Stars
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
React’s programming model, compiled. The successor to Inferno, carrying its performance-first goal forward:
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.
Free, private, on-device dictation for Mac, powered by Apple's SpeechAnalyzer and Foundation Models.
Open source alternative to Semrush and Ahrefs
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
The open-source app everyone uses to manage agents at work
A skill that turn any brand into a scrollable 3D world landing page
A Codex skill that finds evidence-backed potential first customers from recent public signals.
The design language that makes your AI harness better at design.
Use your most capable model to audit your codebase and write plans for cheaper models to execute.
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
An open-source framework for making universal native apps with React. Expo runs on Android, iOS, and the web.
vean — the agent-native video editing core: a typed document, edit algebra, and diagnostics layer (a 'language server for video') on top of MLT. AGPL-3.0.
Use Codex from Claude Code to review code or delegate tasks.
cut Claude Code token usage by rendering text context as images
Production-grade engineering skills for AI coding agents.
A simple Tailwind plugin to create borders via CSS classnames that have gradients.
Your agent writes bad React. This catches it
A Swiss International Style design system skill for AI agents
A structured self-interrogation framework that exhaustively explores a topic through 100 sequential questions, each building on the previous answer.