Add custom instructions/memory to allow the AI ​​to provide better and more personalized responses.
• Export chat messages: Seamlessly generate and save your chat messages in json or markdown format.
• Voice input support: Use voice interactions to interact with models.
• Regenerate answers: not quite the answer you were hoping for? Refresh it quickly without having to rewrite your prompt.
• Light and Dark Mode: Switch between light and dark mode.