AI 开源项目榜。
Generative UI examples for: AG-UI, A2UI/Open-JSON-UI, and MCP Apps.
Run LLMs inside a PDF file.
A Scientific Multimodal Foundation Model
A user-friendly toolkit for voice recgonition/transcription/conversion etc. | 简单易用的语音工具箱
書籍「つくりながら学ぶ! PyTorchによる発展ディープラーニング」の実装コードを配置したリポジトリです
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)
A collection of comprehensive notes on Deep Reinforcement Learning, customized for UC Berkeley's CS 285 (prev. CS 294-112)
Trading bot with support for realtime trading, backtesting, custom strategies and much more.
Code for "FlashWorld: High-quality 3D Scene Generation within Seconds" (ICLR 2026 Oral)
AI projects
A medical imaging framework for Pytorch
Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779
Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.
OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.
SGPT: GPT Sentence Embeddings for Semantic Search
PyTorch DDPM implementation
The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.
Notes for the Reinforcement Learning course by David Silver along with implementation of various algorithms.
Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.
Local-first, zero-trust agentic IDE for verifiable autonomous software development.
This repository contains tutorials and examples for Triton Inference Server
MCP-NixOS - Model Context Protocol Server for NixOS resources
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
AlphaPose + ST-GCN + SORT.
Can Neural Networks Crack Sudoku?
Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data
Suno AI's Bark model in C/C++ for fast text-to-speech generation
Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
Keras Generative Adversarial Networks