LLM Sandbox
Python library and MCP server for running LLM-generated code in isolated backends (Docker, Kubernetes, Podman, Bubblewrap, NsJail, Windows) behind one API.
Tags
Description
One code-execution API over several isolation backends, with security policies, CPU/memory/time limits, network isolation, artifact (plot) capture, on-the-fly dependency install, file copy and container pooling. Supports Python, JavaScript, Java, C++, Go and R. Includes an MCP server so MCP clients can run code in the sandbox, plus runnable examples for eleven agent frameworks (OpenAI Agents SDK, Claude Agent SDK, LangChain, LlamaIndex, Google ADK, CrewAI, Pydantic AI, smolagents, Strands and others). pip install 'llm-sandbox[docker]'.
Agent access
Related
- E2B: Open-source, secure cloud sandboxes for AI agents: an isolated machine per agent to run code, browse and use tools.
- microsandbox: Easy, fast, programmable, local-first microVM runtime for untrusted workloads.
- Docker Sandboxes: Docker's `sbx` CLI runs coding agents like Claude Code and Codex in isolated microVM sandboxes, locally for free or on metered Docker-managed cloud compute.
- Anthropic Sandbox Runtime (srt): Lightweight OS-level sandbox enforcing filesystem and network restrictions on agents, MCP servers and arbitrary processes, without a container.
- OpenSandbox: Open-source sandbox platform for running agents on your own infrastructure: isolated environments for code, commands, files, browsers and desktops, from Docker to Kubernetes.
Sources
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)