🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.

Making large AI models cheaper, faster and more accessible

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

🤗 smolagents: a barebones library for agents that think in code.

Fully open reproduction of DeepSeek-R1

Rembg is a tool to remove images background

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

A TTS model capable of generating ultra-realistic dialogue in one pass.

An open source platform for Python in the browser. https://pyscript.net Docs: https://docs.pyscript.net/ Try it: https://pyscript.com/ Community: https://discord.gg/HxvBtukrg2

The Rogue Access Point Framework

A collaboration friendly studio for NeRFs

Official repository for LTX-Video

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Point cloud diffusion for 3D model synthesis

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Google Drive Public File Downloader when Curl/Wget Fails

WebRTC and ORTC implementation for Python using asyncio

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

Run LLMs with MLX

Python package for the evaluation of odometry and SLAM

Visual localization made easy with hloc

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

Open source Structure-from-Motion pipeline

Open source process design kit for usage with SkyWater Technology Foundry's 130nm node.

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…