你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

Pure-Go GPU/NPU compute wrapper for Intel NEO driver Level Zero APIs.

Simple x86-64 VT-x Hypervisor with EPT Hooking

A lightweight 2D render engine for Go, ported from Rust's tiny-skia.

A Wasm to Go translator

A new bootable USB solution.

Official implementation of "EndoCoT". Scaling endogenous Chain-of-Thought (CoT) reasoning in diffusion models for complex structured generation.

oneAPI Level Zero Specification Headers and Loader

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

DiffSinger community vocoders release page

The easiest, most secure way to use WireGuard and 2FA.

Run LLMs with MLX

SGLang is a high-performance serving framework for large language models and multimodal models.

A tool for download asmr media from asmr.one(Thanks for the asmr.one)

⚡ Dynamically generated stats for your github readmes

一个强大的网易云、QQ、酷狗、Bilibili、汽水等音乐聚合搜索与下载核心库 (Go 语言实现)

一个基于 Go 语言的全网音乐搜索与下载工具。支持 CLI 命令行与 Web 服务双模式，内置网易云、QQ、酷狗、Bilibili、汽水音乐等 10+ 个主流平台，支持多源并发搜索与无损音质解析。music-dl交流群：1074285005

A web-based model directory that parses and visualizes the intricate anatomy of Transformer-based architectures.

Read AVI streams, extract inner packets for decoding. Pure C implementation, zero malloc()/free() calls, designed for embedded systems (e.g. STM32).

A completely vibecoded operating system targeting Aarch64

C bindings for the OpenAI API

Wan: Open and Advanced Large-Scale Video Generative Models

《美国反对美国》是王沪宁先生在上世纪80年代末赴美观察写作的。我们知道在那个年代中国对西方特别是美国的追捧有多高，所以突然看到一个学者在80年代就有如此清楚的认识，十分钦佩。由于网上只有效果很差的PDF扫描版，所以我想利用OCR技术和肉眼（人体OCR）来转成现代化的文本格式。目前已经全部完成。

go test output for humans

隶体计划・曺全碑

基于图像识别的自动化黑盒测试框架 | An automation black-box testing framework based on image recognition

"rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files

Android Automation Tool Based on Vision-Language Models

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory