AI 开源项目榜。

FlashAttention (Metal Port)

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

不要问 AI，问薯条。一个结合麦当劳 MCP 与 AI 答案之书的 Skill。

[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

[TIP'19] AttGAN: Facial Attribute Editing by Only Changing What You Want

Jupyter widget helpers for ROS, the Robot Operating System

N-BEATS is a neural-network based model for univariate timeseries forecasting. N-BEATS is a ServiceNow Research project that was started at Element AI.

This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

⚡️ A library of widgets and helpers to build instant-search applications on iOS.

Simple Agents Made Easy

A Python library for running thousands of MuJoCo simulations in parallel on CPU

jsontt 💡 - AI JSON Translator with GPT / Gemma / Mixtral / llama + other FREE translation modules to translate your json/yaml files into other languages ✅ Check Readme ✌ Supports GPT / Gemma / Mixtral / llama / DeepL / Google / Bing / Libre / Argos

Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.

Perplexity GPU Kernels

Real-time transcription using faster-whisper

MDA Open Spec — a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md, MCP-SERVER.md, and CLAUDE.md. JSON Schema validated, with typed dependency graph, footnote relationships, and Sigstore-anchored signatures. For agentskills.io and AAIF runtimes.

Python library for analysing faces using PyTorch

MCP to connect your LLM with Spotify.

The official PyTorch implementation of img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation - CVPR 2021

🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox

📣 商用级开源语音自动识别程序库，开箱即用，全平台支持，中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide a set of easier APIs to call ASR models.

NetVLAD: CNN architecture for weakly supervised place recognition

Unitree Go2 simulation platform for testing navigation, decision-making and autonomous tasks. (NVIDIA Isaac/ROS2)

🔥Deep Learning for Face Anti-Spoofing

ChatGPT raycast extension

Anki Vector Python SDK

Skills and eval rubrics for K-12 teachers, co-developed with Learning Commons

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)