VibeKit
VibeKit is a simple, open source SDK for safely running Codex and Claude Code agents in secure, customizable sandboxes. It enables you to embed coding agents directly in your app or workflow via a drop‑in SDK. import VibeKit and VibeKitConfig, and call generateCode with prompts, modes, and streaming callbacks for live output handling. VibeKit runs code in fully isolated private sandboxes, supports customizable environments where you can install packages, and is model‑agnostic, letting you choose any compatible Codex or Claude model. It streams agent output efficiently, maintains full prompt and code history, provides async run handling, integrates with GitHub for commits, branches, and pull requests, and supports telemetry and tracing (via OpenTelemetry). Compatible sandbox providers include E2B (today), with Daytona, Modal, Fly.io, and others coming soon, plus support for any runtime that meets your security needs.
Learn more
E2B
E2B is an open source runtime designed to securely execute AI-generated code within isolated cloud sandboxes. It enables developers to integrate code interpretation capabilities into their AI applications and agents, facilitating the execution of dynamic code snippets in a controlled environment. The platform supports multiple programming languages, including Python and JavaScript, and offers SDKs for seamless integration. E2B utilizes Firecracker microVMs to ensure robust security and isolation for code execution. Developers can deploy E2B within their own infrastructure or utilize the provided cloud service. The platform is designed to be LLM-agnostic, allowing compatibility with various large language models such as OpenAI, Llama, Anthropic, and Mistral. E2B's features include rapid sandbox initialization, customizable execution environments, and support for long-running sessions up to 24 hours.
Learn more
Cua
Cua is a computer-use agent platform that lets AI agents see screens, click buttons, type, and run code just like a human across macOS, Windows, Linux, browsers, and mobile environments. It provides cloud-based, sandboxed desktops where agents can automate real software workflows without relying on APIs. Built on open-source Cua agents, the platform enables developers to build, run, and scale computer-use agents with precision and reliability. Cua supports multi-step tasks, structured outputs, and human-in-the-loop recovery for complex automation. Agents operate in fully isolated environments to ensure safety and reproducibility. Cua is designed to make AI interaction with real applications practical and scalable.
Learn more
happycapy
happycapy is an agent-native AI platform that turns your browser into a powerful “agent computer,” enabling developers and users to deploy and run autonomous AI agents 24/7 without traditional server infrastructure, letting you delegate work across hundreds of large language models (LLMs) and AI services such as Claude Code in a secure, sandboxed environment. It supports running multiple AI agents in parallel to handle coding, automation, data-processing, and custom workflows continuously, giving teams a unified interface for orchestrating, scaling, and monitoring agent tasks. happycapy emphasizes flexibility and developer control by providing a private sandbox where agents can execute jobs, interact with code and data, and collaborate on complex tasks while managing state, logs, and outputs from AI services. It simplifies building and maintaining AI-powered applications by abstracting the complexity of infrastructure and model orchestration.
Learn more