Open-source alternatives to Mlkit

LiteRT-LM is a high-performance inference framework designed to execute large language models locally on mobile, desktop, and IoT hardware. It serves as an on-device model runtime that utilizes CPU, GPU, and NPU acceleration to provide low-latency processing. The framework is distinguished by its ability to process text, vision, and audio inputs through a single multi-modal inference engine. It features a local HTTP server that emulates OpenAI-compatible API endpoints and a WebGPU-based runtime for executing models directly within a web browser. To ensure output reliability, it includes a con

AI-on-the-edge-device is an edge AI meter digitizer and computer vision image processor designed to convert images of analog and digital utility meters into numeric values. It functions as an IoT gateway that runs neural network inference locally on hardware to monitor water, power, and gas readings. The system is distinguished by its ability to handle both analog pointers and digital digits through custom-trained neural networks. It includes specialized tools for image alignment, region-of-interest extraction, and hardware-level lighting control to minimize glare on glass surfaces. To mainta

Moonshine is a complete on-device voice interface toolkit that provides speech recognition, text-to-speech synthesis, phonetic processing, speaker diarization, and intent recognition, all running locally on edge hardware without any cloud dependency. It executes quantized neural networks for speech and language tasks directly on the device, enabling fully offline conversational AI capabilities. The toolkit distinguishes itself by orchestrating multi-turn spoken exchanges through a conversational flow manager that maintains context across interactions and manages branching dialog flows. It inc

Local-File-Organizer is a local-first file classification system that uses on-device machine learning models to categorize documents and media into structured directories. It functions as an automated file classifier and asset manager that leverages local inference to sort files based on content, meaning, and metadata. The project emphasizes privacy by performing all data processing and analysis on the local device, eliminating the need to send sensitive files to external cloud services. It utilizes local models to analyze text and image content to generate descriptive filenames and thematic

AidLearning-Framework is an integrated development platform for building and deploying AI applications on ARM-based devices. It combines Android and Linux operating systems running simultaneously on a single device, providing a unified runtime environment for cross-system AI development. The platform includes hardware acceleration across CPU, GPU, and NPU, with a unified API that automatically selects the optimal compute backend for inference. The framework distinguishes itself by enabling Python-based AI projects to be packaged directly into Android APK files for installation on mobile devic

ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,

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

gemma.cpp is a C++ inference engine for Gemma, PaliGemma, and Griffin language models, designed to run directly on-device without Python dependencies. It provides a self-contained runtime that loads quantized model weights and performs text generation on CPU or GPU, along with a model checkpoint converter that transforms PyTorch or Keras checkpoints into a compact binary format for fast loading. The engine supports multiple model architectures, including the Griffin recurrent architecture with gated linear recurrent layers and sliding-window attention for efficient long-sequence handling, as

Porcupine is an on-device wake word detection engine that listens for a specific spoken phrase in real-time audio and triggers actions, all processed locally without any cloud connectivity. It includes a custom wake word model creator that generates production-ready models from just a few spoken examples in seconds, requiring no training data. Beyond wake word detection, Porcupine also provides on-device speech recognition for real-time transcription with custom vocabulary, an on-device audio content searcher that indexes and finds spoken phrases in audio files or streams, and a lightweight vo

The nexa-sdk is an on-device AI SDK and multimodal inference engine designed to run large language, vision, and audio models locally on mobile and desktop hardware. It functions as a local LLM runtime and NPU acceleration framework, enabling the execution of generative and discriminative models without reliance on cloud services. The project distinguishes itself through a dedicated NPU acceleration framework that optimizes model execution on Neural Processing Units to reduce latency and power consumption. It employs hardware-agnostic backend routing to dynamically distribute computations acro

A collection of reference implementations and code samples for integrating Android camera hardware and software APIs. The project provides demonstrations for using both the Jetpack CameraX library and the low-level Camera2 API to implement photo and video capture features. The repository includes specialized implementations for high-performance recording, such as high-frame-rate slow motion and high-dynamic-range video. It also features examples of machine learning vision, demonstrating how to analyze live camera frames for object detection and QR code scanning. The project covers broad imag

LiteRT is a runtime and API for executing machine learning and generative AI models on mobile, desktop, and IoT hardware. It consists of an inference engine and a specialized environment for running quantized large language and diffusion models locally on edge hardware. The system includes an ahead-of-time model compiler that translates models into hardware-specific bytecode to reduce startup latency and memory overhead. It provides a unified interface for Neural Processing Units with automatic fallback routing to CPUs or GPUs when specific subgraph support is unavailable. An edge model conve

Deeplearnjs is a JavaScript deep learning framework and automatic differentiation engine designed for building and training artificial intelligence models within a web browser environment. It functions as a machine learning library that leverages WebGL to provide hardware acceleration for neural networks. The project serves as a high-performance linear algebra library, using the GPU to execute operations on multi-dimensional arrays. This enables the implementation of deep learning models and the execution of client-side machine learning inference. The framework covers the complete automatic

Paddle is a deep learning framework designed for building, training, and deploying large-scale machine learning models. It incorporates a distributed training engine for optimizing performance across multiple chips and a model inference engine for transforming trained models into production-ready formats for cross-platform execution. The platform features a heterogeneous hardware abstraction and a standardized software stack that allows models to run across diverse hardware architectures through a common interface. It also includes a scientific computing library capable of solving complex dif

OpenCV-Face-Recognition is a computer vision system designed to detect human faces and verify identities within live video streams and static images. It functions as a Python-based toolkit that processes visual data to locate facial boundaries and match detected features against a pre-trained database of profiles. The system utilizes a structured computer vision pipeline that integrates object detection with statistical analysis to perform identity verification. It employs pre-trained classifiers to scan for facial patterns and encodes facial textures into binary histograms to create represen

TengineKit is a mobile computer vision software development kit designed for real-time inference on local hardware. It functions as a neural network engine that executes deep learning models directly on mobile devices, enabling applications to perform complex visual analysis without relying on cloud connectivity. The framework provides specialized tools for detecting and tracking human features, including faces, hands, bodies, and irises, alongside general object detection capabilities. By utilizing a native core runtime and hardware-accelerated execution, the library processes visual data lo

Noctalia Shell is a modular Wayland desktop shell that provides a user interface consisting of status bars, launchers, and notifications for Wayland compositors. It is built as a plugin-based desktop environment that utilizes declarative configuration for managing system defaults, wallpapers, and plugin installations. The project features a dynamic desktop theming engine that extracts color palettes from wallpapers to theme the shell and external applications. This is supported by an inter-process communication bridge that exposes endpoints, allowing external scripts and keybindings to trigge

Lite XL is a lightweight, cross-platform text editor built around a minimal C core that embeds a Lua interpreter, allowing the entire editor interface and functionality to be scripted and customized through Lua. It draws text and UI elements directly to a pixel buffer using a single-threaded event loop, bypassing heavyweight widget toolkits to keep the editor fast and responsive even on low-resource hardware. The editor distinguishes itself through its Lua-based plugin architecture and file-based configuration system, where settings, keybindings, and plugin metadata are stored as plain Lua fi

Flight is a JavaScript component framework and DOM interactivity library used to map behavioral logic to HTML nodes. It provides an event-driven architecture for building modular user interface elements and managing web application interactivity. The library distinguishes itself through a mixin-based system for injecting reusable functions and properties into components, promoting code reuse without rigid inheritance. It further enables behavior modification via function hooking, allowing developers to wrap existing methods to inject custom logic without altering the original source code. Th

This project is a comprehensive library and toolkit for simultaneous localization and mapping, designed to construct three-dimensional environment models while tracking device position. It functions as a robotics perception framework that processes data from RGB-D, stereo, and lidar sensors to enable autonomous navigation and spatial awareness. The system distinguishes itself through its focus on long-term mapping and global consistency. It employs a sophisticated loop-closure detection engine and graph-based pose optimization to identify previously visited locations and eliminate cumulative

This project is an AI model quota monitoring and management tool for development environments. It provides a centralized interface for tracking remaining request limits, managing multiple authorized API accounts, and orchestrating AI service access. The system synchronizes quota reset cycles and automates model activation through scheduled tasks. It enables the inspection of large language model capabilities, such as context window sizes and supported input types, while allowing models to be clustered into groups based on shared service categories. Real-time usage data is delivered through a

ModernFlyouts is a Windows UI customization tool and system flyout replacer. It provides a set of Fluent Design overlays that replace legacy operating system notifications for volume, brightness, and network connectivity. The project functions as a media control interface and overlay manager, offering extended audio playback tools such as shuffle, repeat, and playback timelines. It uses a visual layer with transparency and contrast support to modify the appearance and behavior of system-level overlays. The software includes capabilities for flyout appearance and behavior management, allowing

d3-cloud is a JavaScript library for creating non-overlapping word cloud layouts using the D3.js data visualization framework. It serves as a text visualization tool that converts raw text or CSV data into scalable vector graphics and stylized typographic clouds. The library utilizes a spiral-based collision layout algorithm to compute coordinates and rotations, ensuring that words within a visual cluster do not overlap. It maps word frequency to font size and supports a customized layout process where positions are calculated based on text distribution. The system covers data processing for

Koala is a graphical user interface for managing the compilation, transpilation, and background monitoring of web asset preprocessors. It serves as a build tool that converts Less, Sass, and CoffeeScript files into browser-compatible CSS and JavaScript. The application features a visual interface for controlling the transformation process, removing the need for command line interaction. It integrates a background file monitor that automatically recompiles source files in real time as changes are detected on the local filesystem. The tool provides utilities for managing global and project-spe

This project is an open-source video production suite and non-linear video editor. It provides a multi-track timeline for cutting, splicing, and arranging video and audio clips with frame-level precision, serving as a comprehensive workspace for video post-production. The suite includes specialized tools for keyframe animation, allowing for the creation of 2D and 3D visual effects and motion graphics. It also features a multi-track audio mixer for blending sound sources and adjusting levels to accompany visual content. Capability areas cover a full post-production workflow, including color c