Search Results for "run code" - Page 4
Sort By:
Showing 123 open source projects for "run code"
View related business solutions-
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.
-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
1
Anthony Fu's Skills
Anthony Fu's curated collection of agent skills
Anthony Fu's Skills is an open-source collection of agent skills — modular instruction packages that teach AI coding assistants how to perform specific tasks automatically when relevant. These skills are typically simple, human-readable files that contain structured steps, rules, examples, and workflow logic, letting tools like Claude Code or Copilot CLI load and run them only when they apply to the user’s input. By offloading detailed task patterns into discrete skill modules, developers can greatly extend what coding agents can do without retraining the underlying language model itself. The project serves as a curated registry of utilities that save time, standardize best practices, and encode expertise across domains, while still being easy to customize or extend. ... -
2
Modelence
Modelence is an all-in-one TypeScript platform
...The project is built to support modern application workflows where product teams want to move quickly without stitching together many separate services and libraries. It includes scaffolding and tooling to create a new application quickly, then run a local development server with a predictable structure that’s easy to extend. Modelence also focuses on “standard features” that most apps require, so developers can spend more time on product logic rather than setup and glue code. -
3
barba.js
Create badass, fluid and smooth transitions between website’s pages
Barba.js — aka Barba — is a small (7kb minified and compressed) and easy-to-use library that helps you create fluid and smooth transitions between your website's pages. It makes your website run like a SPA (Single Page Application) and help reduce the delay between your pages, minimize browser HTTP requests and enhance your user's web experience. -
4
MCP Server Chart
A visualization mcp contains 25+ visual charts
...Out of the box it exposes more than 20–25 chart generators—covering staples like bar, line, area, histogram and pie, plus advanced visuals such as dual-axes, heatmaps, radar, flow and fishbone diagrams—so an AI client can request a chart and receive an image URL in return. The server can run over stdio for desktop IDEs or via SSE/“streamable” HTTP transport, making it easy to plug into MCP-capable clients and platforms (including Dify) without custom glue code. A simple CLI and environment variables control behavior, including disabling specific tools, selecting a visualization request service, or tagging a service instance for multi-tenant setups. ... -
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
Playwriter
Chrome extension to let agents control your browser
...Playwriter’s architecture supports both extension-based control for real browser windows and CLI integration, giving developers flexibility in how they build and run browser automation workflows. -
6
Open Responses
Specification for multi-provider, interoperable LLM interfaces
Open Responses is an open-source implementation of an API compatible with the OpenAI Responses API that lets developers self-host a drop-in alternative endpoint for AI interactions while preserving compatibility with existing Agents SDKs and model workflows. It enables you to run a local or private server that speaks the standard Responses API, so tools, applications, and agents built against that API can operate without contacting OpenAI’s cloud and can instead route calls to any large language model provider you choose, such as Claude, Qwen, Ollama, or others. This makes it a powerful option for teams or individuals who want full control over their AI infrastructure, prioritize privacy, or need to standardize inference calls across multiple backends without rewriting their code. -
7
mcp-server-chatsum
Query and Summarize your chat messages
...Although releases are minimal, the code and README are sufficient for local setups and experimentation. It’s a practical utility for converting long chat logs into usable, agent-friendly context. -
8
Solid
A declarative JavaScript library for building user interfaces
...Instead of using a Virtual DOM, it compiles its templates to real DOM nodes and updates them with fine-grained reactions. Declare your state and use it throughout your app, and when a piece of state changes, only the code that depends on it will rerun. Check out our intro video or read on! Fine-grained updates to the real DOM. Declarative data: model your state as a system with reactive primitives. Render-once mental model: your components are regular JavaScript functions that run once to set up your view. Automatic dependency tracking: accessing your reactive state subscribes to it. ... -
9
TensorFlow.js
TensorFlow.js is a library for machine learning in JavaScript
TensorFlow.js is a library for machine learning in JavaScript. Develop ML models in JavaScript, and use ML directly in the browser or in Node.js. Use off-the-shelf JavaScript models or convert Python TensorFlow models to run in the browser or under Node.js. Retrain pre-existing ML models using your own data. Build and train models directly in JavaScript using flexible and intuitive APIs. Tensors are the core datastructure of TensorFlow.js They are a generalization of vectors and matrices to... -
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.
-
10
OpenNext for Cloudflare
Open Next.js adapter for Cloudflare
This sibling project targets Cloudflare’s edge platform, adapting Next.js apps to run on Workers and related services. It converts server components, API routes, and middleware into Worker scripts, while placing static assets in globally distributed storage for low-latency delivery. The adapter accounts for edge constraints—limited runtime APIs, streaming semantics, and per-request cold starts—so Next.js features remain functional at the perimeter. -
11
Delightful JavaScript Testing
Delightful JavaScript Testing
Jest is a delightful JavaScript Testing Framework with a focus on simplicity. Jest aims to work out of the box, config-free, on most JavaScript projects. Make tests that keep track of large objects with ease. Snapshots live either alongside your tests or embedded inline. Tests are parallelized by running them in their own processes to maximize performance. By ensuring your tests have unique global state, Jest can reliably run tests in parallel. To make things quick, Jest runs previously... -
12
VibeKit
Run Claude Code, Gemini, Codex in a clean, isolated sandbox
Vibekit is an open-source toolkit focused on rapid prototyping and building of AI-driven experiences, particularly those that integrate multimodal inputs, reactive interfaces, and context-aware behaviors. It provides a set of abstractions and utilities that let developers connect generative models to UI frameworks, sensors, event streams, and external services without having to build plumbing from scratch. Instead of treating AI models as black boxes behind simple prompts, Vibekit encourages... -
13
AWS IoT Device SDK for JavaScript v2
Next generation AWS IoT Client SDK for Node.js using the AWS Runtime
...This SDK is built on the AWS Common Runtime, a collection of libraries (aws-c-common, aws-c-io, aws-c-mqtt, aws-c-http, aws-c-cal ...) written in C to be cross-platform, high-performance, secure, and reliable. The libraries are bound to JS by the awscrt package. You will need to install NodeJS in orderto run the SDK on Windows, MacOS, and Linux. You can find installers for NodeJS on the NodeJS website's download page. To build the SDK, you will need a compiler that can compile C++ 11 code or higher. C++ compilers vary based on platform. You will also need CMake to build the SDK. The minimum required version is CMake 3.1. There are several ways to install CMake depending on the Linux operating system. -
14
BRAID
Themeable design system for the SEEK Group
Braid aims to make cross-brand UI development as fast as possible while maintaining a high level of quality and accessibility. In order to achieve this, Braid provides as a set of React components and CSS variable-based styling themes using vanilla-extract. As much as possible, we want Braid code to make sense to non-developers. We’re aggressively focused on the simplicity and composability of its API. Along with our work on Playroom, our goal is to empower designers and developers to... -
15
AnyClaw
Android app running two AI coding agents with a built-in Linux runtime
...Through the embedded runtime, the agents can read codebases, write code, and execute shell commands within the packaged Linux environment. It also supports parallel conversations with separate working contexts, enabling multi-threaded development workflows on a mobile device. -
16
Slashbase
Modern database IDE for your dev & data workflows
Slashbase is an open-source modern database IDE for your dev/data workflows. Use Slashbase to connect to any of your databases, browse data and schema, write, run and save queries, create charts. Supports MySQL, PostgreSQL and MongoDB. -
17
Maestro
Agent Orchestration Command Center
...It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create detailed specification documents, then let Auto Run execute them automatically, each task in a fresh session with clean context. Allowing for long-running unattended sessions, my current record is nearly 24 hours of continuous runtime. Run multiple agents in parallel with a Linear/Superhuman-level responsive interface. Currently supporting Claude Code, OpenAI Codex, and OpenCode with plans for additional agentic coding tools (Aider, Gemini CLI, Qwen3 Coder) based on user demand. -
18
CodinIT.dev
Free, local, open-source AI app builder
CodinIT.dev is a free, local, open source AI app builder that lets you go from idea to full-stack application entirely on your machine, no coding required, just chat with AI. You can build unlimited apps with real-time previews, instant undo, and responsive, frictionless workflows. Deep Supabase integration means you can create UI and backend logic in one cohesive environment, while the model-agnostic architecture lets you connect to any AI, whether cloud-based (Gemini 3 Pro, GPT-5,... -
19
Brill Software
A faster way to develop React Web Applications
The Brill Framework allows React web applications to be built quickly using a "Low Code" approach. A Content Management System (CMS) supports editing of pages containing React components. The React components communicate with each other and the Server using a middleware that's based on WebSockets. With a "No Code" solution, there's always something you require that's not support. You spend ages bending the product to your requirements or pay the supplier to provide the components... -
20
Shinkai: Local AI Agents
Shinkai allows you to create advanced AI (local) agents effortlessly
Shinkai is a free, open-source AI platform that lets anyone create powerful AI agents without coding. These agents can collaborate with each other, handle complex tasks, and operate in decentralized crypto environments. Key Features: - No-Code Agent Creation - Build specialized agents (trading bots, sentiment trackers, etc.) with simple descriptions - Multi-Agent Collaboration - Agents work together to solve complex problems - Crypto Integration - Built-in support for decentralized payments and transactions - Flexible AI Models - Choose from cloud models (GPT-4, Claude) or run locally - Universal Compatibility - Works with Model Context Protocol (MCP) for cross-platform integration - Local Security - Crypto keys and computations stay on your device Shinkai transforms AI from single-task tools into collaborative, autonomous systems that can operate in decentralized networks while maintaining privacy and security. -
21
AutoGPT.js
Auto-GPT on the browser
AutoGPT.js is an open-source project that brings autonomous AI agent capabilities similar to AutoGPT directly into the browser environment. The system allows users to run an AI agent capable of performing tasks such as generating code, searching the web, and interacting with files on the local computer. Unlike traditional AutoGPT implementations that require server infrastructure, AutoGPT.js is designed to run primarily in the browser, making it easier to deploy and experiment with autonomous agents. ... -
22
GPT-Code UI
An open source implementation of OpenAI's ChatGPT Code interpreter
An open source implementation of OpenAI's ChatGPT Code interpreter. Simply ask the OpenAI model to do something and it will generate & execute the code for you. You can put a .env in the working directory to load the OPENAI_API_KEY environment variable. For Azure OpenAI Services, there are also other configurable variables like deployment name. See .env.azure-example for more information. Note that model selection on the UI is currently not supported for Azure OpenAI Services. -
23
LlamaGPT
Self-hosted ChatGPT-like chatbot powered by Llama models locally
...LlamaGPT includes both a user interface and an API component that work together to deliver a web-based chat experience backed by local language models. It supports models such as Llama 2 and Code Llama, allowing users to perform both general conversation and programming-related tasks. It integrates components built around the llama.cpp ecosystem to efficiently run models on consumer hardware. It can be deployed using containerized setups and supports environments ranging from personal computers to self-hosted servers. -
24
html-pdf-chrome
HTML to PDF or image (jpeg, png, webp) converter via Chrome/Chromium
HTML to PDF or image (jpeg, png, webp) converter via Chrome/Chromium. This library is NOT meant to accept untrusted user input. Doing so may have serious security risks such as Server-Side Request Forgery (SSRF). If you run into CORS issues, try using the --disable-web-security Chrome flag, either when you start Chrome externally, or in options.chromeFlags. This option should only be used if you fully trust the code you are executing during a print job. It is strongly recommended that you keep Chrome running side-by-side with Node.js. There is significant overhead starting up Chrome for each PDF generation which can be easily avoided. ... -
25
Hydrogen
Run code interactively, inspect data, and plot
...Watch expressions let you keep track of variables and re-run snippets after every change. Completions from the running kernel, just like autocomplete in the Chrome dev tools. Code can be inspected to show useful information provided by the running kernel. One kernel per language (so you can run snippets from several files, all in the same namespace).
