Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
LLM Sandbox is a Python library and MCP server for running code generated by large language models inside isolated containers. It is used when AI-generated programs need controlled access to languages, dependencies, computing resources, or networks without directly reaching the host system. The catalogue add-ons help agents use the sandbox.
Latest release 0.3.46 — 0.3.46 — Native Linux and experimental Windows backends · 16 Oct 2026
2 files for GitHub Copilot and Claude Code: llm-sandbox copilot-instructions.md, llm-sandbox CLAUDE.md — 4,844 tokens loaded in every session.
.github/copilot-instructions.md A 2,205 tok CLAUDE.md A 2,639 tok These files are vndee/llm-sandbox's own configuration — they tell GitHub Copilot and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.