Agent Sandbox
ActiveDescription
A local execution sandbox for AI agents that uses Docker to isolate filesystem, network, and processes, enabling safe execution of model-generated code, commands, and tool calls.
A local execution sandbox for AI agents that uses Docker to isolate filesystem, network, and processes, enabling safe execution of model-generated code, commands, and tool calls.
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
Open-source AI sandbox infrastructure for code execution, browser use, and AI agent runtimes.
Run coding agents in sandboxes. Control them over HTTP. Supports Claude Code, Codex, OpenCode, and Amp with isolated execution environments.
A sandboxed execution environment for AI agents via WASM, providing lightweight and high-performance code isolation for safely executing untrusted agent code.