AI 开源项目榜。

A curated list of awesome AGI frameworks, software and resources

[NeurIPS 2021] LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

[ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control

On-device Neural Engine

Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

Llama from scratch, or How to implement a paper without crying

Search over large image datasets with natural language and computer vision

Cli allows AST search, ~40-50% economy tokens. Claude/Codex/Cursor searches (suitable for any AI agent that can use Bash)

CLI for running large numbers of coding agents in parallel with git worktrees

PyTorch implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation.

This is a Torch implementation of ["Deep Residual Learning for Image Recognition",Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun](http://arxiv.org/abs/1512.03385) the winners of the 2015 ILSVRC and COCO challenges.

A peer-to-peer database that spans devices. For apps and agents that work everywhere.

PmHub，一个基于 SpringCloud & LLM 的智能项目管理系统，该项目旨在帮助小伙伴们快速掌握微服务/分布式项目的架构设计和开发流程。如果你想在校招或者社招中拿到一个满意的 offer，PmHub 将是一个非常 nice 的选择😄。

AI-powered ab initio biomolecular dynamics simulation

Medical Imaging Deep Learning library to train and deploy 3D segmentation models on Azure Machine Learning

Modified version of Chatterbox that accepts text files as input and no character restrictions. I use it to make audiobooks, especially for my kids.

Code and information for face image quality assessment with SER-FIQ

A Convolutional Neural Network Accelerator implementation on FPGA, xilinx （xczu7ev-ffvc1156-2-i）, The inference of yolov8 took 60ms.

Swift Concurrency agent skill for Claude Code, Codex, and other AI tools.

Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding

ComfyUI wrapper for segment anything 3

Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021

C3D is a modified version of BVLC tensorflow to support 3D ConvNets.

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.

A Pytorch Implementation of "Attention is All You Need" and "Weighted Transformer Network for Machine Translation"

TOROS N2 - lightweight approximate Nearest Neighbor library which runs fast even with large datasets

Run any agent on any model, models stored as OCI images