Open Source JavaScript Artificial Intelligence Software - Page 21
Sort By:
JavaScript Artificial Intelligence Software
View 17349 business solutionsBrowse free open source JavaScript Artificial Intelligence Software and projects below. Use the toggles on the left to filter open source JavaScript Artificial Intelligence Software by OS, license, language, programming language, and project status.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
neurojs
A JavaScript deep learning and reinforcement learning library
neurojs is a JavaScript framework designed to enable deep learning and reinforcement learning directly within web environments. The library provides a full machine learning framework implemented in JavaScript that can run inside browsers or Node.js environments. It focuses particularly on reinforcement learning algorithms, enabling developers to create intelligent agents that learn through interaction with simulated environments. The framework supports neural network architectures and reinforcement learning methods such as deep Q-networks and actor-critic algorithms. Several interactive demonstrations included with the project illustrate how neural networks can be used to train agents in simulated tasks, including a browser-based self-driving car example. These demos allow users to visualize how reinforcement learning agents improve their behavior over time as they receive rewards and update their neural networks. -
2
npati-content-automation
WordPress plugin for content planning, AI-assisted writing, social sch
NPATI Content Automation is a free WordPress plugin that combines editorial planning, AI-assisted content creation, social media scheduling, and NPATI marketplace workflows in one WordPress admin workspace. Plan and manage WordPress articles, import content tasks from CSV or XLSX, organize SEO keywords and publishing dates, and optionally generate content with your own OpenAI API key. The plugin also connects WordPress to NPATI Hub for supported social publishing and scheduling, and allows connected NPATI users to manage marketplace listings, videos, and Shorts. NPATI Content Automation is designed for website owners, bloggers, marketers, and businesses that want to manage more of their content workflow directly from WordPress. Official website: https://www.npati.com/plugins/npati-content-automation WordPress.org: https://wordpress.org/plugins/npati-content-automation/ Source code: https://github.com/andrii-koss/npati-content-automation -
3
ocrad.js
OCR in Javascript via Emscripten
Ocrad.js is a JavaScript port of the GNU Ocrad optical character recognition engine compiled with Emscripten. It brings text recognition directly into web applications without requiring a remote OCR service. Local processing can reduce network latency and support offline-capable applications. Possible uses include extracting text from images, browser-based note tools, image indexing, and experimental handwriting input. The repository includes the compiled library, source material, examples, a browser demo, and worker support. Its recognition engine is rule-based, so accuracy can vary substantially with character quality, spacing, weight, and input preparation. -
4
offyai
OffyAI — Local AI. Private by Design. Built for Your Machine.
OffyAI is a modern local-first AI desktop application that brings a ChatGPT-like experience to your computer while keeping your AI workloads close to you. It is designed for users who want to run, manage, and interact with local Large Language Models (LLMs) through a clean desktop interface without depending entirely on cloud-based AI services. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
NB: openDIAS is moving away from SF.net. Please visit the homepage link for the most update to date information, support and files. Document Imaging Archive System. Home document imaging, with OCR. Scan documents (with SANE) or import ODF documents, assign tags. Use openDIAS to store all our letters, bills, statements, etc in a convenient, safe and easily retrievable way.
-
6
openhealthpractice
A simulation environment for physiology models simulation
The OpenHealhPractice Simulation Environment is a web framework intended to concurrently manage and launch generalized models. Models can be uploaded by the users and also can be connected to other models in order to simulate them in a row. These simulations are stored and can be reviewed or deleted at anytime. The Graphical Visualization Environment (GVE) provides the graphical visualization of the simulation results. Results can also be exported to different formats (xls, txt or csv). This simulation environment is built using Spring Framework and Java technologies. For more information on how to deploy and use the tool, check the installation and user manuals. This tool was developed within the Synergy project. You can view our publication about the Simulation Environment here: http://www.translational-medicine.com/content/12/S2/S7 The rest of the publication outcomes of the project can be found here: http://www.translational-medicine.com/supplements/12/S2 -
7
openv0
AI tool for generating modular UI components with live previews
openv0 is a generative UI component framework designed to help developers create interface elements using AI-assisted workflows. It enables users to generate, iterate, and refine UI components with a live preview system, making it easier to visualize results during development. openv0 is built around a modular architecture, allowing different parts of the generation process to be extended or replaced through plugins. A key aspect of openv0 is its multipass pipeline, where each stage of component generation operates independently, enabling more complex and flexible transformations. It integrates with multiple frontend frameworks and UI libraries, leveraging existing open source ecosystems to build reusable assets. openv0 also supports various icon libraries and emphasizes extensibility for adding new tools, frameworks, and integrations. Although the project is no longer actively maintained, it demonstrates a structured approach to AI-driven UI generation and experimentation. -
8
pipeless
A computer vision framework to create and deploy apps in minutes
Pipeless is an open-source computer vision framework to create and deploy applications without the complexity of building and maintaining multimedia pipelines. It ships everything you need to create and deploy efficient computer vision applications that work in real-time in just minutes. Pipeless is inspired by modern serverless technologies. It provides the development experience of serverless frameworks applied to computer vision. You provide some functions that are executed for new video frames and Pipeless takes care of everything else. You can easily use industry-standard models, such as YOLO, or load your custom model in one of the supported inference runtimes. Pipeless ships some of the most popular inference runtimes, such as the ONNX Runtime, allowing you to run inference with high performance on CPU or GPU out-of-the-box. You can deploy your Pipeless application with a single command to edge and IoT devices or the cloud. -
9
pixelmatch
The smallest, simplest JavaScript pixel-level image comparison library
The smallest, simplest and fastest JavaScript pixel-level image comparison library, originally created to compare screenshots in tests. Features accurate anti-aliased pixels detection and perceptual color difference metrics. Inspired by Resemble.js and Blink-diff. Unlike these libraries, pixelmatch is around 150 lines of code, has no dependencies, and works on raw typed arrays of image data, so it's blazing fast and can be used in any environment (Node or browsers). Compares two images, writes the output diff and returns the number of mismatched pixels. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
10
pump-fun-skills
This repo contains pump fun skills for AI agents
pump-fun-skills is a repository that provides a collection of predefined “skills” or modules designed for use with AI agents in the pump.fun ecosystem. These skills represent reusable capabilities that agents can execute, enabling more structured and modular behavior. The project focuses on expanding the functionality of agents by providing ready-to-use components that can be combined into larger workflows. It supports customization, allowing developers to adapt or extend skills to meet specific requirements. The repository is particularly useful for developers building agent-based systems who want to accelerate development by reusing existing logic. It emphasizes modularity and composability, making it easier to build complex systems from smaller parts. Overall, pump-fun-skills serves as a library of building blocks for agent-based applications. -
11
read chung is a small txt reader with multilingual tts text to speech voices from responsivevoice and yandextranslate and animated 3D face avatar written in html5 , javascript and uses jsc3D .
-
12
retina.js
JavaScript helpers for rendering high-resolution image variants
retina.js makes it easy to serve high-resolution images to devices with displays that support them. You can prepare images for as many levels of pixel density as you want and let retina.js dynamically serve the right image to the user. retina.js assumes you are using Apple's prescribed high-resolution modifiers (@2x, @3x, etc) to denote high-res image variants on your server. It also assumes that if you have prepared a variant for a given high-res environment, that you have also prepared variants for each environment below it. For example, if you have prepared 3x variants, retina.js will assume that you have also prepared 2x variants. If the environment does have 3x capabilities, retina.js will serve up the 3x image. It will expect that url to be /images/my_image@3x.png. If the environment has the ability to display images at higher densities than 3x, retina.js will serve up the image of the highest resolution that you've provided, in this case 3x. -
13
riscordbot
Discordbot which will keep track of Risk: Global Domination Matches.
This discordbot will be available to all servers who are hosting Risk tournaments, so there is an easy and centralised way to track statistics for players, scores, tournament settings, and much more data that will be nicely output into a userfriendly environment (being plaintext data structured to be viewed in discord-chat, twitch-chat or via a nice designed website.) -
14
sentiment
AFINN-based sentiment analysis for Node.js
Sentiment is a simple and lightweight sentiment analysis tool for Node.js that evaluates the polarity of text by scoring words based on positive and negative sentiment. -
15
tmi.js
Javascript library for the Twitch Messaging Interface
Connect to and interact with Twitch chat (IRC) from Node.js or a browser. Control the delay in milliseconds between JOIN requests when using the channels array option. Minimum of 300 milliseconds. If the identity has special permission from Twitch for a higher join rate then you should implement your own calls to the client.join method. Disable receiving JOIN/PART events for other users. Good for decreasing network traffic when joining lots of channels or you don't care about this data. After a threshold per channel Twitch stops sending this data so it may not be necessary for all cases. Channels to automatically join upon connecting. The rate of joins is controlled by the options.joinInterval option. Automatically reconnect the client if it gets disconnected for any reason. Sometimes Twitch will request the client to reconnect and tmi.js will disconnect and reconnect even if this option is set to false. -
16
tracking.js
A modern approach for Computer Vision on the web
The tracking.js library brings different computer vision algorithms and techniques into the browser environment. By using modern HTML5 specifications, we enable you to do real-time color tracking, face detection and much more, all that with a lightweight core (~7 KB) and intuitive interface. To get started, download the project. This project includes all of the tracking.js examples, source code dependencies you'll need to get started. Unzip the project somewhere on your local drive. The package includes an initial version of the project you'll be working with. While you're working, you'll need a basic HTTP server to serve your pages. Test out the web server by loading the finished version of the project. The main goal of tracking.js is to provide those complex techniques in a simple and intuitive way on the web. We believe computer vision is important to improve people's life, bringing it to the web will make this future a reality a lot faster. -
17
voice-elements
Web Component wrapper to the Web Speech API
voice-elements is a set of Web Components that wraps the Web Speech API to make speech synthesis (text-to-speech) and speech recognition (speech-to-text) easy to use via simple HTML tags. Instead of manually dealing with JavaScript APIs like SpeechSynthesis and SpeechRecognition, developers can drop custom elements such as <voice-player> and <voice-recognition> into their markup and configure them with attributes. Built originally with Polymer, it follows the early Web Components ecosystem patterns, integrating custom elements, templates, and data binding. The project includes demos that show how to autoplay spoken text or start listening for voice commands when the element loads, helping developers quickly grasp usage. Because it is based on the browser’s native Web Speech API, it does not require external services, although support can vary across browsers. voice-elements is particularly handy for prototypes, educational projects, and small apps. -
18
vue-tetris
Use Vue, Vuex to code Tetris
vue-tetris is a browser-based implementation of the classic Tetris game built using the Vue.js framework, showcasing both game development concepts and modern frontend engineering practices. The project demonstrates how reactive state management and component-based architecture can be used to create interactive and dynamic applications. It includes core gameplay mechanics such as piece rotation, collision detection, line clearing, and score tracking, all implemented within a clean and modular codebase. The design emphasizes performance and responsiveness, ensuring smooth gameplay even within a web environment. It also serves as an educational resource for developers learning Vue.js, illustrating how to structure real-time applications. The project may include additional features such as keyboard controls, game speed adjustments, and visual styling. Overall, vue-tetris combines entertainment with practical frontend development techniques. -
19
web-access
Skill for installing full networking capabilities for Claude Code
web-access is a tool designed to give AI agents structured and controlled access to web content, enabling them to retrieve, navigate, and process information from online sources in real time. It abstracts common web interactions such as page loading, data extraction, and navigation into reusable functions that can be invoked by agents. The system emphasizes safety and control, likely including mechanisms to manage permissions, rate limits, and content filtering. This allows agents to operate within defined boundaries while still benefiting from dynamic, up-to-date information. The architecture supports integration with broader agent frameworks, making it a key component for building systems that require external knowledge. It is particularly useful for tasks like research, monitoring, and automated data collection. Overall, web-access extends the capabilities of AI agents by connecting them to the live web in a structured and reliable way. -
20
xgplayer
A HTML5 video player with a parser that saves traffic
xgplayer is a web-friendly, open-source media player library maintained by ByteDance, designed for playing audio/video streams in browsers or web applications with robust control, flexibility, and extensibility. It abstracts many of the lower-level complexities of HTML5 media, providing a consistent API for playback control, custom UI overlays, adaptive streaming, plugin hooks, and cross-browser compatibility. Because of its emphasis on modularity and extensibility, xgplayer can be embedded into modern web projects and customized — developers can add controls, custom buffering strategies, subtitle handling, adaptive bitrate streaming, or integrate with other web-based video infrastructures. It seeks to provide a smooth, stable viewing experience even on varied devices or network conditions, and is particularly appealing for web apps that need more control than vanilla video tags offer. -
21
CrimeFighter is the website of a gta-like browser game with rpg and multiplayer parts. Moreover you can see yourself running around in the city in realtime. Never seen such a online game? Just visit http://www.crimefighter.de
