Duane

altara. React components for real-time telemetry dashboards — robotics, aerospace, autonomous vehicles, industrial IoT. PFD, HSI, time-series, gauges, GPS maps, and ROS2/MQTT adapters at 60fps.

gorilla. Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

claude-code-prompt-plunderer. 🔍 Extract and analyze your Claude Code conversation history to discover usage patterns, generate insights, and create custom slash commands from your prompting style.

dev-agent-lens. Proxy Claude Code Requests through LiteLLM to Arize

playwrightess-mcp. An experiment of using playwright MCP via JavaScript

clangd-tidy. A faster alternative to clang-tidy

nano-agent. A MCP Server for a small scale engineering agents with multi-provider LLM support.

mcp-gdb. JavaScript

nanobind. nanobind: tiny and efficient C++/Python bindings

fastmcp. 🚀 The fast, Pythonic way to build MCP servers and clients.

madrona_mjx. C++

mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.

AnyNet. (ICRA) Anytime Stereo Image Depth Estimation on Mobile Devices

LWANet. (Neurocomputing) Light-weight network for real-time adaptive stereo depth estimation

PatchRefiner. [ECCV 2024] Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation

BiTTC. Python

Bi3D. Python

mujoco_warp. GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.

AlphaHero. Distributed AlphaZero implementation in Python.

pypop. [JMLR (CCF-A)] PyPop7: A Pure-PYthon LibrarY for POPulation-based Black-Box Optimization (BBO), especially *Large-Scale* algorithm variants. In the near future, we will add Learning-Based Optimizers as its extensions. [https://jmlr.org/papers/v25/23-0386.html]

Evolutionary-Optimization-Algorithms. DE, CMA-ES, MA-ES, LM-MAES Python Implementation

BARWindSpeed. Beyond All Reason game wind speed simulator

PyDnD. PyDnD is a Dungeons and Dragons SRD Library for Python3

dnd-character. library for making Dungeons & Dragons 5e characters as serializable data

open_spiel. OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

auto-video-editing-suite. All the tools that allow me to never ever open up Final Cut

gymnax-blines. Baselines for gymnax 🤖

rejax. Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!

evosax. Evolution Strategies in JAX 🦎

WU-UCT. A novel parallel UCT algorithm with linear speedup and negligible performance loss.

AlphaZero. Python

cestpasphoto.github.io. AlphaZero and other AI in your browser

alpha-zero-general. A very fast implementation of AlphaZero, applied to games like Splendor, Santorini, The Little Prince, … Browser version available

mctx. Monte Carlo tree search in JAX

mctx-az. Monte Carlo tree search in JAX, with functionality to continue search from a previous subtree

turbozero. fast + parallel AlphaZero in JAX

gymnax. RL Environments in JAX 🌍

pgx. ♟️ Vectorized RL game environments in JAX

turbozero_torch. fast + parallel AlphaZero in PyTorch

AgentBench. A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

LightZero. [NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

1D-ARC.

Single-Player-MCTS. 🌳 Python implementation of single-player Monte-Carlo Tree Search.

torch-distmap. Euclidean distance transform in pytorch

LocNDF. LocNDF: Neural Distance Field Mapping for Robot Localization

maze-dataset. maze datasets for investigating OOD behavior of ML systems

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

Absolute-Policy-Optimization. The source code of Absolute Policy Optimization

direct-preference-optimization. Reference implementation for DPO (Direct Preference Optimization)

rl. A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

source_one. Open Source FPV Drone Frame

IsaacLab. Unified framework for robot learning built on NVIDIA Isaac Sim

aruco_ros. Software package and ROS wrappers of the Aruco Augmented Reality marker detector library

master_project. This project is about vision based navigation and precision landing of a drone using ROS, PX4 and OpenCV

autonomous_landing_uav. ROS packages of the Autonomous landing system of a UAV in Gazebo

NvChad. Blazing fast Neovim framework providing solid defaults and a beautiful UI, enhancing your neovim experience.

Battle-of-the-Backbones.

PointPillars. A Simple PointPillars PyTorch Implementation for 3D LiDAR(KITTI) Detection.

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.

PonderV2. [T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

awesome-rgbd-datasets. This repository contains information for the paper "A Survey on RGB-D Datasets" and is a collaborative initiative to update the datasets list faster.

3D_Hand_Keypoint_Detection. Modified the InterHand2.6M for 3D hand detection on custom images for pose estimation using a Single RGB Image.

diffusion_policy. [RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

diffusion-policy. Implementation of Diffusion Policy, Toyota Research's supposed breakthrough in leveraging DDPMs for learning policies for real-world Robotics

tapnet. Tracking Any Point (TAP)

aot-benchmark. An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

Segment-and-Track-Anything. An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

CoDeF. [CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

product-key-memory. Standalone Product Key Memory module in Pytorch - for augmenting Transformer models

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

segment_anything_tensorrt. Accelerate segment anything model inference using Tensorrt 8.6.1.6

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

x-transformers. A concise but complete full-attention transformer with a set of promising experimental features from various papers

NYU-DLSP20. NYU Deep Learning Spring 2020

act. Python

fast-whisper-finetuning. Jupyter Notebook

Track-Anything. Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

interbotix_ros_manipulators. ROS Packages for Interbotix Arms

dreamerv3. Mastering Diverse Domains through World Models

crafter. Benchmarking the Spectrum of Agent Capabilities

solo-learn. solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

adios. Shell

ROS-Mobile-Android. Visualization and controlling application for Android

roverrobotics_stack. ROS1 stack for Rover Pro, Rover Zero and Rover Zero 2. Its recommended all users of archived rr_openrover_stack update to this repo.

tensorrt_inference. C++

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

imutils. A series of convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and Python.

SiamTrackers. (2020-2022)The PyTorch version of SiamFC，SiamRPN，DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on deep learning

YOLOv7_Tensorrt. A simple implementation of Tensorrt YOLOv7

docker-mavros. Docker Container for MAVROS

fastbook. The fastai book, published as Jupyter Notebooks

connectbot. ConnectBot is the first SSH client for Android.

cma-es. Covariance Matrix Adaptation Evolution Strategy (CMA-ES)

sutherland-hodgman. A differentiable Python implementation of the Sutherland–Hodgman algorithm for clipping polygons in 2D.

Python-Games. Python

Pygame-Geometry. My superset of pygame for making simulations and games.

zed-sdk. ⚡️The spatial perception framework for rapidly building smart robots and spaces

sip-call. ESP32 simple VoIP phone based on SPH0645 mic and UDA1334A decoder

OpenKAI. OpenKAI: A modern framework for unmanned vehicle and robot control

prompt-to-prompt. Jupyter Notebook

deis. [ICLR 2023]DEIS: Fast Sampling of Diffusion Models with Exponential Integrator

bthelper. Bluetooth helper tools for setting up serial ports for e.g. SSH

yolo-tiling. Tile (Slice) YOLO Dataset for Small Objects Detection

RxCmd. Bluetooth control of Raspberry Pi

drive_ros_bb_to_obstacle. Converts BoundingBoxArray.msg to ObstacleArray.msg using the camera homography.

gstream_Deep. ZED2 with Nvidia Deepstream

deepsparse. Sparsity-aware deep learning inference runtime for CPUs

robo_magellan. Python

coco-annotator. :pencil2: Web-based image segmentation tool for object detection, localization, and keypoints

cartographer. Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.

deep-video-mvs. Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)

tsdf-fusion-python. Python code to fuse multiple RGB-D images into a TSDF voxel volume.

pyRANSAC-3D. A python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm

RGBD-semantic-segmentation. A paper list of RGBD semantic segmentation (processing)

torchdyn. A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

functorch. functorch is JAX-like composable function transforms for PyTorch.

ELFIO. ELFIO and ARIO are robust, header-only C++ libraries designed to make binary file and archive manipulation effortless, efficient, and portable. Whether you are building compilers, linkers, binary analysis tools, or custom build systems, these libraries provide the foundation you need for working with ELF files and UNIX archives.

iris. Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

DeepStream-Yolo. NVIDIA DeepStream SDK 8.0 / 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

yolov7. Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

yolo-tensorrt. TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.

pysot. SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

SiamTracker-with-TensorRT. The modify PyTorch version of Siam-trackers which are speed-up by TensorRT. [Updating...]

SiamMask. [CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation

goturn-pytorch. GOTURN tracking implemented in PyTorch

GOTURN. Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016

jetson-nano-baseboard. Antmicro's open hardware baseboard for the NVIDIA Jetson Nano, TX2 NX and Xavier NX

MinAtar. Python

mmap.ninja. Memory mapped numpy arrays of varying shapes

mediamtx. Ready-to-use Media-over-QUIC / SRT / WebRTC / RTSP / RTMP / LL-HLS / MPEG-TS / RTP live media server and media proxy that allows to read, publish, proxy, record and playback real-time video and audio streams.

netron. Visualizer for neural network, deep learning and machine learning models

perceiver-pytorch. Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

CFPNet-Medicine. CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

SparseInst. [CVPR 2022] SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation

PyTorch-ONNX-TRT. TensortRT installation and Conversion from PyTorch Models

mobilestereonet. Lightweight stereo matching network based on MobileNet blocks

ONNX-MobileStereoNet. Python scripts for performing stereo depth estimation using the MobileStereoNet model in ONNX

docker-jetson-qemu. Shell

jetson-containers. Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

jetson_stats. 📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series

jetson-image. 💾 Create minimalist, Ubuntu based images for the Nvidia jetson boards

unet_plus_attention. Unet model with stand-alone self-attention blocks

segmentation_models.pytorch. Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

SeqFormer. SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)

UNet-family. Paper and implementation of UNet-related model.

url_benchmark. Python

pixel_models. Pytorch implementations of autoregressive pixel models - PixelCNN, PixelCNN++, PixelSNAIL

ladder-vae-pytorch. Ladder Variational Autoencoders (LVAE) in PyTorch

deformer. An order-agnostic distribution estimating Transformer.

denoising_diffusion. Unofficial Implementation of "Denoising Diffusion Probabilistic Models" in PyTorch(Lightning)

SDEdit. PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

score-denoise. :snowflake: Score-Based Point Cloud Denoising (ICCV 2021)

jax-variational-diffwave. Jax/Flax implementation of Variational-DiffWave.

pytorch_geometric. Graph Neural Network Library for PyTorch

NeuralRecon. Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

gradsim. Differentiable simulation for system identification and visuomotor control

jaxlie. Rigid transforms + Lie groups for JAX

liegroups. Python implementation of SO2, SE2, SO3, and SE3 matrix Lie groups using numpy or pytorch

OpenDUNE. DUNE, REINVENTED

carla-visual-odometry. Visual odometry using stereo camera with CARLA simulator

spconv. Spatial Sparse Convolution Library

sgnn. [CVPR'20] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans

Atlas. Atlas: End-to-End 3D Scene Reconstruction from Posed Images

CPG-RBFN-framework. Code availability for M. Thor et al. 2021 submitted to NMI

RAFT-Stereo. Python

HTM-pytorch. Implementation of Hierarchical Transformer Memory (HTM) for Pytorch

brax. Massively parallel rigidbody physics simulation on accelerator hardware.

micrograd. A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

mbpo. Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

Realsense-disparity-refinement-with-CUDA. C

lightning-kitti. Semantic Segmentation with Pytorch-Lightning

RealtimeStereo. Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)

PSMNet. Pyramid Stereo Matching Network (CVPR2018)

GwcNet. Group-wise Correlation Stereo Network, CVPR 2019

PyTorch-HITNet-Hierarchical-Iterative-Tile-Refinement-Network-for-Real-time-Stereo-Matching. HITNet implementation using PyTorch

PENet_ICRA2021. ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"

X-StereoLab. SOS IROS 2018 GOOGLE; StereoNet ECCV2018 GOOGLE; ActiveStereoNet ECCV2018 Oral GOOGLE; HITNET CVPR2021 GOOGLE；PLUME Uber ATG

YOLOP. You Only Look Once for Panopitic Driving Perception.（MIR2022）

DROID-SLAM. Python

fast-depth. ICRA 2019 "FastDepth: Fast Monocular Depth Estimation on Embedded Systems"

External-Attention-pytorch. 🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

jaxopt. Hardware accelerated, batchable and differentiable optimizers in JAX.

ORB_SLAM3. ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

Bayesian_Hilbert_Maps. Mapping spatiotemporal patterns in an online and continuous fashion

tinyloader. Python

pytube. Lightweight, dependency-free Python library and CLI for downloading YouTube videos, playlists, and captions.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

transfuser. [PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

a0lite. A neural net chess engine in 95 lines of python

batch_rl. Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

lightning-bolts. Toolbox of models, callbacks, and datasets for AI/ML researchers.

CQL. Code for conservative Q-learning

taichi_three. A soft renderer based on Taichi (work in progress)

pyrigidbody3d. tiny toy rigid body sim in python