AI 开源项目榜。
ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.
📚 AIGC 求职面经、必备基础知识、提示词工程、ChatGPT、Stable Diffusion、Prompt、Embedding、Fintune 等 AIGC 求职你所需要知道的一切~
Research papers with annotations, illustrations and explanations
Efficient Part-level 3D Object Generation via Dual Volume Packing
rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale
A pytorch implementation for paper 'Exploring Simple Siamese Representation Learning'
AI-powered Resume Analyzer built with React & Puter.js. Includes seamless auth, upload and store resumes, and match candidates to jobs using smart AI evaluations. All wrapped in a clean, reusable UI.
The AI Org-OS — a collaborative platform for humans and agents. Explore: https://spaces.xyne.ai
Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch
Deep learning with spiking neural networks (SNNs) in PyTorch.
Light-GPT is an interactive website project based on the GPT-3.5-Turbo Model.
Gemini API 代理, 把Gemini API免费中转到国内。还可以聚合多个Gemini API Key，随机选取API Key的使用实现负载均衡，使得Gemini API免费成倍增加。
🦄 The world's most complete open-source Midjourney API — Discord, YouChuan and the official site behind one HTTP interface, 1M+ images per day.
The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.
A flexible Federated Learning Framework based on PyTorch, simplifying your Federated Learning research.
Real-World Super-Resolution via Kernel Estimation and Noise Injection
[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
"End-To-End Memory Networks" in Tensorflow
Chapyter: ChatGPT Code Interpreter in Jupyter Notebooks
The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)
本地监控 + AI 视觉 — LAN-based smartphone-powered AI monitoring framework with structured event output for data acquisition and analysis.
If tinygrad wasn't small enough for you...
A better /goal for Codex and Claude Code
A minimalistic MCP client with a good feature set.
Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex
A very simple CNN project to recognize gestures made in American Sign Language
Unofficial implementation of YOLO-World + EfficientSAM for ComfyUI
A high-fidelity 3D face reconstruction library from monocular RGB image(s)
♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️
This repository offers various extension nodes for ComfyUI. Nodes here have different characteristics compared to those in the ComfyUI Impact Pack. The Impact Pack has become too large now...