AI 开源项目榜。

Simple, extensible and powerful one stop personal assistant

Native macOS app to monitor AI usage limits and watch your coding sessions live

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

Update arXiv papers about Spiking Neural Networks daily.

Generating bash command from natural language https://arxiv.org/abs/1802.08979

Paper-Agent 是一个面向科研人员和学生的智能论文检索与调研工具。项目基于多智能体协作架构（LangGraph），通过自然语言处理（NLP）、自动化搜索，帮助用户高效查找学术论文、分析文献内容，并进行论文调研。Paper-Agent 支持多平台集成、关键词搜索、自动分析、论文调研，提升了学术研究的效率。适用于论文写作、学术调研、科研项目管理等多种场景，是学术调研的理想助手。

Demo on adding virtual background to a live video stream in the browser

A Codex skill for creating and verifying animated GIF sticker packs from character references.

INSTA - Instant Volumetric Head Avatars [CVPR2023]

[CVPR'17] Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to high performance at fast speed..

dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.

Open-source mobile SSH/Mosh terminal and native AI workspace for Android and iOS.

PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"

Bayesian Deep Learning: A Survey

🌲 Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams

A comprehensive collection of advanced prompts engineered for Grok AI. Features optimized templates, strategies, and expert techniques to maximize Grok's potential across diverse applications.

This is a pytorch implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks

Official pytorch implementation for "Deep Video Inpainting" (CVPR 2019)

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation (CVPR 2023)

A list of works on video generation towards world model

Python package for Bayesian Machine Learning with scikit-learn API

Deep Reinforcement Learning for Robotic Grasping from Octrees

An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.

Portable AI-agent skill: turn YouTube, Instagram, TikTok, X and other video links into Obsidian-ready Markdown notes: captions or local Whisper transcripts, frames, metadata and timestamps

[NeurIPS 2025] Improving Video Generation with Human Feedback

Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)

[CVPR 2024] PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor

Claude Code Plugin Marketplace with LSP servers

A space exploration game built by Claude Opus 5