bhack

SenseNova-Vision. Vision as Unified Multimodal Generation

neural-amp-modeler-lv2. Neural Amp Modeler LV2 plugin

vllm-omni. A framework for efficient model inference with omni-modality models

pbpctrl. Control Google Pixel Buds Pro from the Linux command line.

BudsLink. JavaScript

io.github.bhack.mini-eq.

GEM-X. Monocular whole-body 3D human pose estimation using the SOMA body model

jackclient-python. 🂻 JACK Audio Connection Kit (JACK) Client for Python :snake:

pyFFTW. A pythonic python wrapper around FFTW

Awesome-Feed-Forward-3D. An curated list for feed-forward 3D scene modeling, including research directions, datasets, and applications.

mini-eq. Compact PipeWire system-wide parametric EQ for Linux desktops

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

LitLogger. A minimal Python logger that tracks everything you try when building AI - metrics, prompts, models, etc, so you can see what changed and why.

ColorVideoVDP. Colour video VDP

opencode. The open source coding agent.

SAM3-TrackBench. This repository contains the implementation of SAM3 trackers.

executorch. On-device AI across mobile, embedded and edge for PyTorch

py-spy. Sampling profiler for Python programs

spdl. Scalable and Performant Data Loading

devspace. DevSpace - The Fastest Developer Tool for Kubernetes ⚡ Automate your deployment workflow with DevSpace and develop software directly inside Kubernetes.

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

torchforge. PyTorch-native post-training at scale

Stable-Video-Infinity. [ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Sparse-VideoGen. [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

codex. Lightweight coding agent that runs in your terminal

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

OpenImageIO. Reading, writing, and processing images in a wide variety of file formats, using a format-agnostic API, aimed at VFX applications.

X-SAM. [AAAI2026] X-SAM: From Segment Anything to Any Segmentation

Awesome-Multimodal-Referring-Segmentation. [IJCV 2026] Multimodal Referring Segmentation

Awesome-MLLM-Segmentation. A curated list of publications on image and video segmentation leveraging Multimodal Large Language Models (MLLMs), highlighting state-of-the-art methods, innovative applications, and key advancements in the field.

ROSE. Official Repository of "ROSE: Remove Objects with Side Effects in Videos"

BlenderProc. A procedural Blender pipeline for photorealistic training image generation

ripunzip. Rust

torchvision-extra-decoders. An extension of `torchvision` for decoding AVIF and HEIC images.

Video-Frame-Interpolation-Rankings-and-Video-Deblurring-Rankings. ABME AdaFNIO AMT BiM-VFI BiT CBBD CDFI CtxSyn DBVI DC-BVFI DQBC DRVI DvP EAFI EBME EDC EDEN EDENVFI EDSC EMA-VFI FGDCN FILM FLAVR GIMM-VFI HFD HiFI H-VFI IFRNet InterpAny-Clearer IQ-VFI JNMR LADDER M2M MA-GCSPA MoMo PerVFI RIFE RN-VFI SepConv SoftSplat SSR ST-MFNet Swin-VFI TDPNet TLB-VFI TTVFI UGFI UPR-Net VFIformer VFIFT VFIMamba VFIT VRT XVFI

open-r1. Fully open reproduction of DeepSeek-R1

Awesome-Dataset-Distillation. A curated list of awesome papers on dataset distillation and related applications.

torchcodec. PyTorch media decoding and encoding

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

ao. PyTorch native quantization and sparsity for training and inference

EfficientTAM. Efficient Track Anything

torcheval. A library that contains a rich collection of performant PyTorch model metrics, a simple interface to create new metrics, a toolkit to facilitate metric computation in distributed training and tools for PyTorch model evaluations.

VFIMamba. [NeurIPS 2024] VFIMamba: Video Frame Interpolation with State Space Models

llm-continual-learning-survey. [CSUR 2025] Continual Learning of Large Language Models: A Comprehensive Survey

MovieGenBench. Movie Gen Bench - two media generation evaluation benchmarks released with Meta Movie Gen

scalene. Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

openexr-thumbnailer. Show thumbnails for OpenEXR images on Linux

colour-hdri. HDRI / Radiance image processing algorithms for Python

river. 🌊 Online machine learning in Python

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

AI_for_Science_paper_collection. List the AI for Science papers accepted by top conferences

torch-uncertainty. Open-source framework for uncertainty and deep learning models in PyTorch 🌱

aim. Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

llama3. The official Meta Llama 3 GitHub site

nvitop. An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

rustdesk. An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

kineto. A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

openimageio-feedstock. A conda-smithy repository for openimageio.

llamafile. Distribute and run LLMs with a single file.

federated-learning-cg. HTML

VideoSys. VideoSys: An easy and efficient system for video generation

Awesome-Video-Object-Segmentation. 🔥 Latest advances in Video Object Segmentation (VOS) – papers, datasets, and projects.

wireguard-ui. Wireguard web interface

PyAV. Pythonic bindings for FFmpeg's libraries.

kompute. General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.

vision. Datasets, Transforms and Models specific to Computer Vision

Awesome-Reasoning-Foundation-Models. ✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

GLEE. [CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

stocks-extension. A extension to display stock quotes in GNOME Shell Panel

nerfstudio. A collaboration friendly studio for NeRFs

Tiling-Assistant. An extension which adds a Windows-like snap assist to GNOME. It also expands GNOME's 2 column tiling layout.

xstudio. xSTUDIO is a modern, high performance and feature rich playback and review application designed for organisations and individuals in the post production, VFX and Animation industries.

Natron. Open-source video compositing software. Node-graph based. Similar in functionalities to Adobe After Effects and Nuke by The Foundry.

lensfun. The Lensfun project Git repository

opentofu. OpenTofu lets you declaratively manage your cloud infrastructure.

pips2. PIPs++

webrtc-nv-use-cases. Use cases for WebRTC NV

com.slack.Slack. Shell

co-tracker. CoTracker is a model for tracking any point (pixel) on a video.

Blender-Addon-Photogrammetry-Importer. Addon to import different photogrammetry formats into Blender

Meshroom. Node-based Visual Programming Toolbox

Semantic-SAM. [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

triton. Development repository for the Triton language and compiler

StableStudio. Community interface for generative AI

vscode-arduino. Visual Studio Code extension for Arduino

gst-nvmaxine. Gstreamer plugin that allows use of NVIDIA Maxine SDK in a generic pipeline.

mlflow. The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

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.

helm. Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

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.

UNINEXT. [CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Enzyme. High-performance automatic differentiation of LLVM and MLIR.

tracy. Frame profiler

audio-ai-timeline. A timeline of the latest AI models for audio generation, starting in 2023!

SegLossOdyssey. A collection of loss functions for medical image segmentation

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

mysql-operator. MySQL Operator for Kubernetes

visu3d. 3d without friction (Torch, TF, Jax, Numpy)

celluloid. A simple GTK+ frontend for mpv

guac. GUAC aggregates software security metadata into a high fidelity graph database.

scenic. Scenic: A Jax Library for Computer Vision Research and Beyond

vizier. Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.

eepresetselector. EasyEffects Preset Selector GNOME Extension

keras-cv. Industry-strength Computer Vision workflows with Keras

camilladsp. A flexible cross-platform IIR and FIR engine for crossovers, room correction etc.

cpython. The Python programming language

Vitals. A glimpse into your computer's temperature, voltage, fan speed, memory usage and CPU load.

moode. moOde sources and configs

autoeq2camilladsp. Conveniently create CamillaDSP configurations for headphone listening with AutoEq correction data and options for Crossfeed etc.

spot. UNMAINTAINED! Please check out active forks

disco. DISCO is a code-free and installation-free browser platform that allows any non-technical user to collaboratively train machine learning models without sharing any private data.

pugl. A minimal portable API for embeddable GUIs

omigroup. Sandbox for discussing Open Metaverse Interoperability objectives. Want to get involved? Join us in GitHub discussions, and on Discord. PR's welcome!

fwupd. A system daemon to allow session software to update firmware

pep600_compliance. Check manylinux policies to conform to PEP600

pre-commit. A framework for managing and maintaining multi-language pre-commit hooks.

docker-msvc-cpp. Dockerized Visual C++ environment with wine

manylinux-timeline. Tracking manylinux progress on packager side

oss-fuzz. OSS-Fuzz - continuous fuzzing for open source software.

lsp-plugins. Linux Studio Plugins Project

ABX. Web app for AB and ABX listening tests

terraform-google-github-actions-runners. Creates self-hosted GitHub Actions Runners on Google Cloud

camset. GUI for v4l2-ctl

pappl. PAPPL - Printer Application Framework

o3de. Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D engine that enables developers and content creators to build AAA games, cinema-quality 3D worlds, and high-fidelity simulations without any fees or commercial obligations.

Crowded-Valley---Results. This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"

hivemind. Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

grimoirelab. GrimoireLab: platform for software development analytics and insights

AdaptiveCpp. Compiler for multiple programming models (SYCL, C++ standard parallelism, HIP/CUDA) for CPUs and GPUs from all vendors: The independent, community-driven compiler for C++-based heterogeneous programming models. Lets applications adapt themselves to all the hardware in the system - even at runtime!

mlir-emitc. Conversions to MLIR EmitC

autocxx. Tool for safe ergonomic Rust/C++ interop driven from existing C++ headers

actions-runner-controller. Kubernetes controller for GitHub Actions self-hosted runners

BIG-bench. Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

tensorflow-coder. Python

covid19-opendata-vaccini. Open Data su consegna e somministrazione dei vaccini anti COVID-19 in Italia - Commissario straordinario per l'emergenza Covid-19

vscode-restore-git-branch-tabs. TypeScript

io-app. IO, l'app dei servizi pubblici

khelm. A Helm chart templating CLI, kustomize plugin and containerized kustomize/kpt KRM function

javaproperties. Python library for reading & writing Java .properties files

long-range-arena. Long Range Arena for Benchmarking Efficient Transformers

lucid. A collection of infrastructure and tools for research in neural network interpretability.

discourse-topic-voting. Adds the ability for voting on a topic within a specified category in Discourse.

torch-mlir. The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

cloud. ⛔️ DEPRECATED - The TensorFlow Cloud repository provides APIs that will allow to easily go from debugging and training your Keras and TensorFlow code in a local environment to distributed training in the cloud.

xournalpp. Xournal++ is a handwriting notetaking software with PDF annotation support. Written in C++ with GTK3, supporting Linux (e.g. Ubuntu, Debian, Arch, SUSE), macOS and Windows 10. Supports pen input from devices such as Wacom Tablets.

svgwg. SVG Working Group specifications

tensortrade. An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.

benchmarks. A benchmark framework for Tensorflow

detr. End-to-End Object Detection with Transformers

godot-blender-exporter. Addon for Blender to directly export to a Godot Scene

decidim. The participatory democracy framework. A generator and multiple gems made with Ruby on Rails

iree. A retargetable MLIR-based machine learning compiler and runtime toolkit.

codespaces-flutter-web. A sample Flutter web project for use on VS Online.

pathfinder. A fast, practical GPU rasterizer for fonts and vector graphics

jukebox. Code for the paper "Jukebox: A Generative Model for Music"

mlir-npcomp. npcomp - An aspirational MLIR based numpy compiler

clvk. Implementation of OpenCL 3.0 on Vulkan

openconnect. Mirror of the official openconnect repository

krustlet. Kubernetes Rust Kubelet

JamTaba. Jamtaba is a software to play online music jam sessions.

pulseaudio-modules-bt. [Deprecated, see https://github.com/EHfive/pulseaudio-modules-bt/issues/154] Adds Sony LDAC, aptX, aptX HD, AAC codecs (A2DP Audio) support to PulseAudio on Linux

AutoEq. Automatic headphone equalization from frequency responses

obs-studio. OBS Studio - Free and open source software for live streaming and screen recording

COVID-19. COVID-19 Italia - Monitoraggio situazione

docker-jitsi-meet. Jitsi Meet on Docker

jitsi-meet-electron. Jitsi Meet desktop application powered by :electron:

FairMOT. [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

element-android. A Matrix collaboration client for Android.

numpy-stubs. Experimental typing stubs for NumPy

DSGN. [CVPR 2020] DSGN: Deep Stereo Geometry Network for 3D Object Detection

EasyEffects-Presets. Collection of PulseEffects presets

CenterTrack. Simultaneous object detection and tracking using center points.

mypy. Optional static typing for Python

DeepSpeech. DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

io. Dataset, streaming, and file system extensions maintained by TensorFlow SIG-IO

onnx-mlir. Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

nerf. Code release for NeRF (Neural Radiance Fields)

jitsi-meet. Jitsi Meet - Secure, Simple and Scalable Video Conferences that you use as a standalone app or embed in your web application.

nuclear. Streaming music player that finds free music for you

Text-Image-Augmentation. Geometric Augmentation for Text Image

COVID-19. Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

addons. Useful extra functionality for TensorFlow 2.x maintained by SIG-addons

dendrite. Dendrite is a second-generation Matrix homeserver written in Go!

mriviewer. MRI Viewer is a high performance web tool for advanced 2-D and 3-D medical visualizations.

centermask2. [CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation

fmjpeg2koj. JPEG2000 codec for DCMTK using openjpeg

aravis. A vision library for genicam based cameras

v4l2loopback. v4l2-loopback device

element-web. A glossy Matrix collaboration client for the web.

pipewire. Mirror of the PipeWire repository (see https://gitlab.freedesktop.org/pipewire/pipewire/)

vscode-bazel. Bazel support for Visual Studio Code

nnstreamer. :twisted_rightwards_arrows: Neural Network (NN) Streamer, Stream Processing Paradigm for Neural Network Apps/Devices.

flax. Flax is a neural network library for JAX that is designed for flexibility.

tflite_native. A Dart interface to TensorFlow Lite (tflite) through dart:ffi

wasmtime. A lightweight WebAssembly runtime that is fast, secure, and standards-compliant

web. Grow Open Source

highway. Performance-portable, length-agnostic SIMD with runtime dispatch

XNNPACK. High-efficiency floating-point neural network inference operators for mobile, server, and Web

liboqs. C library for prototyping and experimenting with quantum-resistant cryptography