sauravpanda/BrowserAI
Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser
Leverages WebGPU acceleration and dual engine support (MLC and Transformers.js) for near-native inference performance, with pre-optimized quantized models enabling offline-capable deployment. Provides a unified SDK for text generation, speech recognition (Whisper), text-to-speech (Kokoro), structured JSON output, and conversation management via Web Workers for non-blocking UI interactions.
1,381 stars. Actively maintained with 44 commits in the last 30 days.
Stars
1,381
Forks
137
Language
TypeScript
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
44
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sauravpanda/BrowserAI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
cel-ai/celai
Open source framework designed to accelerate the development of omnichannel AI virtual assistants.
lone-cloud/gerbil
A desktop app for running Large Language Models locally.
cztomsik/ava
All-in-one desktop app for running LLMs locally.
vinjn/llm-metahuman
An open solution for AI-powered photorealistic digital humans.
snwfdhmp/llm
Use any LLM from the command line.