AI 开源项目榜。

A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018

Collection of recent methods on (deep) neural network compression and acceleration.

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization

Local MCP work notes with persistent sessions, decisions, evidence and resumable tasks.

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

OpenEverest is an open-source platform for automated database, storage and LLMs provisioning and management. It supports multiple technologies and can be hosted on any Kubernetes infrastructure, in the cloud or on-premises.

Review your agent's diff in a terminal pane and send comments back to Claude Code, Codex, OpenCode or Pi. A herdr plugin.

go version of tiktoken

A general list of resources to image text localization and recognition 场景文本位置感知与识别的论文资源与实现合集 シーンテキストの位置認識と識別のための論文リソースの要約

A simple resume parser used for extracting information from resumes

[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)

Fast Diffusion Models with Transformers

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

A CLI-based, flat-file issue tracker for humans and robots. 🤖

Batteries for your Pydantic AI agent.

OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

[中文法律大模型] DISC-LawLLM: an intelligent legal system powered by large language models (LLMs) to provide a wide range of legal services.

This is the Curriculum for "Machine Learning Journey" By Siraj Raval on Youtube

TruthfulQA: Measuring How Models Imitate Human Falsehoods

A real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

Technical specifications for IAB Europe Transparency and Consent Framework that will help the digital advertising industry interpret and comply with EU rules on data protection and privacy - notably the General Data Protection Regulation (GDPR) that comes into effect on May 25, 2018.

KDD 2019: Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Machine Learning Open Source University

Bolt is a deep learning library with high performance and heterogeneous flexibility.