AI 开源项目榜。
Autonomous LLM Trading Asterism — a research-only multi-agent trading platform with evidence-first research, an auditable console, Shadow simulation and explicitly authorized broker execution.
GigaTrain: An Efficient and Scalable Training Framework for AI Models
面向数学建模竞赛的 Claude Code / Codex Skills ，支持分阶段建模流程与 Python、MATLAB/北太天元代码分支。
(CVPR 2021 Oral) Open World Object Detection
[TPAMI 2023] LibFewShot: A Comprehensive Library for Few-shot Learning.
Dynamiq is an orchestration framework for agentic AI and LLM applications
A set of Python classes that transport OpenCV images from one computer to another using PyZMQ messaging.
Nightshift uses your leftover Claude / Codex budget to surprise you with useful PRs. Love them or leave them.
Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"
OpenClaw Security Vault — Atomic "claw" control: every AI reach, within your sight.
Unified interface for AI chat, Agentic workflows and more ...
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
AI-powered social media agent with real browser automation
HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training
[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
A list of projects that were or will be featured in Weekly Robotics newsletter
Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
Local Responses-API shim that exposes Factory BYOK models (and optional ChatGPT GPT-5.5 passthrough) to Codex Desktop.
Agents-ufy-Core
[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.
Real-time pose estimation accelerated with NVIDIA TensorRT
AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.
A benchmark to evaluate language models on questions I've previously asked them to solve.
Attempting to make the Deep Learning Book easier to understand.
The PyTorch implementation of LightGCN
Autonomous mobile robots (2WD, 4WD, Mecanum Drive)
DepthAI
机器学习笔记
ComfyUI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.
Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/