n-skills
Curated plugin marketplace for AI agents - works with Claude Code, Codex, and openskills
HYSEN LABS DIRECTORY
Curated repositories with precise taxonomy, verified metadata and practical context.
Curated plugin marketplace for AI agents - works with Claude Code, Codex, and openskills
Homebrew is the standard package manager on macOS. brew-browser gives it a real native GUI.
🖥️ 📱 ▶️ Wrap your iPhone screen recordings in a beautiful device frame, add cinematic zoom moments, and export ready-to-share videos.
An embedded development environment for mcs51/stm8/avr/cortex-m/riscv on VsCode.
From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.
在 Mac(Apple Silicon / Intel)上用 UTM 跑 Linux 虚拟机,把大疆 4G 模块(EG25-G)伪装成移远 Quectel EC25 并部署 vohive 平台的完整步骤
A local-first browser 3D design editor for building, cutting, importing STL files, and exporting models.
从 NLP 到 LLM 的算法全栈教程,在线阅读地址:https://datawhalechina.github.io/base-llm/
[support ollama/other model]【兼容ollama和其他模型】将任何具有OpenAI API调用方法的模型集成到PotPlayer中。它使你在观看视频时能够实时翻译字幕,从而打破语言障碍,提升你的观看体验。 This real-time subtitle translation plugin integrates OpenAI's ChatGPT API (or any model with the same API calling method) into PotPlayer. It enables you to translate subtitles on-the-fly while watching videos.
The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.
TypeScript AI AI Function Calling Framework enhanced by compiler skills.
Project brief: Emails at the heart of your business logic. Create your *own personal solution* for emails treatment by assembling the components you need thanks to the Inversion of Control mail platform offered and go further customizing filtering and routing rules using *James Mailet Container*.
ChatGPT Pro 国内怎么开通?2026年 Pro 5x(100 美元)/ 20x(200 美元)、支付宝、无海外卡、Codex 与订单查询指南
A version of verl to support diverse tool use [TMLR 2026]
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
Extensible, Efficient Quantum Algorithm Design for Humans.
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.
Gesture recognition via CNN. Implemented in Keras + Tensorflow/Theano + OpenCV
📖 Paper reading list in conversational AI.