AI open source rankings.

A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.

Implementing cognitive architecture and psychological memory concepts into Agentic LLM Systems

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

A project management framework for AI-assisted development with Claude Code

An accurate GUI element detection approach based on old-fashioned CV algorithms [Upgraded on 5/July/2021]

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

LimSim & LimSim++: Integrated traffic and autonomous driving simulators with (M)LLM support

RepoMaster: The open-source AI agent that masters GitHub. It turns any code repository into a powerful tool, achieving a new level of autonomous task-solving. An open alternative to Claude-Code.

Hunyuan 3D Part Segmentation and Generation Pipeline

A library for high performance deep learning inference on NVIDIA GPUs.

Let's finetune video generation models!

IndexTTS Voice Cloning: Supports two-person dialogue

A versatile, self-hosted manga reader and manager with extensible agent-based metadata retrieval

Code for paper

A curated list of artificial intelligence resources (Courses, Tools, App, Open Source Project)

Computer vision based vehicle detection and tracking using Tensorflow Object Detection API and Kalman-filtering

Automating Host Exploitation with AI

Search Airbnb using your AI Agent

Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention. Join our Discord communty: https://discord.com/invite/TgHXuSJEk6

AI Trading Agent on Hyperliquid

This repo is implemented based on detectron2 and centernet

Hands-On Machine Learning with C++, published by Packt

CRSLab is an open-source toolkit for building Conversational Recommender System (CRS).

An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.

Code for some of my articles

Pytorch implementation of VQGAN (Taming Transformers for High-Resolution Image Synthesis) (https://arxiv.org/pdf/2012.09841.pdf)

[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.