Search Results for "which" - Page 4
Sort By:
Showing 318 open source projects for "which"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI Studio. Switch between models without switching platforms.
-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
1
OpenAI CS Agents Demo
Demo of a customer service use case implemented with the OpenAI Agents
...The demo covers tasks you’d expect in customer service: changing flights, checking status, answering FAQs, etc. It shows how multiple subagents can be coordinated under a triage agent that decides which specialized agent should handle a given request. The UI includes visualization of which agent is active, routing logic, and conversation tracking. It also demonstrates guardrails to validate or constrain responses, memory usage to maintain context, and tracing to help debugging of workflows. -
2
Vuefire
Firebase bindings for Vue.js & Vuex
Firebase provides two solutions to handle real-time databases: Realtime Database and Cloud Store (which is also a realtime database). In order to keep all clients data in-sync with its cloud database, their js SDK provides the tools to do so. However, it quickly becomes bothersome to bind multiple documents or collections to your application, keep them synchronized as well as handling references to other documents or collections, which can contain references themselves and must also be kept up to date. ... -
3
Formly
JSON powered dynamic forms for Angular
...In order to get all the information from the enum, we have to store them in the ProductTypeNames which output an Array from the enum . -
4
Polyglot
Cross-platform AI language practice app
...It is built around conversational large language models and Azure based text to speech services, turning them into an interactive environment for speaking practice in multiple languages. Users can define custom AI personas, choose languages, and configure their own OpenAI and Azure keys so they retain control over which backends they use. The app supports speech recognition with quick keyboard shortcuts, allowing learners to hold down a key to speak and release it to submit for recognition and response. It includes translation features, dark mode, playback of the user’s own recorded speech, and word highlighting that tracks the progress of synthesized audio to make following along easier. ... -
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.
-
5
OpenAI Assistants Quickstart
OpenAI Assistants API quickstart with Next.js
...The repository includes multiple example pages that each showcase specific capabilities, while all examples share the same underlying assistant with all capabilities enabled. The primary chat logic lives in the Chat component at app/components/chat.tsx, which manages rendering, streaming, and forwarding function calls. Server handlers for threads are provided under api/assistants/threads/..., giving a reference for wiring the API into Next.js routes. The Chat component can be copied directly into other projects, along with its styles from app/components/chat.module.css. Example pages include a basic chat, a function calling demo, a file search demo, and a full-featured example, allowing developers to explore each feature in isolation or together. -
6
TypeORM
ORM for TypeScript and JavaScript (ES7, ES6, ES5)
...Its goal is to always support the latest JavaScript features and provide additional features that help you to develop any kind of application that uses databases - from small applications with a few tables to large scale enterprise applications with multiple databases. TypeORM supports both Active Record and Data Mapper patterns, unlike all other JavaScript ORMs currently in existence, which means you can write high-quality, loosely coupled, scalable, maintainable applications the most productive way. TypeORM is highly influenced by other ORMs, such as Hibernate, Doctrine and Entity Framework. Supports both DataMapper and ActiveRecord (your choice). Uni-directional, bi-directional and self-referenced relations. -
7
Eververse
The open source product management platform
Eververse is an open source product management platform. It is a simple alternative to tools like Productboard and Cycle. Bring your product team together to explore problems, ideate solutions, prioritize features and plan roadmaps with the help of AI. -
8
claude-devtools
A desktop app that reconstructs exactly what Claude Code did
...Rather than acting as a wrapper or modifying Claude Code behavior, the application passively reads the logs stored in the user’s environment and rebuilds a structured, searchable timeline of what actually occurred during each session. The tool was created to address the loss of detail in the standard CLI output, which often summarizes actions without exposing the full underlying operations. It surfaces granular information such as file reads, edits, tool calls, token consumption, and subagent activity, enabling developers to understand exactly how the AI interacted with their codebase. Because it runs entirely locally and makes no network calls, it requires no API keys or configuration and works with any previously recorded sessions. -
9
Design OS
The missing design process between your product idea and your codebase
...The tool is poised to produce production-ready UI components and artifacts that any AI coding tool can consume, encouraging a disciplined front-to-backend workflow that avoids disjointed, reactive design prompts. Design OS emphasizes clarity of intent, consistency of design systems, and exporting usable components rather than just static mockups, which aligns better with automated build pipelines and agent-driven development. -
Catch Bugs Before Your Customers DoMove from alert to fix before users notice. AppSignal monitors errors, performance bottlenecks, host health, and uptime—all from one dashboard. Instant notifications on deployments, anomaly triggers for memory spikes or error surges, and seamless log management. Works out of the box with Rails, Django, Express, Phoenix, Next.js, and dozens more. Starts at $23/month with no hidden fees.
-
10
Algora TV
Open source Twitch for developers
Algora TV is an open source Elixir/Phoenix application developed by Algora.io that powers Live Billboards—a platform for embedding in-video ads during livestreams. The project enables developers to monetize their live content while providing devtools companies a dynamic and non-intrusive way to reach audiences in real time. Built on top of the Phoenix framework, it leverages Elixir’s concurrency and scalability to handle streaming, ad management, and user interactions seamlessly. The system... -
11
massCode
A free and open source code snippets manager for developers
...It helps you create and organize your own personal snippet collection and have quick access to it. massCode allows you to organize snippets using multi-level folders as well as tags. Each snippet has fragments - tabs, which gives even greater level of organization. massCode uses Codemirror as the basis for the editor and .tmLanguage as the grammar for syntax highlighting. massCode allows you to write in Markdown and provide support to syntax highlighting, tables, list and other formatting. Also massCode supports Mermaid. massCode allows you to make a presentation out of a sequence of snippets. ... -
12
Fishing Funds
Fund, big market, stock, virtual currency status bar display for apps
...Any trend and ranking data come from third-party websites and do not represent the author's views. This project is a small plug-in for personal use of the status bar, which is completely open source and free, and is only for learning. -
13
CodePush
Cloud service that enables developers to deploy mobile app updates
...This allows you to have a more deterministic and direct engagement model with your userbase, when addressing bugs and/or adding small features that don't require you to re-build a binary and re-distribute it through the respective app stores. A JavaScript library for programmatically managing your CodePush account (e.g. creating apps, promoting releases), which allows authoring Node.js-based build and/or deployment scripts, without needing to shell out to the App Center CLI. The code-push module exports a single class (typically referred to as CodePush), which represents a proxy to the CodePush account management REST API. -
14
Wingman
An open source AI coding assistant VSCode extension
The Wingman-AI extension brings high-quality AI-assisted coding right to your computer, it's 100% free and private which means data never leaves your machine. The AI will look for natural pauses in typing to decide when to offer code suggestions (keep in mind the speed is limited by your machine). The code completion feature will also analyze comments you type and generate suggestions based on that context. -
15
Mysti
AI coding dream team of agents for VS Code
...The experience is organized around “personas” that change how the assistant approaches a task, such as architecture, debugging, security review, performance tuning, or refactoring, which helps structure the AI’s behavior for different goals. It also supports a brainstorm-style workflow where using more than one backend can produce competing solutions and then synthesize a best answer. Mysti is designed for speed and convenience with quick actions, toolbar persona switching, and a saved conversation history so work is not lost between sessions. -
16
OCRBase
MD/.JSON Document OCR and structured data extraction API
...The core output is designed for downstream automation, producing structured results like JSON according to user-defined schemas while also providing readable formats like Markdown for human review or indexing. It includes real-time job progress updates via WebSockets, which makes it easier to integrate into UIs, dashboards, or ingestion systems where users need feedback on long-running document processing. -
17
js-libp2p-monorepo
The JavaScript Implementation of libp2p networking stack
...In order to build P2P applications, devs have long had to make custom ad-hoc solutions to fit their needs, sometimes making some hard assumptions about their runtimes and the state of the network at the time of their development. Today, looking back more than 20 years, we see a clear pattern in the types of mechanisms built around the Internet Protocol, IP, which can be found throughout many layers of the OSI layer system, libp2p distils these mechanisms into flat categories and defines clear interfaces that once exposed, enable other protocols and applications to use and swap them, enabling upgradability and adaptability for the runtime, without breaking the API. -
18
AI Logo Generator
A free + OSS logo generator powered by Flux on Together AI
...It integrates Clerk for authentication so users can sign in, save their logo history (planned via a dashboard), and potentially manage usage tied to their own API key. Upstash Redis is used for rate limiting, which is important for controlling API usage and preventing abuse when generating many images. Analytics and observability are baked in with Plausible and Helicone, so developers can monitor usage patterns and model behavior over time. -
19
Claude Code Safety Net
A Claude Code plugin that acts as a safety net
...The repository defines patterns and reusable components for validating agent decisions, sanitizing user inputs, and enforcing operational boundaries, making it easier to design fail-safe integrations with both internal toolchains and external APIs. It includes example safety checks that cover common categories like infinite loops, unsafe system commands, data leakage risks, and visibility constraints, which help engineering teams anticipate and defend against unpredictable agent behavior. -
20
React Hook Form
React Hooks for form state management and validation
Performant, flexible, and extensible forms with easy-to-use validation. Intuitive, feature-complete API providing a seamless experience to developers when building forms. Leverage existing HTML markup and validate your forms with our constraint-based validation API. Package size matters. React Hook Form is a tiny library without any dependencies. Minimizes the number of re-renders, minimizes validate computation, and faster mounting. Since the form state is inherently local, it can be easily... -
21
Soketi
Just another simple, fast, and resilient open-source WebSockets server
Ever dreamed about Serverless WebSockets? Soketi can be deployed to Cloudflare Workers. All around the world, closer to your users. Same Pusher protocol. Powered by Cloudflare's Durable Objects and KV, you can achieve great speeds at edge for your users. -
22
TediCross
Bot which bridges Telegram chats with Discord channels
TediCross is a bot that bridges a chat in Telegram with a channel in Discord. There is no public TediCross bot. You need to host it yourself. To host a bot, you need nodejs. The bot requires NodeJS 18 or higher. -
23
Zarm
React-based mobile UI component library
An enterprise-level mobile UI component library developed by Zhongan Technology based on React. The name Zarm (pronounced /zɑːm/, which can be pronounced Zam in Chinese) is inspired by the philosophy that Zhongan Insurance adheres to: to be an insurance with warmth. Zarm = za + warm, za stands for "Zhong An", and warm means "warmth", with the overlapped "a" letter as the center, and the left and right parts are taken respectively. Pursuing the ultimate user experience and committing to building a warm component library is also the original intention of the zarm project. -
24
Acontext
Context data platform for building observable, self-learning AI agents
...The platform observes agent tasks and user feedback in real time, offering robust observability into workflows and helping teams understand how agents perform over time. Acontext also supports agent self-learning by distilling structured skills and experiences from previously completed tasks, which can later be reused or searched to improve future performance. It includes tools to interact with session data, background agents that monitor progress, and a dashboard that visualizes success rates, artifacts, and learned skills. By combining persistent storage, observability, and learning capabilities, Acontext aims to make AI agents more scalable, reliable, and capable. -
25
Planck.js
2D JavaScript Physics Engine
...By offering collision detection, rigid-body dynamics, joints, and simulation capabilities, Planck.js makes it possible for developers to build physically realistic 2D games, simulations, or visualizations in browsers or Node.js without relying on native code. Its API mirrors Box2D’s concepts — bodies, fixtures, shapes, joints — which makes it familiar to users of classic Box2D, while being idiomatic for JavaScript developers. Because it's pure JavaScript, Planck.js integrates easily with HTML5 canvas, WebGL, or other browser-based rendering pipelines, facilitating smooth physics-driven games across platforms. It also is conducive to rapid prototyping and experimentation, since it avoids the complexity of compiling native libraries for web.
