AI 开源项目榜。

Cloud-native Financial Reinforcement Learning

Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)

An open source, minimal AI powered note taking app and powerful markdown editor

My Answer to 120 Data Science Interview Questions

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

[ICLR 2024 & ECCV 2024] The All-Seeing Projects: Towards Panoptic Visual Recognition&Understanding and General Relation Comprehension of the Open World"

DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.

Generate textbook-quality synthetic LLM pretraining data

A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude Code, and Codex CLI.

Open Duet card feed: agents finish work, Magnus decides with one click

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation (CVPR 2022)

DevOps-Models is a series of industrial-first LLMs for theDevOps domain. Asking it for any question in the DevOps domain to get solution!

KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)

Interactive AI-driven game to learn Docker, Linux, networking & Kubernetes. Open in Claude Code or Cursor, type 'let's play'.

A modern, cross-platform client for the Agent Client Protocol (ACP) on desktop, mobile, and the web — connect to any ACP-compatible AI agent (Claude, Codex, Copilot, Qwen, Gemini, OpenCode, OpenClaw and more)

The BlazeFace face detector model implemented in PyTorch

AI-powered video editor that turns raw footage and a creative brief into a polished ad using an ensemble of AI agents (Google Gemini + FFmpeg)

Tool for chatting with your codebase and docs using OpenAI, LlamaCpp, and GPT-4-All

An open source advanced driver assistance system (ADAS) that uses Jetson Nano as the hardware. Features: Traffic sign detection, Forward collision warning, Lane departure warning.

X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)

Learning Implicit Surfaces from Point Clouds (ECCV 2020)

A deep learning-based tool to identify splice variants

Source code for the paper "Empowering LLM to use Smartphone for Intelligent Task Automation"

CUDA checkpoint and restore utility

Prebuilt binary with Tensorflow Lite enabled. For RaspberryPi / Jetson Nano. Support for custom operations in MediaPipe. XNNPACK, XNNPACK Multi-Threads, FlexDelegate.

闭源系统半自动漏洞挖掘工具，针对 jar/war/zip 进行静态代码分析，输出从source到sink的可达路径。LLM将验证路径可达性，并根据上下文给出该路径可信分数

Python wrapper for ByteDance's Seedance 2.5 API — Text-to-Video, Image-to-Video, realistic human faces, native 4K, consistent character generation.

[Nature 2026] Merlin is a 3D VLM for computed tomography that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining.

Convolutional Spatial Propagation Network

LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation