Repo đang lênCập nhật hằng ngày từ GitHub

Hardware accelerated, batchable and differentiable optimizers in JAX.

Official PyTorch implementation of Superpoint Transformer [ICCV'23], SuperCluster [3DV'24 Oral], and EZ-SP [ICRA'26]

🐝 The First Self-Improving agents with RL / Prompting Optimization

ComfyUI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

Deep learning toolkit-enabled VLSI placement

Real-time pose estimation accelerated with NVIDIA TensorRT

Efficient Multi-Scale 3D Convolutional Neural Network for Segmentation of 3D Medical Scans

An All-MLP solution for Vision, from Google AI

Stable Diffusion in NCNN with c++, supported txt2img and img2img

Face Editor for Stable Diffusion

Agentic coding in your terminal,Simultaneously compatible with OpenAI, Gemini, and Claude.运行在终端的 AI 编程智能体，同时兼容 Deepseek、OpenAI、Gemini和Claude。

Essential Guide to keep up with AI/ML/DL/CV

AI-native, cloud-native file system in Rust. Full POSIX on object storage with a multi-tier distributed cache, for AI training, inference, and agents. CNCF Sandbox project.

Search + Chat = SearChat(AI Chat with Search), Support OpenAI/Anthropic/VertexAI/Gemini, DeepResearch, SearXNG, Docker. AI对话式搜索引擎，支持DeepResearch, 支持OpenAI/Anthropic/VertexAI/Gemini接口、聚合搜索引擎SearXNG，支持Docker一键部署。

Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)

[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

eBPF-based Cloud Native Monitoring Tool

Predict Cryptocurrency Price with Deep Learning

Experts.js is the easiest way to create and deploy OpenAI's Assistants and link them together as Tools to create advanced Multi AI Agent Systems with expanded memory and attention to detail.

[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

Mastering Atari with Discrete World Models

OpenMMLab optical flow toolbox and benchmark

UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

This project is a plugin that supports ChatGPT running on JetBrains series IDE.

Caffe implementation of multiple popular object detection frameworks

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

Build agents which are controlled by LLMs

Prometheus rule linter/validator

Next RecSys Library

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).

A Modular Optimization framework for Localization and mApping (MOLA)

The Fastest Deep Reinforcement Learning Library

Closed-form Continuous-time Neural Networks

Implementations of CNNs, RNNs, GANs, etc

Layers Outputs and Gradients in Keras. Made easy.

⌘⌘ - A lightweight, native macOS screenshot tool that lives in your menu bar. Double-tap ⌘ Command to capture any region of your screen — instantly copied to clipboard, or annotate first with pen and mosaic tools.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Code and other material for the book "Deep Learning and the Game of Go"

Introduction to PyTorch, covering tensor initialization, operations, indexing, and reshaping.

1st Place Solution for Zhihu Machine Learning Challenge . Implementation of various text-classification models.(知乎看山杯第一名解决方案)

Open-source alternative to Claude Agent SDK, ChatGPT Agents, and Manus.

🔥 On-Policy Self-Distillation in Diffusion Models

A version of verl to support diverse tool use [TMLR 2026]

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

PyTorch implementation of UNet++ (Nested U-Net).

Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation

A pytorch quantization backend for optimum

A family of lightweight multimodal models.