#sandbox

E2B sandbox backend for Vercel's Eve agent framework

Declarative incus sandboxes: Rust core, CLI and compose-style YAML, over incusd's unix socket

A programming language where signatures declare types, effects, and machine-checked promises — proven with Z3, compiled with LLVM. Built for trusting AI-written code.

Fastest, cheapest, safest agentic runtime

🦎 Declarative test sandboxing for TYPO3 via PHP attributes.

Allows you to easily create a sandboxed Twig environment where you can control what tags, filters, functions, and object methods/properties are allowed

A clean, ergonomic Rust client for NEAR Protocol

该仓库未发布描述。

Fast, Multi-Cloud Sandbox Engine for AI Agents

Velane is agentic cloud for deploying your basic workflows, agents and sub-agents. 800+ OAuth integrations, sandboxed Bun and Python execution, and a full deployment pipeline managed via MCP

Official TypeScript SDK for islo.dev

Sui (粋) — Rust-native Nix replacement with API-first design

TypeScript SDK, CLI, agent, and relayer for Tangle AI Cloud — decentralized LLM inference

A bash tool for AI SDK

A lightweight, in-process sandbox for safely executing the tool calls an AI agent requests

Sandboxed TypeScript runtime for AI coding agents to query AWS — full SDK access with in-sandbox aggregation, credentials flow via IMDS and never enter the VM. Ships as a Claude Code plugin (MCP) and a standalone CLI, backed by Shuru microVMs or Docker.

Typed, zero-dependency iframe for React 18+. Real DOM refs, srcDoc, sandbox arrays, allowFullScreen that actually works, and postMessage helpers.

该仓库未发布描述。

该仓库未发布描述。

🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.

该仓库未发布描述。

Sandboxed JSON-over-stdin/stdout tool executor for AI coding agents with 19 tools, workspace confinement, and guarded mutation.

A browser-native code sandbox. Run Node.js, Rust, C++, Python (preview), and other full-stack runtimes directly in the browser.

SDK for interfacing with Thunder Compute Sandboxes.

TypeScript SDK for Declaw — security-first sandboxing for AI agents

Cage lets you programmatically create isolated environments ("sandboxes"), run commands inside them, and tear them down — all through a simple REST API.

Your AI finds the open-source tool it needs on GitHub. Legwork installs it in a sandbox.

A sandbox for coding agents with parametrized state.

productivity-focused sandboxing for Linux

Verifiable coding-agent harness in Go: external test gates, typed outcomes, sandboxed execution, multi-model providers, and signed proof bundles.