沙箱执行

A CNCF Sandbox SRE Agent that automatically analyzes infrastructure logs and metrics to assist with incident diagnosis and system operations.

Open-source AI agent desktop app for Windows and macOS with one-click install of Claude Code, MCP tools, and Skills, featuring sandbox isolation, multi-model support, and Feishu/Slack integration.

面向 AI Agent 的沙箱化代码执行环境，支持本地和云端部署，具备大规模并行执行能力，为 SWE-agent 等编程 Agent 提供安全可靠的代码运行时。

Arrakis is a fully customizable and self-hosted sandboxing solution written in Go, designed specifically for AI agent code execution scenarios, providing a secure isolated runtime environment.

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime — sandbox any command with file, network, and credential controls.

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container, providing a secure isolated execution environment for agents.

OpenSandbox 是阿里巴巴开源的安全、快速、可扩展的 AI Agent 沙箱运行时环境。

A capability-based, multiplexing sandbox tool built for developers — run agents securely without needing any additional infra, zero setup, zero latency.

字节跳动开源的长周期 SuperAgent 框架，支持研究、编码和创作任务，具备沙箱环境、记忆系统、工具调用和子 Agent 协同能力，可处理从分钟到小时级别的复杂任务。

A Data Agent Ready Warehouse unifying Analytics, Search, AI, and Python Sandbox in one system. Runs on your S3 with built-in vector search, full-text search, and Python execution for AI-powered data analysis.

Daytona 提供面向开发 Agent 与自动化任务的安全开发环境基础设施，适合作为代码 Agent、远程执行与开发者工作流自动化的运行底座。

开源一站式 AI 生产力平台，集通用 AI Agent、工作流引擎、即时通讯和在线文档于一体

Python 和 JS/TS SDK，用于在安全的云端沙箱中运行 AI 生成的代码，支持 Jupyter Notebook 风格的代码解释

E2B 提供面向 AI Agent 的安全云沙箱运行环境，支持代码执行、文件操作与隔离计算，适合作为代码 Agent、数据 Agent 与自动化任务的执行层。

本地 AI Agent 沙箱工具，通过文件系统权限控制让 AI 代理只能读写其所需的文件，保障本地运行安全。

A lightweight, fast, and secure code execution environment supporting multiple programming languages — provides sandboxed code execution for the Dify platform.

Easy Linux virtual machine on macOS to sandbox LLM agents — a lightweight VM solution for safely running AI-generated code in isolation.

Microsoft's AI Agent Governance Toolkit providing policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Context Mode 是面向 AI 编程 Agent 的上下文窗口优化工具，通过沙盒化工具输出实现 98% 的上下文缩减，支持 12 个主流编程平台。

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, and MCP tools.

在沙箱中运行编程 Agent 的工具，通过 HTTP 控制，支持 Claude Code、Codex、OpenCode 和 Amp，为 AI 编程 Agent 提供隔离的执行环境。

Dev environments in your web app — run Node.js runtime environments in the browser with full sandboxing, no server-side execution needed.

Arrow 是面向 Agentic 时代的前端 UI 框架，体积小巧、性能优异，内置 WASM 沙箱实现安全代码执行，专为构建 AI Agent 交互界面而设计。

Steel Browser 是一个专为 AI Agent 和应用设计的开源浏览器沙盒，提供完整的浏览器 API，支持会话管理、代理集成和自动反检测，让开发者无需关注基础设施即可实现 Web 自动化。

Secure, local, cross-platform and programmable sandboxes for AI agents. Provides strict resource isolation using microVM technology.

CUA 是开源的计算机使用 Agent 基础设施，提供沙箱、SDK 和基准测试，支持 AI Agent 控制完整桌面环境。

Lightweight and portable LLM sandbox runtime Python library — provides a code interpreter for safely executing AI agent-generated code in isolated environments.