Zero shot pdf OCR with gpt-4o-mini

Automate browser-based workflows with LLMs and Computer Vision

VNC client web application

Modern, scalable tools. Exceptional developer experience.

Native UI testing / controlling with node

macOS CLI tool for emulating mouse and keyboard events

fake keyboard/mouse input, window management, and more

🪄 Create rich visualizations with AI

A utility for converting pdf to image and base64 format.

The open-source browser made for headless usage

On-device Speech Recognition for Apple Silicon

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

A tiny (286 bytes) state manager for React/RN/Preact/Vue/Svelte with many atomic tree-shakable stores

Vision model based document ingestion

🚀 The easiest, free and open-source Tailwind CSS component library with semantic classes.

open source 24/7 screen & voice recording for the age of superintelligence

Create guided tours in your apps

A modular geospatial engine written in JavaScript and TypeScript

An isomorphic Javascript library for Supabase Auth.

Semantic Image Search CLI tool.

A lightweight React Hook intended mainly for AI chat applications, for smoothly sticking to bottom of messages

Novel implementation of a Trie data structure optimized for small, sparse maps

Endo is a distributed secure JavaScript sandbox, based on SES

🧡 Next generation information browser.

Collection of popular LLM icons for building AI apps

Creates a complete full text historical archive for an RSS or ATOM feed.

Key/value storage for JavaScript File objects

A request.formData() wrapper with pluggable file upload handling