BrowserAI allows users to run local LLMs like llama, deepseek-distill, kokoro and more directly in their browser, providing a simple, fast, and private experience without the need for server infrastructure.
Features
Run AI models in browser
Run AI models directly in the browser without requiring any server infrastructure, providing privacy and efficiency.
WebGPU acceleration
Utilizes WebGPU for acceleration, providing near-native performance for AI model inference.
Offline capable
Once downloaded, the app works without internet connectivity, enabling offline AI processing.
Developer-friendly API
Offers an easy-to-use SDK that supports multiple engines, making it accessible for developers building AI-powered applications.
Speech recognition and Text-to-speech
Includes built-in capabilities for both speech recognition and text-to-speech, enhancing interaction options for users.
Built-in database support
Allows for storing conversations and embeddings directly within the browser context, enabling seamless data management.