Havuz

Emboss — precision PDF generation for Python. Declarative specs, Knuth-Plass typography, PDF/UA tagging, deterministic output.

🔢 Live-formatting React number input — headless, i18n-first (Persian ۱۲۳, Arabic ١٢٣…), WAI-ARIA spinbutton, ~2.2 KB core

Drive a GNOME Wayland desktop from AI agents. CLI-first, no portals, no consent dialogs.

Open-source dotted maps and animated 3D globes for designers. 21 looks, PNG, SVG, GLB, WebM, MP4 and GIF export, embeds, a React component,

Material Design 3 component library on web standards — 56+ components for React, Angular, Vue, Svelte, or plain HTML. WCAG 2.1 AA, SSR, them

Cross-platform Rust computer-use MCP server for macOS and Windows: AX/UIA, screenshots, OCR, pointer and keyboard input, clipboard, stdio, a

Open-source AI agent testing framework for browser and native desktop apps, with explicit tool effects, evidence, lifecycle, and trace contr

Accessible, source-owned flag components for shadcn/ui.

Bionic reading for Claude Code: bolds the leading part of each word in Claude's streamed replies so your eyes move faster. Zero dependencies

♻️ Site educativo mobile-first, acessado por QR Code na lixeira de compostagem da UCB, que orienta o descarte correto de resíduos orgânicos.

A calm, visual recipe finder with search, favorites, meal planning, pantry inventory, shopping lists, and price estimates.

Private, offline library and player for your own adult collection. Rust, egui, GStreamer, SQLite. No account, no telemetry. Linux, 18+.

A streaming action language for computer-use agents. LLMs emit one JSON action per line; the executor runs each the moment its newline arriv

PlopUI: hand-drawn React UI kit, imperfect on purpose. Wobbly stickers, washi tape and a hand-lettered font, accessible to WCAG AA.

A Liquid Glass voice speed-dial for your AI agents — call, mute, hang up and switch between ChatGPT dot, Grok Bot, Copilot, Devin and more.

suiss/ui: copy-paste components, patterns, interactions, charts and blocks with a clean, minimal design for React (Next.js, Vite), React Nat

🌍 Real-time, offline screen translator for games & videos — OCR + NLLB-200 + subtitle overlay + neural voice dubbing that matches the speake

A Claude Code skill that catches commonly-forgotten UX/product details before you ship a screen or feature.

On-device live captions for Linux — for deaf and hard-of-hearing users. Flatpak, offline, low latency.

Reverse-engineering & re-implementation of OpenAI Computer Use macOS plugin for DeepSeek Harness: 10 MCP tools, JSON-RPC wire protocol, nati

Practical guidance for AuDHD-friendly interfaces that are easier to understand, use, pause, resume and correct for users and developers who

🧱 A composable input for AI apps in React.

A free, fully local, minimal-setup voice dictation app for macOS - built specifically for developers.

Agent skill for web typography: Bringhurst applied to modern CSS, with claims measured in the browser and a baseline eval suite

A local-first cognitive substrate for neurodivergent professionals. Gives Claude memory, a sense of time, a translator for corporate ambigui

Let an AI see and operate Windows apps cheaply, without stealing focus or moving your mouse. MCP server for Claude Code.

macOS menu bar app that translates selected text in place with a hotkey: up to three language pairs with automatic direction, your writing s

Accessible Angular 22 UI library (standalone, signals, zoneless, SSR) ported from BlatUI — 155 components, 16 blocks, 70 charts, 34 template

ThorOS - a voice-controlled, AI-first Linux distribution built on Debian 13. Say what you want; on-device AI plans it and permissioned agent

划词即理解的 AI 阅读工具 — Select text anywhere on macOS or windows system and get instant AI translate / explain / summarize in a floating bar. Tauri

Agent-native creative progress bar toolkit with Gallery, CLI, Skill, and MCP integration.

BALDR-accessibility-scan est un outil d'audit d'accessibilité numérique conçu pour évaluer la conformité des sites web aux référentiels RGAA

MCP server for production-grade UI and brand design — 37 tools: anti-slop quality gates, OKLCH tokens with auto dark mode, WCAG 2.1 audits,

You're a developer, not a server. A macOS menu bar app that works out what you're doing and interrupts at a defensible moment instead of on

Give your app's status a face: six tiny animated characters in one <tiny-tell> element.

The guidelines for building UI components with a perfect user experience, developer experience and agentic experience.

jev-chat 对话副驾的派生版：判断、排序和候选回复由同一个模型在同一次调用里给出，所以只需配一把 key。Windows / macOS / Android 三份，其余代码与原版相同。

🧠 The UI's brain in a state machine. Write once, run it on any JS runtime.

Elegant, themeable, accessible components for SolidJS.

The definitive collection of cross-platform Agent Skills. Compatible with Claude Code, Codex, Cursor, OpenClaw, Gemini CLI, Copilot, Hermes.

Notification banners on the display you're actually looking at — follows your mouse or active window

Open-source neural-voice audiobook player for Android. Reads any text — Royal Road, GitHub, RSS, EPUB, Wikipedia & 20+ more sources — aloud

What a PDF says out loud. The PDF accessibility checker that runs anywhere: PDF/UA-1 + WCAG 2.2 in your terminal, CI and browser, plus the s

See and drive a GPUI app from the command line or MCP: snapshots with refs, clicks, typing, waits, screenshots and recordings

Aster describes what a lecture video shows but never says, so blind and low-vision students can follow it

Python-scriptable keyboard customization for Windows and macOS: remap keys, bind them to Python, drive apps and windows. An AI assistant can

Open-source Android utility for background playback and system control, supporting Accessibility, Shizuku, Dhizuku, Root, LSPosed, and LSPat

Chrome extension that turns video subtitles and tab audio into real-time 3D Chinese Sign Language with local Whisper.

Agent Skill + Playwright/axe-core verification loop that teaches AI coding agents to build accessible frontends on the first pass. Companion

Native macOS push-to-talk dictation app — hold key, speak, release to transcribe and paste text via ChatGPT Web or Groq API; no API key requ