Open-source alternatives to OpenGlass

Mimiclaw is a framework for integrating large language models with microcontroller hardware to create interactive AI agents. It provides an embedded AI agent runtime and a tool-calling engine that allows language model loops to execute on embedded devices. The system acts as a bridge between language model APIs and physical hardware peripherals, enabling the control of sensors and actuators through natural language. The project features a dedicated manager for over-the-air firmware updates, allowing system images to be installed via web browsers or wireless networks to remove local toolchain

LLaMA-Adapter is a parameter-efficient fine-tuning framework designed to adapt large language models using a minimal set of trainable parameters. It functions as an instruction tuning tool and a multimodal adapter, allowing pre-trained models to follow human instructions and process non-textual data. The project specializes in the integration of image, video, audio, and sensor data into language models for cross-modal understanding. It enables the customization of LLaMA models through the use of lightweight adapters, which allows for the extraction and storage of learned weights independently

zero_nlp is a distributed framework for training and fine-tuning large language models and multimodal architectures. It provides a specialized toolkit for distributed model parallelism, allowing neural network layers and weights to be partitioned across multiple GPU devices to train models that exceed the memory capacity of a single processor. The project distinguishes itself through a combination of high-throughput data pipelines and parameter-efficient tuning. It utilizes multi-threading and memory mapping to preprocess and stream datasets exceeding 100GB and implements memory-saving adapta

TaskMatrix is a visual language model orchestration framework and modular visual pipeline designed to coordinate disparate foundation models. It functions as a multi-model workflow coordinator that sequences visual and textual models through logic paths to handle image processing tasks without requiring additional training. The system integrates large language models with visual foundation models to enable the exchange of image data during interactive chat sessions. It utilizes template-based orchestration to chain specialized models together for complex visual tasks. The framework supports

RT-DETR is a real-time object detection model based on the detection transformer architecture. It is implemented as a computer vision model for both the PyTorch and PaddlePaddle deep learning platforms, designed to identify and locate multiple objects in images and video streams. The model eliminates the need for anchor generation and non-maximum suppression by utilizing a transformer-based approach. It focuses on high-performance detection, balancing precision and low latency for live environment deployment. The system employs a hybrid encoder and multi-scale feature fusion to extract globa

YOLOv9 is a real-time computer vision framework and deep learning model designed for image classification, object detection, and instance segmentation. It functions as both a vision model and a trainer, allowing for the optimization of neural network weights on custom datasets using single or multiple GPUs. The framework utilizes programmable gradient information to perform high-speed identification and location of multiple objects within images and video streams. It extends beyond bounding box detection to provide instance segmentation and panoptic segmentation, which labels every pixel in a

This application is a real-time computer vision system designed to identify and label objects within live video feeds, recorded files, and static images. It functions as a comprehensive framework that integrates pre-trained machine learning models with video processing pipelines to perform multi-object localization and visual data tracking. The system distinguishes itself through a multithreaded architecture that decouples frame acquisition from detection logic, ensuring the interface remains responsive during continuous analysis. It provides specialized scripts for training and optimizing cu

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

YOLOv7 is a PyTorch vision library and real-time inference engine designed for object detection, human pose estimation, and instance segmentation. It provides a framework for detecting and locating multiple objects within images or video streams using neural networks. The system includes tools for custom model training and fine-tuning, allowing pre-trained weights to be adapted to specialized datasets via transfer learning. It also supports model weight export and format conversion to facilitate deployment on production servers and embedded edge devices.

This project is an automated image translation system and pipeline specifically optimized for manga and comics. It provides a sequence of text detection, machine translation, and typesetting, and is available as an image translation API, a command-line tool for batch processing, and an LLM-powered translator. The system utilizes OCR to detect text regions and an inpainter to remove original content by synthesizing background pixels. Translated text is then overlaid using an automated typesetter that manages font sizes, colors, and reading directions based on the original coordinates. The wor

This project is a PyTorch implementation of the YOLOv4 object detection framework. It provides a system for training and deploying neural networks that identify and locate multiple objects within images and video streams. The framework includes tools for converting trained weights into universal formats and hardware-specific optimized engines, specifically supporting ONNX and TensorRT. It features a TensorRT inference optimizer to reduce latency and increase throughput, as well as a model architecture compatible with NVIDIA DeepStream streaming analytics pipelines. The system covers model tr

This project is a PyTorch implementation of the YOLOv3 object detection architecture. It functions as a real-time object detector and computer vision framework designed to identify and locate multiple objects within images using bounding boxes and class labels. The system allows for both the use of pretrained weights for immediate image analysis and the training of custom models using datasets with bounding box annotations. It provides a programmatic interface to integrate detection capabilities directly into other software applications. The framework includes tools for model evaluation to m

Darknet is a high-performance C-based inference engine and computer vision library designed for real-time object identification and localization. It serves as a neural network framework for training and deploying detection models using the YOLO architecture, providing a toolset for deep learning training and deployment. The project differentiates itself through a C and CUDA implementation that enables hardware acceleration for matrix multiplication and inference speed optimization. It provides a shared library interface for embedding detection capabilities into external applications and suppo

This project is a PyTorch implementation of the EfficientDet architecture designed for real-time object detection. It provides a neural network and inference engine capable of identifying and locating multiple objects within images or video streams. The implementation includes pretrained computer vision models with optimized weights, enabling immediate inference and fine-tuning without the need for training from scratch. The project covers the full pipeline for computer vision model optimization, including custom object detection training and model weight optimization. It incorporates struct

Dango-Translator is an OCR translation system and multi-engine translation client designed to extract text from images or screens and replace it with translated content. It functions as an image text translator and real-time screen translator, utilizing optical character recognition to convert text between different languages automatically. The software distinguishes itself through coordinate-based image typesetting and a glossary manager. These tools allow for the replacement of original image content with translated text in the same area and the use of specialized dictionaries to ensure con

YOLOv5 is a comprehensive computer vision framework designed for end-to-end deep learning, specializing in real-time object detection, image classification, and instance segmentation. It provides a unified toolkit that manages the entire lifecycle of a model, from initial dataset configuration and hyperparameter tuning to high-speed inference and deployment. The framework utilizes a modular neural architecture, allowing users to swap backbone and head components to tailor models for specific visual tasks. What distinguishes this project is its focus on production-ready deployment and model ef

Betaflight is open-source flight controller firmware designed to stabilize aircraft and manage sensor data through PID loops and motor control. It serves as a multirotor flight stack that integrates low-level drivers and control algorithms to manage electronic speed controllers, radio receivers, and telemetry hardware. The system focuses on real-time flight stabilization and telemetry routing. It includes a PID stabilization system to calculate motor outputs for aircraft stability and a flight telemetry manager to route real-time information to ground stations and on-screen displays. The fir

FairMOT is a multi-object tracking framework and deep learning model designed to identify and track multiple entities across video frames. It implements a unified pipeline that integrates object detection and identity re-identification into a single-stage joint network. The system utilizes an anchor-free detection method to predict object centers and bounding box dimensions. It maintains identity consistency across consecutive frames by generating high-dimensional embedding vectors for re-identification and employing a Kalman filter for motion state prediction. The framework covers a broad r

LazyLLM is a multi-agent framework and orchestration engine designed for building complex AI applications. It provides a system for chaining large language models into sequential or parallel pipelines, utilizing a tool registry to convert standard functions into discoverable tools that models can invoke via reasoning. The project features an application deployment kit that enables hosting model workflows as web services with integrated chat interfaces and API gateways. It includes an infrastructure abstraction layer that allows users to switch between bare-metal servers, clusters, and public

BallonsTranslator is a software suite designed for extracting, translating, and replacing text within comic panels while preserving the original visual layout. It functions as an image translation tool that combines text region detection, optical character recognition, and deep learning inpainting to automate the localization of comics. The tool features a deep learning image inpainter that removes original text and restores backgrounds using generative neural networks and patch-matching algorithms. It also includes a rich-text translation editor for modifying translated dialogue with support

GoCV is a computer vision library and Go language binding for OpenCV. It serves as an image processing toolkit and deep learning inference engine, providing programmatic access to a wide range of algorithms for image manipulation, object detection, and video analysis. The project differentiates itself through high-performance native bindings and hardware acceleration. It utilizes a foreign function interface to map Go calls to C++ functions and includes a hardware-agnostic backend dispatch to route neural network tasks to computation engines such as CUDA and OpenVINO. The library covers a br

This project is a multi-object tracking framework designed to assign persistent identities to detected bounding boxes across consecutive video frames. It functions as a computer vision tracking algorithm that monitors multiple moving targets in real time by associating detections with consistent labels. The system utilizes a state estimation approach centered on a Kalman filter to predict future object positions and maintain identity during detection gaps. It employs the Hungarian algorithm for optimal data association and calculates intersection over union to match predicted track locations

This project is a TensorFlow object detection framework designed for training and deploying Single Shot MultiBox Detector models. It provides a neural network training toolkit for implementing the SSD architecture to achieve real-time image and video object localization. The framework includes a dedicated data pipeline for transforming object detection datasets into binary record formats to increase training speed and performance. It also features utilities for converting model weights between different checkpoint formats to facilitate the reuse of pre-trained networks. The system covers a b

This project is a collection of research and tools for reverse engineering the hardware and communication protocols of Nintendo Switch consoles and controllers. It provides a comprehensive toolset for analyzing physical hardware interfaces, parsing controller communication protocols, extracting embedded firmware, and emulating input signals. The project focuses on decoding raw serial data and packets from controllers to extract input and sensor states. It includes capabilities for simulating hardware signals to send spoofed input data to the system console and extracting microcontroller softw

OpenCV is an open-source computer vision library and visual analysis toolkit. It provides a framework for processing static images and dynamic video frames to analyze visual data and extract information using deep learning. The project functions as a real-time image processing framework, enabling the execution of vision algorithms on live video streams for immediate analysis and data processing. The toolkit covers a broad range of capabilities including image pattern recognition, real-time video analysis, and visual data extraction. It also supports automated visual inspection for detecting

tracking.js is a browser computer vision library written in JavaScript for performing real-time image analysis and object tracking directly within a web browser. It functions as a real-time object tracker, a color tracking tool, and a face detection utility. The library enables the detection and monitoring of specific color ranges, human faces, and known visual patterns across consecutive video frames. It extracts visual features and descriptors from images to identify distinct landmarks for matching and tracking. The project covers broad computer vision capabilities, including the ability t

MediaPipe is a cross-platform machine learning framework designed for building and deploying pipelines that process live and streaming media. It provides a system for connecting processing components into custom machine learning chains to analyze real-time audio and video streams. The framework includes a suite of pre-trained models for tasks such as hand, face, and pose tracking, along with tools for retraining and customizing these models with specific datasets. It also features a dedicated benchmarker for measuring the execution speed and accuracy of machine learning models directly within