Starred repositories
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Production-grade client-side tracing, profiling, and analysis for complex software systems.
OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful re…
The simplest, fastest repository for training/finetuning small-sized VLMs.
A straightforward method for training your LLM, from downloading data to generating text.
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
Agent Skills for Google products and technologies
💫 Toolkit to help you get started with Spec-Driven Development
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A fast, helpful, and open-source document parser
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Production-grade engineering skills for AI coding agents.
[CVPR 2026] Official implementation of Fourier Angle Alignment for Oriented Object Detection in Remote Sensing
Add a virtual speaker and mic to your windows 10/11 device! Works with VR, OBS, Sunshine, and/or any desktop sharing software.
The API to search, scrape, and interact with the web at scale. 🔥
X-monitor 是一个基于 Twitter (X) 的实时监控系统，能够自动基于大模型分析推文内容、识别潜在MEME加密货币交易机会，并支持自动执行链上交易。X-monitor is a real-time monitoring system based on Twitter (X) that automatically analyzes tweet content using larg…
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
Fast and accurate AI powered file content types detection
[CVPR 2022]"CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings", Zhiwen Fan, Tianlong Chen, Peihao Wang, Zhangyang Wang
Symbol as Points: Panoptic Symbol Spotting via Point-based Representation. ICLR 2024
Source Code of NeurIPS21 and T-PAMI24 paper: Recognizing Vector Graphics without Rasterization
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.