Search Results for "vision"
Sort By:
Showing 28 open source projects for "vision"
View related business solutions-
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.
-
$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.
-
1
Computer Vision Annotation Tool (CVAT)
Interactive video and image annotation tool for computer vision
Computer Vision Annotation Tool (CVAT) is a free and open source, interactive online tool for annotating videos and images for Computer Vision algorithms. It offers many powerful features, including automatic annotation using deep learning models, interpolation of bounding boxes between key frames, LDAP and more. It is being used by its own professional data annotation team to annotate millions of objects with different properties. -
2
Claude Code Video Vision
Give Claude the ability to watch and understand videos
Claude Video Vision is a plugin designed for Claude Code that enables large language models to process and understand video content by transforming it into multimodal inputs the model can reason over. Instead of attempting to directly interpret raw video streams, the system extracts key frames using tools like ffmpeg and processes audio through transcription engines, converting both visual and auditory signals into structured inputs for the model. -
3
draw-a-ui
Draw wireframe sketches and generate HTML with AI vision models
draw-a-ui is an experimental open source application that converts hand-drawn interface wireframes into working HTML code using artificial intelligence. draw-a-ui combines the tldraw canvas drawing tool with a vision-capable language model to interpret user-created mockups and translate them into a single HTML layout styled with Tailwind CSS. When a user sketches a UI on the canvas, the application captures the current drawing as SVG, converts it into a PNG image, and sends that image to a vision model that generates the corresponding markup. ... -
4
Midscene
Vision-based AI framework for cross-platform UI automation tasks
Midscene.js is an open source AI-driven UI automation framework designed to control user interfaces across multiple platforms using natural language instructions. Instead of relying on traditional selectors, DOM structures, or accessibility attributes, it uses a vision-first approach where screenshots are analyzed by visual-language models to identify interface elements and perform actions. It allows developers to automate interactions on web applications, desktop software, and mobile devices without needing platform-specific automation logic. Developers can describe tasks such as clicking buttons, filling forms, or extracting information, and the system interprets these commands to interact with the interface accordingly. ... -
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
5
Magnitude
Vision AI browser agent for automation, testing, and extraction
Browser Agent by Magnitude is an open source, vision-first browser automation framework that enables users to control web interfaces using natural language instructions. It leverages visually grounded AI models to interpret and interact with web pages based on what is seen on the screen rather than relying solely on the DOM structure. This approach allows the agent to generalize better across complex and modern websites, making it more robust than traditional selector-based automation tools. ... -
6
Maths, CS & AI Compendium
Become a cracked AI/ML Research Engineer
...It favors intuition, practical context, and connected explanations over dense textbook notation. Its chapters cover vectors, matrices, calculus, statistics, probability, machine learning, language processing, computer vision, speech, multimodal learning, robotics, and graph neural networks. It also addresses operating systems, algorithms, production software, GPU programming, AI inference, and ML systems design. Readers need only elementary mathematics and basic Python knowledge to begin. A bundled MCP server lets compatible AI assistants use the locally cloned compendium as a knowledge base. ... -
7
UI-TARS Desktop
A GUI Agent app based on UI-TARS to control your computer using AI
UI-TARS Desktop is a graphical user interface (GUI) agent application that leverages the UI-TARS vision-language model to enable natural language control of computers. This cross-platform tool supports both Windows and macOS, allowing users to perform tasks through intuitive commands. Key features include screenshot-based visual recognition, precise mouse and keyboard control, and real-time feedback on actions. Provides immediate responses and visual feedback on actions performed. ... -
8
Portkey AI Gateway
A blazing fast AI Gateway with integrated guardrails
...It supports automatic retries, fallbacks, load balancing across providers or keys, and request timeouts to avoid latency spikes. The gateway is multimodal: it can handle text, vision, audio, and image models under a common interface. It also offers features for governance: role-based access, compliance with standards (SOC2, HIPAA, GDPR), secure key management, and logging/analytics of usage, latency, errors, and cost. The system integrates with agent frameworks like LangChain, Autogen, and others, enabling the building of more complex AI applications. ... -
9
Design OS
The missing design process between your product idea and your codebase
Design OS is an open-source product planning and UI design framework that sits at the intersection of design thinking and generative AI, guiding creators through a repeatable process from product idea to structured design deliverables. It fills what the maintainers describe as the “missing design process” in AI-first development, helping users define product visions, model data, map user flows, and lay out interfaces before a coding agent begins implementation. The tool is poised to produce... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
React ChatBotify
A modern React library for creating flexible and extensible chatbots
...Whether you're aiming to create a simple FAQ bot or a sophisticated conversational interface integrated with Large Language Models (LLMs), React ChatBotify provides the tools and flexibility you need to bring your vision to life. -
11
Hollama
A minimal LLM chat app that runs entirely in your browser
Hollama is a lightweight open-source chat application designed to run entirely within the browser while interacting with large language model servers. The project provides a minimal but powerful user interface for communicating with local or remote LLMs, including servers powered by Ollama or OpenAI-compatible APIs. Because the application runs as a static web interface, it does not require complex backend infrastructure and can be easily deployed or self-hosted. Hollama supports both... -
12
Chat UI
The open source codebase powering HuggingChat
Hugging Face Chat UI is an open-source web interface designed for interacting with large language models through a modern conversational interface. The project serves as the codebase behind HuggingChat and can be deployed locally or on cloud infrastructure to create customizable AI chat applications. Built with modern web technologies such as SvelteKit and backed by MongoDB for persistence, the interface provides a responsive environment for multi-turn conversations, file handling, and... -
13
Helm Dashboard
The missing UI for Helm - visualize your releases
Helm Dashboard is an open-source project which offers a UI-driven way to view the installed Helm charts, see their revision history and corresponding k8s resources. It also allows users to perform simple actions such as rolling back to a revision or upgrading to a newer version. This project is part of Komodor's vision to help Kubernetes users to navigate and troubleshoot their clusters. It is important to note that Helm Dashboard is NOT an official project by the helm team. -
14
react-native-fast-tflite
High-performance TensorFlow Lite library for React Native
...It can load and swap TensorFlow Lite models at runtime, making it useful for apps that run multiple machine learning tasks. The project supports GPU-accelerated delegates such as CoreML, Metal, and OpenGL. It is especially useful for mobile computer vision, on-device inference, and VisionCamera-based workflows that need fast local model execution. -
15
Obsidian Local GPT
Local Ollama and OpenAI-like GPT's assistance for maximum privacy
Obsidian Local GPT is a plugin that embeds AI assistance directly into the Obsidian knowledge management environment while prioritizing privacy and local execution. It supports both local models through Ollama and OpenAI-compatible APIs, allowing users to choose between fully offline workflows or hybrid setups. The plugin introduces an “Action Palette” system that enables users to run predefined or custom AI-powered actions on selected text, notes, or entire documents. It integrates deeply... -
16
litlyx
Analytics for developers, setup Analytics in 30 seconds
...The brand emphasizes sustainability by reducing single-use plastics and promoting long-term use of their products. Their cleaning kit is compact, portable, and designed to be effective for everyday use, ensuring that users can maintain clear vision without the hassle of disposable wipes or sprays. -
17
superfluid protocol-monorepo
Superfluid protocol specification, implementations and development kit
...Create, modify or close streams in a single interface, even if the stream was started on other applications. The Superfluid Protocol is a framework that realizes the real-time finance vision where user accounts are connected together, and transactions can happen between user accounts instantaneously as a result. This repository implements the superfluid protocol as Ethereum contracts. It also contains a Javascript SDK for developing Web3 applications using the superfluid protocol. -
18
Page Agent
JavaScript in-page GUI agent. Control web interfaces
Page Agent is an open-source in-page AI agent framework that allows developers to control and interact with web interfaces using natural language directly within the browser. Unlike traditional browser automation tools, it operates entirely through in-page JavaScript, eliminating the need for browser extensions, headless browsers, or external automation environments. The system enables users to manipulate the DOM through text-based commands, allowing complex workflows such as form filling,... -
19
Covalent
Teradata UI Platform built on Angular Material
Reusable tested tools to build robust Angular Material & Angular applications. Vision: To build an atomic, reusable component platform for Teradata to consume, while collaborating in an open-source model. Covalent is a reusable UI platform from Teradata for building web applications with common standards and tooling. It is based on Angular and Material Design. Visualize your data easily. ECharts is an extensive "tried and true" charting library brought to Angular as Covalent Charts. td-chart-x-axis and td-chart-y-axis elements generate an axis inside a td-chart. ... -
20
AI Employe
Create browser automation as if you were teaching a human using GPT-4
...Please sign up for a Firebase account and create a project. There are several techniques for this, ranging from sending a shortened form of HTML to GPT-3, creating a bounding box with IDs and sending it to GPT-4-vision to take actions, or directly asking GPT-4-vision to obtain the X and Y coordinates of the element. However, none of these methods were reliable; they all led to hallucinations. To prevent GPT from derailing from tasks, we use a technique that is akin to retrieval-augmented generation, but we kind of call it Actions Augmented Generation. ... -
21
ModelFusion
The TypeScript library for building AI applications
...Instead of writing separate integration logic for each provider, developers can use ModelFusion to handle common operations such as text generation, structured object generation, streaming responses, and tool calls. The library supports a wide range of model types, including text generation models, vision models, text-to-speech engines, speech-to-text systems, and embedding models. It also includes built-in production features such as observability hooks, logging, automatic retries, and error handling mechanisms that improve reliability when deploying AI systems in real-world environments. -
22
Amica
Amica is an open source interface for interactive communication
Amica is an open source interface for interacting with fully animated 3D characters that combine voice chat, vision, and an emotion engine into a single experience. It lets you hold natural conversations with AI characters that can see, listen, and speak, while expressing emotional states through facial expressions and body language. Users can import VRM character models, adjust their appearance, tune the voice to match the character, and define behavior using different large language models and TTS backends. ... -
23
RoomGPT
Upload a photo of your room to generate your dream room with AI
RoomGPT is an open-source app that lets you upload a photo of your room and generate redesigned versions of it using AI. It uses a model such as ControlNet to condition the generation on the original room layout, producing realistic variations while preserving structure like walls, windows, and furniture placement. The app is built on Next.js and exposes a simple web interface where users can upload images, choose styles, and view generated outputs. Under the hood, it calls a hosted ML model... -
24
Serverless Next.js Component
Deploy your Next.js apps on AWS Lambda@Edge via Serverless Components
...Since Next.js 8.0, serverless mode was introduced which provides a new low-level API that projects like this can use to deploy onto different cloud providers. However, Next.js doesn't provide the full serverless routing logic, hence why this project is needed to fill the gap. The long-term vision is to allow you to self-host with various clouds, starting with AWS. This project is a better version of the serverless plugin which focuses on addressing core issues like next 9 support, better development experience, the 200 CloudFormation resource limit and performance. Users of this component should be able to use Next.js development tooling, aka next dev. ... -
25
Cloud Annotations
A fast, easy and collaborative open source image annotation tool
Learn computer vision & AI by building real-world applications. Learn to build and train computer vision models—then show off your skills in an interactive web application. Build impressive applications and learn coveted skills. The examples below were created by the Skills Network Team—right here in CV Studio. Create your own project dataset by uploading images and videos.
