Nic

openclaude. runs anywhere. uses anything

TagStudio. A User-Focused Photo & File Management System

sqlite-vector. SQLite-Vector is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database.

Z-Image. Python

CentauriCarbon. Learn more about ELEGOO Centauri Carbon 3D printer: https://www.elegoo.com/products/centauri-carbon

awesome-n8n. Useful n8n resources: list of community nodes and tutorials

microSD_express_Pi. HTML

OpenCentauri. Exploration, Research and Development of extensions to the Centauri Carbon printer from Elegoo

gpio_viewer. GPIOViewer Arduino Library to see live GPIO Pins on ESP32 boards

annotation_tools. Visipedia Annotation Tools

marioparty4. C

cc1101-mqtt-fan-controller. Automate dumb ceiling fans using CC1101 RF transceiver, ESP32, and MQTT

PiLiDAR. Python

fnirsi-usb-power-data-logger. Driver / Data logger for FNIRSI FNB48, FNIRSI C1 and FNIRSI FNB58 USB Power meter

p2pro-live. web app to display a live stream of the Infiray P2Pro thermal camera

jellyfin-mpc-shim. Jellyfin MPC Shim is a Windows cast client for Jellyfin

TRELLIS-for-windows. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

kokoro-onnx. TTS with kokoro and onnx runtime

mdoc. Markdown documentation viewer for Visual Studio Code

py-gpt. Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants,and more. Linux, Windows, Mac

Vscode-Python-Config. TypeScript

spandrel. Spandrel gives your project support for various PyTorch architectures meant for AI Super-Resolution, restoration, and inpainting. Based on the model support implemented in chaiNNer.

fasthtml. The fastest way to create an HTML app

piper. A fast, local neural text to speech system

awesome-docker-compose. My Collection of Docker Compose Files. Use "make up" to test it.

mmpose. OpenMMLab Pose Estimation Toolbox and Benchmark.

airflow. Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

SeleniumBase. 📊 APIs for web automation, testing, and bypassing bot-detection.

pandas-ai. Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

superduper. Superduper: End-to-end framework for building custom AI applications and agents.

qapyq. AI-assisted media curator for large image/video datasets. Streamlined captioning, cropping, masking for LoRA/diffusion training workflows.

awesome-cursorrules. 📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

infinity. The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

In-Context-LoRA. Official repository of In-Context LoRA for Diffusion Transformers

joycaption. JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.

quivr. Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

SearChat. Search + Chat = SearChat(AI Chat with Search), Support OpenAI/Anthropic/VertexAI/Gemini, DeepResearch, SearXNG, Docker. AI对话式搜索引擎，支持DeepResearch, 支持OpenAI/Anthropic/VertexAI/Gemini接口、聚合搜索引擎SearXNG，支持Docker一键部署。

anything-llm. Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

awesome-ml. Curated list of useful LLM / Analytics / Datascience resources

karakeep. A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search

FLUX-IR. Python

ctrlora. [ICLR 2025] Codebase for "CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation"

Fabric. Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

ml-depth-pro. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

MiVOLO. MiVOLO age & gender transformer neural network

NanoKVM. Affordable, Multifunctional, Nano RISC-V IP-KVM

Windows-Super-God-Mode. Creates shortcuts to virtually every special location or action built into Windows

bigasp-training. Various training scripts used to train bigasp

FollowYourEmoji. [SIGGRAPH Asia 2024 & IJCV 2025] Follow-Your-Emoji & Follow-Your-Emoji-Faster: This repo is the official implementation of "Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation"

ControlNetPlus. ControlNet++: All-in-one ControlNet for image generations and editing!

candy-machine. Image Dataset Tagger for Stable Diffusion / Lora / DreamBooth Training

ComfyUI-IC-Light. Using IC-LIght models in ComfyUI

pifuhd. High-Resolution 3D Human Digitization from A Single Image.

pifuhd. High-Resolution 3D Human Digitization from A Single Image.

SUPIR. SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

taggui. Tag manager and captioner for image datasets

DatasetTag. Helper utility for Machine Learning dataset images caption preparation

InstantID. InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

GPT4V-Image-Captioner. Python

mutagen. Python module for handling audio metadata

toolBLEx. A multiplatform Bluetooth Low Energy (and Classic) device scanner and analyzer.

AnimateAnyone. Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

super-gradients. Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

tortoise-tts. A multi-voice TTS system trained with an emphasis on quality

FlexiCubes. Python

Fusion360-Tool-Icons. Tool icons from Autodesk Fusion 360.

ytdlp2STRM. A little script to serve Youtube / Twitch / Crunchyroll videos without storage it. Uses yt-dlp HTTP data throught Flask and dynamic URLs. We can use this dynamic URLs to set STRM files.

Klipper-Adaptive-Meshing-Purging. A unique leveling solution for Klipper-enabled 3D printers!

tubearchivist. Your self hosted YouTube media server

dock-droid. Docker Android - Run QEMU Android in a Docker! X11 Forwarding! CI/CD for Android!

Docker-OSX. Run macOS VM in a Docker! Run near native OSX-KVM in Docker! X11 Forwarding! CI/CD for OS X Security Research! Docker mac Containers.

docker-android. Android in docker solution with noVNC supported and video recording

redroid-doc. redroid (Remote-Android) is a multi-arch, GPU enabled, Android in Cloud solution. Track issues / docs here

streamlit-image-select. 🖼️ An image select component for Streamlit

PackageMate. Tracking deliveries on your own terms

hm-panelizer. a simple PCB panelizer

exllamav2. A fast inference library for running LLMs locally on modern consumer-class GPUs

atlas-python. Easily bring your Python applications online with the world's lightest GUI toolkit.

Redream. Realtime Diffusion, using Automatic1111 Stable Diffusion API

UniControl. Unified Controllable Visual Generation Model

OneTrainer. OneTrainer is a one-stop solution for all your Diffusion training needs.

docker-partkeepr. 📦 Multi-platform Partkeepr inventory management system image with host volume support.

SeargeSDXL. Custom nodes and workflows for SDXL in ComfyUI

scoppy. Use your Rasperry Pi Pico and Android Phone as an Oscilloscope and Logic Analyzer

sd-tagtool. A stable diffusion training dataset tag editor.

PanoHead. Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"

sam-hq. Segment Anything in High Quality [NeurIPS 2023]

Video-LLaMA. [EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

recognize-anything. Open-source and strong foundation image recognition models.

FlagAI. FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

PowerToys. Microsoft PowerToys is a collection of utilities that supercharge productivity and customization on Windows

ExplorerPatcher. This project aims to enhance the working environment on Windows

VisionLLM. VisionLLM Series

DragGAN. Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

Multimodal-GPT. Multimodal-GPT

babyagi. Python

Edit_Everything. Jupyter Notebook

mPLUG-Owl. mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

seait. SEAIT is a user-friendly application that simplifies the installation process of AI-related projects

Anything-3D. Segment-Anything + 3D. Let's lift anything to 3D.

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

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

GPTCache. Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

GroundingDINO. [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

PAIR-Diffusion. [CVPR 2024] PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor

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.

FytHWOneKey. App to modify the hardware buttons on FYT units (Sofia3GR/PX5/sc9853i/sc9863a/uis7862)

HRN. [CVPR2023] A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images.

awesome-python. 🐍 Hand-picked awesome Python libraries and frameworks, organised by category

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

prismer. The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".

navidrome. 🎧 Your Personal Streaming Service

CTranslate2. Fast inference engine for Transformer models

selfhosted-apps-docker. Guide by Example

nomic. Nomic Developer API SDK

gpt4all. GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

ToolJet. ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀

onedev. The Unified and Autonomous Development Platform

alpaca.cpp. Locally run an Instruction-Tuned Chat-Style LLM

typst. A markup-based typesetting system that is powerful and easy to learn.

textgen. Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

subsai. 🎞️ Subtitles generation tool (Web-UI + CLI + Python package) powered by OpenAI's Whisper and its variants 🎞️

viper. Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

ainodes-engine. Python

vanilla-llama. Plain pytorch implementation of LLaMA

alpaca-lora. Instruct-tune LLaMA on consumer hardware

learnopencv. Learn OpenCV : C++ and Python Examples

ultralytics. Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

hcaptcha-challenger. 🥂 Gracefully face hCaptcha challenge with multimodal large language model.

mgob. MongoDB dockerized backup agent. Runs schedule backups with retention, S3 & SFTP upload, notifications, instrumentation with Prometheus and more.

DeepFaceLive. Real-time face swap for PC streaming or video calls

sd-webui-cutoff. Cutoff - Cutting Off Prompt Effect

Stable-Diffusion-Webui-Civitai-Helper. Stable Diffusion Webui Extension for Civitai, to manage your model much more easily.

kaolin. A PyTorch Library for Accelerating 3D Deep Learning Research

3d-photo-inpainting. [CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

dmt-meshes. Python

stylegan-t. [ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

clip-retrieval. Easily compute clip embeddings and build a clip retrieval system with them

pose-classification-kit. 🤙 Hand and body gesture classifier tool - Creation of datasets, real-time visualization, and processing pipeline deployment!

SkinToneClassifier. An easy-to-use library for skin tone classification

hora. 🚀 efficient approximate nearest neighbor search algorithm collections library written in Rust 🦀 .

txtai. 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

sd-webui-depth-lib. Depth map library for use with the Control Net extension for Automatic1111/stable-diffusion-webui

ImageAI. A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

facetorch. Python library for analysing faces using PyTorch

DashboardPlusPlus. Demonstrating the Dashboard++ method of organizing a vault in Obsidian

digital-gardeners. Resources, links, projects, and ideas for gardeners tending their digital notes on the public interwebs

Second-Brain. A curated list of awesome Public Zettelkastens 🗄️ / Second Brains 🧠 / Digital Gardens 🌱

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

sd-tagging-helper. Python

evue. Evue is a high-performance gui framework base an html/css which can run on windows/linux/macos/web/ios/andriod/rtos! Write once, run everywhere! .

kohya_ss. Python

my-flet. Codes I wrote with the Flet library

flet-cheatsheet. Flet code snippets and patterns to boost productivity

flet-hacks. Quick, dirty hacks with Flet / Flutter. Improvising innovation

blip2_8bit. BLIP-2 Captioning with 8-bit Quantization

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

captionr. GIT/BLIP/CLIP Caption tool

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

letsencrypt-docker-compose. Set up Nginx and Let’s Encrypt in less than 3 minutes with a Docker Compose project that automatically obtains and renews free Let's Encrypt SSL/TLS certificates and sets up HTTPS in Nginx for multiple domain names. Configuration is done using a simple CLI tool.

ngman. A lightweight abstraction layer around nginx and lego

SonyHeadphonesClient. A {Windows, macOS, Linux} client recreating the functionality of the Sony Headphones app

A1111-Web-UI-Installer. Complete installer for Automatic1111's infamous Stable Diffusion WebUI

OpenPose-to-Blender-Facial-Capture-Transfer. This blender Python Script maps an OpenPose Facial Capture to a blender facial Rig

sd-tagging-helper. A GUI to help with manual tagging and cropping

openpose. OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

clip-interrogator. Image to prompt with BLIP and CLIP

flet. Build realtime web, mobile and desktop apps in Python only. No frontend experience required.

Crop-CLIP. Crop using CLIP

StableTuner. Finetuning SD in style.

litestar. Light, flexible and extensible ASGI framework | Built to scale

ColossalAI. Making large AI models cheaper, faster and more accessible

waifu-diffusion. stable diffusion finetuned on weeb stuff

ripgrep-all. rga: ripgrep, but also search in PDFs, E-Books, Office documents, zip, tar.gz, etc.

ocrpy. OCR, Archive, Index and Search: Implementation agnostic OCR framework.

carefree-creator. AI magics meet Infinite draw board.

novelai-aspect-ratio-bucketing. Implementation of aspect ratio bucketing for training generative image models as described in: https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac

Constrained-Text-Generation-Studio. Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)

TabPFN. ⚡ TabPFN: Foundation Model for Tabular Data ⚡

StylePile. A prompt generation helper script for AUTOMATIC1111/stable-diffusion-webui and compatible forks

TLC. Test-time Local Converter

chaiNNer. A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.

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

stable-diffusion. Jupyter Notebook

stable-diffusion-aesthetic-gradients. Personalization for Stable Diffusion via Aesthetic Gradients 🎨

marqo. Ecommerce Search and Discovery - marqo.ai

GET3D. Python

TabularEditor. This is the code repository and issue tracker for Tabular Editor 2.X (free, open-source version). This repository is being maintained by Daniel Otykier.

examples. Deep Learning Examples

baklavajs. Graph / node editor in the browser using VueJS

ripme. Downloads albums in bulk

Zero-DCE. Zero-DCE code and model

awesome-low-light-image-enhancement. This is a resouce list for low light image enhancement

KinD_plus. Beyond Brightening Low-light Images

InvokeAI. Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

stylegan3-fun. Modifications of the official PyTorch implementation of StyleGAN3. Let's easily generate images and videos with StyleGAN2/2-ADA/3!

dbdiagram-oss. Open-Source Implementation of the great dbdiagram.io