TypeScript SDK for different in-browser AI model providers, built to make client-side AI integration simpler and more consistent across vendors.
A lightweight recreation of OS1/Samantha from the movie Her, running locally in the browser
A Webapp that uses Retrieval Augmented Generation (RAG) and Large Language Models to interact with a PDF directly in the browser.
interactive semantic search demo using Qwen3-0.6B-Embedding in your browser
The web application for Texo, a minimalist SOTA LaTeX OCR model which contains only 20M parameters runs in browser. | 超轻量SOTA LaTeX公式识别模型，20M参数量的 web 应用仓库
A local-first Chrome extension that passively captures ChatGPT, Gemini, Claude, Grok, Perplexity conversations into a private memory graph. Features in-browser Hybrid RAG (Vector + BM25), semantic search, and 100% privacy via WebAssembly and IndexedDB. No servers, no API keys.
An MCP-enabled Qwen3 0.6B demo with adjustable thinking budget, all in your browser!
100% client-side entity-based topic clustering tool. ML models run in your browser — extract entities, resolve to Wikidata, visualize as knowledge graph.
🚀🛸 Easily boost the speed of pulling your models and datasets from various of inference runtimes. (e.g. 🤗 HuggingFace, 🐫 Ollama, vLLM, and more!)
A Chrome extension that uses PromptAPI and vector embeddings to help users quickly find answers about the current website's content.
LFM2.5 1.2 billion reasoning language model runs on web browsers using Transformers.js and ONNX Runtime Web.
Always-on companion for Claude that remembers your decisions and their evolution. Local-first memory using SQLite + transformers.js embeddings.
A browser-based platform for playing paper Magic: The Gathering remotely with friends. Spell Coven enables MTG players to play their physical cards online through video chat, card recognition, and game management tools—all running in your browser with no downloads required.
🧠 Cognitive memory system for AI coding agents — persistent semantic search, knowledge graph, Ebbinghaus forgetting, zero API cost. Works with Claude, Cursor, Antigravity.
LFM2.5 1.2 billion Japanese language model runs on web browsers using Transformers.js and ONNX Runtime Web.
Semantic search over git commit history — local embeddings, sqlite-vec, terminal UI
Browser-based audio transcription using Whisper and Transformers.js, storing results in Backblaze B2 Cloud Storage.
Browser-based AI image background removal app using Transformers.js and the RMBG-1.4 model, storing original and cutout images in Backblaze B2 Cloud Storage — no GPU or backend required.
Free client-side batch background removal powered by AI. Process up to 100 images — entirely in your browser. No uploads, no servers, no cost.
Add a description, image, and links to the transformers-js topic page so that developers can more easily learn about it.
To associate your repository with the transformers-js topic, visit your repo's landing page and select "manage topics."