Search Results for "image text input"
Sort By:
Showing 55 open source projects for "image text input"
View related business solutions-
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
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.
-
1
Readest
Readest is a modern, feature-rich ebook reader
...The design seems to prioritize flexible input formats, possibly OCR or uploaded documents, and interactive tools to navigate or annotate them. -
2
nut.js
Native UI testing / controlling with node
nut.js gives you full control over your mouse. Move, click or drag your cursor where you need it! Press (and hold) single keys or type pages of text, nut.js handles both! It allows for native UI interactions via keyboard and/or mouse but additionally gives you the possibility to navigate the screen based on image matching. nut.js gives you access to your system clipboard. Copy and paste text as you go! Retrieve info about open windows to improve your tests or workflows. nut.js provides plug-ins to perform on-screen image search, the key component for visual testing or image-based automation! ... -
3
Welcome to node-html-to-image
A Node.js module that generates images from HTML
...Additionally, it embarks Handlebars to provide a way to add logic to your HTML. When you install Puppeteer, it downloads a recent version of Chromium (~170MB Mac, ~282MB Linux, ~280MB Win) that is guaranteed to work with the API. node-html-to-image takes a screenshot of the body tag's content. If you want to set output image's resolution you need to set its dimension using CSS. Handlerbars is a templating language. It generates HTML from a template and an input object. In the following example we provide a template to node-html-to-image and a content object to fill the template. -
4
Choices.js
A vanilla JS customizable select box/text input plugin
Choices.js is a lightweight, configurable select box/text input plugin. Similar to Select2 and Selectize but without the jQuery dependency. Choices is compiled using Babel targeting browsers with more than 1% of global usage and expecting that features listed below are available or polyfilled in the browser. You may see exact list of target browsers by running npx browserslist within this repository folder. -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
Tabby
A terminal for a more modern age
...Better tab-completion cmd.exe thanks to Clink. Explorer menu integration. Optional portable mode. Current directory detection that works. Multiple connection profiles. Newline conversion. Text, reading and byte-by-byte input modes. Text and hexdump output modes. Zmodem, Non-standard baud rates. Simultaneous multi-pane input. Optional PuTTY style right-click paste and copy on select. macOS vibrancy and Win 10 fluent background support. -
6
Portkey AI Gateway
A blazing fast AI Gateway with integrated guardrails
Portkey AI Gateway aims to offer a blazing fast, secure, and flexible gateway for interacting with a wide variety of models and enforcing guardrails. It presents a single, friendly API through which you can route to 200+ LLMs, while applying configurable input/output guardrails to enforce policies or restrict certain content. 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. ... -
7
OpenAI.fm
Code for openai.fm, a demo for the OpenAI Speech API
...Users can experiment with different input text and voice options directly in their browser, gaining a sense of how high-fidelity AI audio can be integrated into applications ranging from podcasts and narration to accessibility tools and interactive agents. Although the web demo is free to explore, production use of the underlying API requires an OpenAI API key and may incur costs based on usage. -
8
Gemini Next Chat
Deploy your private Gemini application for free with one click
Gemini Next Chat is an open-source web application that allows you to deploy your own private chat interface powered by Google’s Gemini models (e.g., Gemini 1.5, Gemini 2.0, etc.). It is built with Next.js/TypeScript and targets developers and hobbyists who want a self-hosted solution for interacting with advanced multimodal models (text, image, voice). It supports features like image recognition, voice-based conversation, plugins (web search, ArXiv search, weather, etc.), and client apps (tray app) for greater convenience. The project emphasizes “one-click” deployment, aiming to make it easy to spin up a custom chat front end without deep infra-setup. It’s licensed under MIT and has an active community of contributors; documentation and release notes note support for newer features like mixed image+text generation. ... -
9
Streamdown
Streaming markdown renderer for AI apps with smooth updates
Streamdown is a lightweight rendering library designed to display streaming Markdown content in real time, making it particularly useful for AI-powered applications that generate text incrementally. It focuses on providing a smooth and visually stable experience while content is being appended, avoiding layout shifts that can disrupt readability. Streamdown is built to handle partial Markdown input gracefully, progressively enhancing the output as more text becomes available. It is especially relevant for chat interfaces, coding assistants, and any environment where responses are streamed token by token. ... -
Connect every part of your business to one bank accountNorth One is proudly built for small businesses, startups and freelancers across America. Make payments easily, keep tabs on your money and put your finances on autopilot through smart integrations with the tools you’re already using. North One was built to make managing money easy so you can focus on running your business. No more branches. No more lines. No more paperwork. Get complete access to your North One Account from your phone or computer, wherever your business takes you. Create Envelopes for taxes, payroll, rent, and anything else automatically.
-
10
react-markdown-editor-lite
A light-weight Markdown editor based on React
A light-weight(20KB zipped) Markdown editor of React component. Supports TypeScript. Supports custom markdown parser. Full markdown support. Supports pluggable function bars. Full control over UI. Supports image uploading and dragging. Supports synced scrolling between editor and preview. -
11
YAML
JavaScript parser and stringifier for YAML
yaml is a definitive library for YAML, the human friendly data serialization standard. This library supports both YAML 1.1 and YAML 1.2 and all common data schemas, passes all of the yaml-test-suite tests. It can accept any string as input without throwing, parsing as much YAML out of it as it can, and supports parsing, modifying, and writing YAML comments and blank lines. The library is released under the ISC open source license, and the code is available on GitHub. It has no external... -
12
LiteParse
A fast, helpful, and open-source document parser
...The library is particularly useful for tasks such as data extraction, document processing, and building pipelines that require structured outputs from natural language input. -
13
OmniTools
Self-hosted collection of powerful web-based tools for everyday tasks
...A key design choice is that file processing happens entirely on the client side, meaning your data stays in your browser instead of being sent to the backend. The tool catalog spans both technical and non-technical needs, including image, video, audio, PDF, text, date/time, math, and data format utilities like JSON/CSV/XML helpers. It’s also packaged for straightforward self-hosting, with a lightweight Docker image and simple run commands, so it can be deployed quickly on a homelab or internal network. -
14
Nextra
Simple, powerful and flexible site generation framework
Simple, powerful, and flexible site generation framework with everything you love from Next.js. Nextra automatically converts Markdown links and images to use Next.js Link and Next.js Image when possible. No slow navigation or layout shift. -
15
TTime
Screenshots, word marking, OCR, AI, translation software
TTime is a desktop productivity tool that combines translation, OCR, and screen capture capabilities into a unified application designed for fast and efficient text processing workflows. It allows users to translate text through multiple methods, including direct input, screenshot-based capture, and real-time word selection, making it versatile for both casual use and professional tasks. The software integrates a wide range of translation engines and OCR services, including cloud-based providers and offline options, ensuring flexibility across different environments and connectivity conditions. ... -
16
Mini QR
Create & scan cute qr codes easily
Mini QR is a web app focused on making QR codes feel friendly and design-forward, combining a polished QR generator with a built-in scanner so you can both create and decode codes in the same place. It emphasizes customization so the QR you generate can match a brand, event theme, or personal style, including color and styling controls, framed layouts with labels, and the ability to add a logo image. Because QR reliability matters as much as looks, it exposes practical settings like error... -
17
Generative AI for Beginners (Version 3)
21 Lessons, Get Started Building with Generative AI
...Lessons are split into “Learn” modules for core concepts and “Build” modules with hands-on code in Python and TypeScript, so you can jump in at any point that matches your goals. The course covers everything from model selection, prompt engineering, and chat/text/image app patterns to secure development practices and UX for AI. It also walks through modern application techniques such as function calling, RAG with vector databases, working with open source models, agents, fine-tuning, and using SLMs. Each lesson includes a short video, a written guide, runnable samples for Azure OpenAI, the GitHub Marketplace Model Catalog, and the OpenAI API, plus a “Keep Learning” section for deeper study. -
18
Deep Chat
Customizable AI chat component for websites with API support
Deep Chat is a highly customizable web component designed to simplify the integration of AI-powered chat interfaces into websites. It allows developers to embed a fully functional chatbot using minimal setup, while still offering extensive control over behavior, appearance, and integrations. Deep Chat supports connections to a wide range of AI services as well as custom backends, enabling flexible deployment for different use cases. It is built as a framework-agnostic solution, meaning it... -
19
ALLWEONE
AI tool that generates custom presentations with real-time editing
...You can define slide count, language, and tone, then review or edit the AI-generated outline before finalising. Slides are built in real time, allowing you to watch content develop as the system works. Presentation AI by ALLWEONE includes image generation, rich text editing, and drag-and-drop functionality for easy adjustments. It also supports presentation mode, so you can present directly within the app. Built with modern technologies like Next.js, React, and Tailwind CSS, it integrates AI services such as OpenAI for content generation. It is fully open source under the MIT licence, making it suitable for developers who want to customise or extend its capabilities. -
20
Notifee Notifications
A feature rich notifications library for React Native
...Present & handle quick actions alongside your notification content. Actions can be handled in the background or foreground with JavaScript code! Notifee supports many notification styles such as Big Text, Big Picture, Inbox & Messaging on Android and attachments & custom summary text on iOS. Trigger your notifications to display at certain point in the future, or set up repeating triggers to alert your users regularly! Notifications support displaying remote images and local with support for requiring React Native image assets. -
21
EcoPaste
Open source clipboard management tools for Windows, Macos and Linux
Open source clipboard management tools for Windows, macOS, and Linux. Built with Tauri, the application is lightweight and refined, consuming minimal resources. It also delivers a uniform user experience across both Windows, MacOS, and Linux platforms. The application is resident in the background, wakes up with one click through custom shortcut keys, saves time, and improves efficiency. Allows you to bookmark clipboard content for easy and fast access. Whether it's crucial data for work or... -
22
Ito
Ito, smart dictation in every application
ito is an open‑source JavaScript library for serverless, browser‑to‑browser communication designed for use on devices with or without user input interfaces, such as IoT devices, mobile devices, tablets, and desktops, enabling peer messaging and data sharing via short passcodes and cloud‑backed pairing without an application server. -
23
MLX Engine
LM Studio Apple MLX engine
MLX Engine is the Apple MLX-based inference backend used by LM Studio to run large language models efficiently on Apple Silicon hardware. Built on top of the mlx-lm and mlx-vlm ecosystems, the engine provides a unified architecture capable of supporting both text-only and multimodal models. Its design focuses on high-performance on-device inference, leveraging Apple’s MLX stack to accelerate computation on M-series chips. The project introduces modular VisionAddOn components that allow image embeddings to be integrated seamlessly into language model workflows. It is bundled with newer versions of LM Studio but can also be used independently for experimentation and development. ... -
24
Starter Applets
Google AI Studio Starter Apps
starter-applets is a collection of minimal, sandboxed example “applets” that demonstrate how to compose Gemini-powered microapps (chat widgets, image generation, workflows) that can be embedded in other applications or used standalone. The applets are structured with a focus on simplicity: each presents a prompt input, minimal UI logic, and inline display of the resulting output or widget (e.g. generated text, images). They are built to illustrate best practices (e.g. safety guards, prompt templates, streaming UI updates) rather than production feature sets. ... -
25
AI App Lab
Implementing large models into scenario-based applications
...The project focuses on helping developers bridge the gap between AI models and practical business use cases by offering a structured environment for creating production-ready AI systems. It includes a high-level SDK called Arkitect, which provides workflows and tools for integrating models, plugins, and multimodal capabilities such as text, image, and voice processing. The repository also contains a large collection of prototype applications that demonstrate how AI can be applied to scenarios such as customer service, education, content generation, and mobile automation. These examples allow developers to quickly replicate and customize solutions for their own business needs.
