Lists (2)
Stars
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.
唯音輸入法 macOS 版，恐怕是截至目前為止在功能多樣性方面最強的第三方免費 macOS 系統專用輸入法，採純 Swift 語言寫就，同時支援拼音與注音打字。唯音的著力點是盡可能在力所能及的範圍內將整個產品的功能做得更好用，搭配特製的簡體中文與繁體中文專用辭庫。更具諸多唯音特色功能。目前研發管理工作均在 Gitee 進行。
Share coding agents with your team on phone and desktop
The agentic CLI for the entire Cloudflare API
chroot, mount --bind, and binfmt_misc without privilege/setup for Linux
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
Local-first voice input for macOS and Windows. On-device speech recognition, offline dictation, and local polishing.
MCP server for Taiwan Stock Exchange (TWSE) open data — stock quotes, ETFs, 140+ public datasets ｜ 台股資料小幫手：讓 AI 查證交所公開資料
A Claude skill that turns vibecoded, AI-looking UI into a designed interface
Towards a More Autonomous Agent System
Self-host the relay for Alma Remote Access — control your desktop Alma from your phone, anywhere. Docker or Cloudflare Workers.
dsh-go — DeepSeek Harness 装进口袋：手机本机运 976C 行，也能遥控你的电脑。
JavaScript in-page GUI agent. Control web interfaces with natural language.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
A calm, quick browser for macOS, with an agent that works in your tabs.
The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.
badlogic / qwen3_tts_rs
Forked from second-state/qwen3_tts_rsA Rust implementation of the Qwen3 Text-to-Speech (TTS) model inference.
A terminal on GPUI and Ely components
A growing collection of viral videos made with Claude Opus 5.5 and the prompts behind them. Watch each original next to a live remake on Skillry. Updated regularly.
Minecraft: Java Edition 26.3 rewritten from scratch in Rust, checked against vanilla with 281 differential harnesses. Get it with the Horizon launcher.
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput