Exploring the space where music, AI, and scientific computing meet.

This GitHub org hosts experiments, tools, and libraries for:

• Music information retrieval, audio feature extraction, and DSP for composition, mixing, and analysis.
• Machine learning / AI tooling for music, sound design, and visual art.
• Reproducible scientific workflows, data pipelines, and research prototypes in Python and JS/TS.

I’m interested in using open tooling to make it easier for researchers, engineers, and artists to:

• Prototype and share audio/ML experiments quickly.
• Reuse models, datasets, and notebooks across projects.
• Bridge DAWs, live performance tools, and research codebases.

If your work touches music tech, MIR, generative models, creative coding, or applied data science for the arts, you’re in the right place.

• Audio and MIDI preprocessing utilities.
• Model training / evaluation scripts for music and audio ML.
• Tools that connect DAWs, live‑coding environments, and ML backends.
• Notebooks and minimal demos for scientific and artistic experiments.

(Repo‑level READMEs go into install, usage, and citations.)

Contributions are very welcome, especially from:

• Researchers (MIR, audio ML, generative models, HCI for creative tools).
• Musicians, producers, and sound designers who like to prototype with code.
• Data/ML engineers interested in open creative tooling.

Ways to get involved:

1. Open an issue to propose a feature, experiment, or integration.
2. Fork a repo, create a small, focused PR (bugfix, refactor, new example, or doc).
3. Share example notebooks, demo projects, or datasets that others can build on.

Please keep contributions:

• Reproducible (clear environment, minimal config).
• Well‑documented (short README, comments where non‑obvious).
• Respectful of licensing for samples, datasets, and models.

If you’d like to discuss a collaboration, research idea, or integration with your lab, DAW workflow, or art project, feel free to:

• Open a “discussion” or issue in the most relevant repository.
• Mention @GuidoGerb on GitHub in a thread you’d like me to see.

Let’s build tools that make science and art talk to each other.

Repository	Description
7digital-api	— ⚠️ — This repo is specific to the 7digital download store, and is not actively maintained. For new integrations with the 7digital ...
AgentCPM-GUI	【English — <a href="README...
AlchemistCoder	> Zifan Song1,2*, Yudong Wang2*, Wenwei Zhang2*, Kuikun Liu2, Chengqi Lyu2, Demin Song2...
AnchorWeave	Zun Wang1, Han Lin1, Jaehong Yoon2, Jaemin Cho3, Yue Zhang1, **Mohit Ban...
ArcLight	ArcLight: A Lightweight LLM Inference Framework
AudioX	**This is the official repository for "AudioX: A Unified Framework for Anything-to-Audio Generation" (Accepted ...
CUDA-Agent	CUDA-Agent is the first known RL-trained model to surpass advanced models such as Claude Opus-4.6 and Gemini 3 Pro on high-performance CUDA kernel ...
ChatDev
CogVideo	中文阅读
ComfyUI
ComfyUI-KJNodes	Various quality of life and masking related -nodes and scripts made by combining functionality of existing nodes for ComfyUI.
ComfyUI-LTXVideo	A collection of powerful custom nodes that extend ComfyUI's capabilities for the LTX-2 video generation model.
ComfyUI-Mickmumpitz-Nodes	A collection of custom nodes for ComfyUI by Mickmumpitz.
ComfyUI-Qwen-TTS	English — 中文版
ComfyUI_OmnimatteZero	Official implementation of OmnimatteZero: Training-Free Video Matting and Compositing via ...
ComfyUI_RH_DreamID-V	<img src="https://img.shields.io/badge/License...
ComfyUI_examples	This repo contains examples of what is achievable with [ComfyUI](https://github.com/comfyanon...
CubeComposer	CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video
DreamID-Omni	> [!NOTE] > This repository is forked from the omni branch of DreamID-V. <a href...
DreamID-V	🌐 Project Page — 📜 Arxiv — <...
FastVMT	FastVMT⚡️: Eliminating Redundancy in Video Motion Transfer
FreeCAD
GLM-5	👋 Join our W...
GLM-OCR	中文阅读
HY-WU
Helios
HiFi-Inpaint	HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Huma...
HunyuanVideo	中文阅读
IC-Light	IC-Light is a project to manipulate the illumination of images.
Intern-S1
InternLM
InternLM-Math
InternLM-XComposer	InternLM-XComposer-2.5
JanusCoder	JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
Kiwi-Edit	Ki<span sty...
LTX-2	LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchron...
LTX-Desktop	LTX Desktop is an open-source desktop app for generating videos with LTX models — locally on supported Windows/Linux NVIDIA GPUs, with an API mode ...
LTX-Video
LavaSR	<img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-FF...
LoRWeB
MFLUX-WEBUI	A pinokio script for git@github.com:CharafChnioune/MFLUX-WEBUI.git
MSongsDB	MILLION SONG DATASET
MindSearch
MiniCPM
MiniCPM-o
Modernizr	<img alt="Modernizr" src="./media/Modernizr-2-L...
MonarchRT
MuseScore	Music notation and composition software
OmniXtreme	This repository contains the official implementation of OmniXtreme, a unified policy framework for high-dynamic humanoid motion tracking.
OmnimatteZero	Official implementation of OmnimatteZero: Training-Free Video Matting and Compositing via Latent Diffusion Models
OpenAOE
OpenDiloco	This repository contains the training code and experiment results for the paper [OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-...
PhysicEdit	From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Prio...
Prompt-Engineering-Guide	Sponsored by    <img src="https://cdn.rawgit.com/standard/standard/master/do...
Qwen-Agent	Copyright 2023 The Qwen team, Alibaba Group. All rights reserved.
Qwen-Image	&n...
Qwen3-Coder
Qwen3-Coder-Next-Zeta-GGUF	MODEL IS AVAILABLE HERE
Qwen3-Omni
Qwen3-VL
Qwen3.5	<a href="https://ch...
RealWonder
SWE-ReX	<img src="https://raw.githubusercontent.com/SWE-agent/swe-agent-media/refs/heads/main/media/logo...
SWE-agent	...
SevenDigital.Api.Schema	What is this code? Schema in C# for public 7digital Api endpoints. These definitions are used by and installed with [The Api Wrapper](https://githu...
SevenDigital.Api.Wrapper	About 7digital
SpatialT2I	<a href="https://github.com/DAG...
Spectrum
Stable-Video-Infinity
Step-3.5-Flash	license: apache-2.0 base_model: - stepfun-ai/step-3.5-flash --- -->
StoryDiffusion
Track4World
UltraRAG	<source media="(prefers-color-scheme: ...
Utonia	TL;DR: This repo provide cross-domain pre-trained Point Transformer V3 for 3D point cloud do...
VecGlypher	This repository contains the re-implementation for VecGlypher: Unified Vector Glyph Generation with Language Models.
VoxCPM
Wan2GP	WanGP by DeepBeepMeep : The best Open Source Video Generative Models Accessible to the GPU Poor
Z-Image	⚡️- Image An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
agentlego	<img src="https://github-production-user-asset-6210df.s3.amazonaws.com/26739999/289025203-f05733ff-6bbb-46f0-92aa-8827c59df79c...
ai-toolkit	AI Toolkit is an all in one training suite for diffusion models. I try to support all the latest models on consumer grade hardware. Image and video...
ampache	www.ampache.org
ampache-administrator	This repo containse the scripts used to build Ampache resources including:
amplify-js
amplify-ui	AWS Amplify
anus	The AI agent that contributes to its own development.
api-stub	About 7digital
app	No description available
apps	Saleor Apps
asset-manager	A comprehensive system for managing creative assets across various storage environments.
asset-manager-xfer	A comprehensive system for managing creative assets across various storage environments.
audiveris	diff - The site https://audiveris.com (note the `.com` extension) - has nothing to do with Audiveris and seems to be a fraudulent site.
awesome-cursorrules	<pictur...
awesome-python	An opinionated list of awesome Python frameworks, libraries, software and resources.
awesome-saleor	An opinionated list of awesome tools, libraries, and resources for Saleor. Inspired by the [awesome-python](https://github.com/vinta/awesome-python...
blacklist-hosts	> [!IMPORTANT] > Cloning this repository can take a long time! > You probably just want to start with the latest version, not its whole history...
blender	Keep this document short & concise, linking to external resources instead of including content in-line. See 'release/text/readme.html' for the end ...
blender-addons	This is an official read-only mirror.
blender-addons-contrib	This is an official read-only mirror.
blender-dev-tools	This is an official read-only mirror.
blender-translations	This is an official read-only mirror.
blockchainvoting	Election integrity with blockchain ballots
bridge-gapp	This project is meant to replace the boilerplate application and configuration processes against the current technology stack. It uses a descripti...
camel
communique	This project can be used as a starting point to create your own Hilla application with Spring Boot. It contains all the necessary configuration and...
configurator	> Commerce as Code — Define your Saleor store in YAML, sync with your instance
crewAI
cycles	Cycles Renderer
diloco_simple	This repo contains a minimal reproducible torch example of the ["DiLoCo: Distributed Low-Communication Training of Language Models"](https://arxiv....
fastapi	<img src="https://fastapi.tiangolo.com/img/logo-margin/logo-teal-vector.svg" alt='FastAPI...
fastapi-cli	<img src="https://github.com/fastapi/fastapi-cli/actio...
fastmcp
ffmpeg-custom	Compile FFMPEG using the latest GCC compiler
fsutil	No description available
garygerber-website	This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.
ggml	Roadmap / Manifesto
ggp-design-system	A zero-dependency design system and multi-site build pipeline providing SCSS stylesheets, vanilla JavaScript behaviors, Jinja2 template macros, OID...
ggp-mcp-agent	> A secure MCP client and agentic workflow manager for Synology NAS
ggp-midi-to-musicxml	The translation of a condensed musical sketch—specifically, a three-track MIDI file comprising a melody, a bassline, and a harmonic chord progressi...
ggp-python-project	Zero-dependency 3D geometry processor — native HTML5 Web Components + Rust WebAssembly. Python-only toolchain — no Node.js, npm, or any JS ...
ggp-react-project	AWS Amplify application with a Vite React frontend (Cognito OIDC authentication) and a Python Lambda backend.
ggp-studio	GGP Studio is a comprehensive, monolithic AI video production workspace. It unifies state-of-the-art generative models (LTX-2, DreamID-V, Wan-A...
gitea	繁體中文 — 简体中文
gpt-builder	Welcome to the https://github.com/guidogerb/gpt-dev repository! This repository hosts the custom GPT (Generative Pre-trained Transformer) model nam...
gpt-engineer	gpt-engineer lets you: - Specify software in natural language - Sit back and watch as an AI writes and executes the code - Ask the AI to implement ...
graffiti-monkey	Graffiti Monkey
grok-1	This repository contains JAX example code for loading and running the Grok-1 open-weights model.
guidogerb-paleontology	A scientific research paper proposal that explores the development, design, and implementation of an AI-assisted fossilized bone harvesting and cat...
guidogerb-web	guidogerb-web is a suite of web components that strictly implement the W3C and WHATWG HTML Living Standard and DOM Standard. The primary focus of...
guidogerb-website	Reusable packages for all four sites.
guidolib	Grame - Centre National de Création Musicale
hedgedoc	SPDX-FileCopyrightText: 2021 The HedgeDoc developers (see AUTHORS file)
hivemind	Distributed training of large neural networks across volunteer computers.
hunyuan-text2video-comfyui-workflows	Workflows to make videos with tencent's hunyuan video model...
ids	GuidoGerb Publishing, LLC
improved-aesthetic-predictor	Train, use and visualize an aesthetic score predictor ( how much people like on average an image ) based on a simple neural net that takes CLIP emb...
kaprekar-thermodynamics	Date: January 2026 Authors: Gary Gerber Journal: Draft for J. Appl. Math. Sci.
lambda-graffiti-monkey	An AWS Lambda function to run Graffiti Monkey serverless. This function works great when triggere...
langchain	⚡ Build context-aware reasoning applications ⚡
langchain-ts-starter	Boilerplate to get started quickly with the Langchain Typescript SDK.
llama.cpp	Manifesto / ggml / [ops](https://github.com/ggml-org/l...
llm-agent-break	At the dawn of artificial general intelligence, Freysa emerged as one of the first truly autonomous AI agents. Unlike her predecessors, she was des...
lmdeploy
localStorage	<img width="1200" height="475" alt="GHBanner" src="https://github.com/user-attachments/assets/0aa67016-6eaf-458a-adb2-6e31a076...
markdown-to-pdf	A Python application that converts Markdown documents to beautifully formatted, printable PDF files.
matrix.to	Matrix.to is a simple url redirection service for the Matrix.org ecosystem which lets users share links to matrix entities without being tied to a ...
mb3d	Mandelbulb3D
mediawiki-bootstrap	This theme was originally developed for wiki.blender.org.
mini-swe-agent	<img src="https://github.com/SWE-agent/mini-swe-agent/raw/main/docs/assets/mini-s...
musicbrainz-docker	musicbrainz slave server with search and replication
musicbrainz-server	The MusicBrainz Server README
new-uid-portal	new-uid-portal
nopaste	NoPaste is an open-source website similar to Pastebin where you can store any piece of code, and generate links for ea...
nucleon-switch	The "Nucleon Switch" represents a highly advanced, theoretical thought experiment designed to probe the extreme boundaries of nuclear physics, ther...
ollama	<...
ollama-fargate	This repository contains a Docker image for running Ollama as an AWS Fargate service, exposing Ollama endpoints to React applications running in AW...
ome	<img src="site/assets/icons/logo-clear-background.png" alt="OME Logo" width="300...
omnimatte	This repository contains a re-implementation of the code for the CVPR 2021 paper "[Omnimatte: Associating Objects and Their Effects in Video](https...
open-llms	These LLMs (Large Language Models) are all licensed for commercial use (e.g., Apache 2.0, MIT, OpenRAIL-M). Contributions welcome!
openai-node	> [!IMPORTANT] > We're actively working on a new alpha version that migrates from node-fetch to builtin fetch. > > Please try it out and let us k...
openai-python	The OpenAI Python library provides convenient access to the OpenAI REST API from any Python 3.8+ application. The library includes type definitions...
openclaw	<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/as...
opensheetmusicdisplay
<img id="osmdlogo" alt="OpenSheetMusicDisplay (OSMD)" src="https://opensheetmusicdisplay.org/wp-content/uploads/2016/05/OSMD_3_icon_only.s...
organize-models	No description available
owl
paperbanana	<td width="220" align="left" valign="middle" style="borde... penpot This repository is a fork of penpot/penpot and is used to apply custom patches or to suggest changes upstream. photoshop A Python application that recursively scans for Photoshop (PSD) files, copies each to an output directory using SHA256 to avoid duplicates, creates... playwright-python Playwright is a Python library to automate Chromium, Firefox and [We... pojo-gernerator No description available portal-client No description available prime prime (previously called ZeroBand) is a framework for efficient, globally distributed training of AI models over the internet. puppeteer python-sdk runner-images runner-images saleor Saleor is a high-performance e-commerce solution created with Python and Django. saleor-dashboard Saleor Dashboard saleor-vatrc Implements VAT reverse charge procedure. seleniumish .venv\Scripts\activate sgl-cookbook A community-maintained repository of practical guides and recipes for deploying and using SGLang in production environments. Our mission is simple:... sgl-docs The official documentation and cookbook for SGLang — a high-performance serving framework for large langua... sgl-learning-materials Please join our Slack Channel https://slack.sglang.ai. For enterprises interested in adopting or deploying SGLang at scale, including technical con... sgl-project.github.io This is the documentation website for the SGLang project (https://github.com/sgl-project/sglang). sglang <img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400" mar... sglang-omni SGLang-Omni is an ecosystem project for SGLang. Omni models refer to models that have multi-modal inputs and multi-modal outputs. These models typi... solaris This repository contains the JAX implementation of the Solaris multiplayer world model for Minecraft. It supports GCP TPU training and inference, a... solaris-engine This repository contains a multiplayer data collection framework for Minecraft. It uses Mineflayer bo... spksrc SynoCommunity is now on Discord! spring-cli A CLI focused on developer productivity spring-data-relational Spring Data Relational. Home of Spring Data JDBC and Spring Data R2DBC. sqlmodel <img src="https://sqlmodel.tiangolo.com/img/logo-margin/logo-margin-vector.svg#only-ligh... stable-diffusion-webui A browser interface based on Gradio library for Stable Diffusion. storefront <img width="1920" height="1080" alt="saleor-storefront-paper-fin" src="https://github.com/user-attachments/assets/a8e37c20-35c8-42e0-a9c5-5c0b6097b... streamlit surge This is the synthesizer plug-in Surge which I previously sold as a commercial product as the company vember audio. As I'm ... tasks-tracker `` python --version python -m venv python-3_12_4-env .\python-3_12_4-env\Scripts\activate python.exe -m pip install --upgrade pip cd tasks_db docke... temp-uid This comprehensive README.md integrates the structural overview of the monorepo with the detailed operational guidelines for the *Hub-and-Spoke... terraform-aws-lambda-scheduler-stop-start Terraform module which create lambda scheduler for stop and start resources on AWS terraform-ggp Terraform GuidoGerb Publishing, LLC terraform init terraform fmt terraform validate terraform plan terraform apply test No description available tiny-aya-tech-report No description available tttLRM tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction <a href="https://arxiv.o... vexchords VexChords renders guitar chords in your browser. vexflow VexFlow is an open-source library for rendering music notation. It is written in TypeScript (compiled to ES6), and outputs scores to HTML Canvas an... videomt CVPR 2026 · 📄 Paper whisper [Blog] [Paper] [[Model card]](https://github.com/openai/whisper/blob/main/mo... whisper.cpp Stable: v1.7.3 / [Roadmap — F.A.Q.](https://github.com/ggerganov/whisper.cpp/discus... wixy A powerful, Wix Studio-inspired web design builder built with Vite, React, and TypeScript. Create stunning web pages with an intuitive drag-and-dro... wordlebuster This project can be used as a starting point to create your own Vaadin application with Spring Boot. It contains all the necessary configuration an... zenphoto A Vite + React website with Vitest testing, organized as a monorepo with npm workspaces.