AI open source rankings.

Content for Udacity's Machine Learning curriculum

Every front-end GUI client for ChatGPT, Claude, and other LLMs

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

A simplified implemention of Faster R-CNN that replicate performance from origin paper

AI-Powered Python & Python-Powered AI (Python-Use)

Task-Aware Agent-driven Prompt Optimization Framework

Vector (and Scalar) Quantization, in Pytorch

Interactive Image Generation via Generative Adversarial Networks

Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow

A simple, easy-to-hack GraphRAG implementation

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Differentiable architecture search for convolutional and recurrent networks

Program learning to play Flappy Bird by machine learning (Neuroevolution)

The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

A lightweight library for portable low-level GPU computation using WebGPU.

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Snips Python library to extract meaning from text

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Learning in infinite dimension with neural operators.

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

OpenHealth, AI Health Assistant | Powered by Your Data

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

Learning embeddings for classification, retrieval and ranking.

Master Claude Code Hooks

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Visual Tracking Paper List