{"library":"llm-sandbox","type":"library","category":null,"description":"LLM Sandbox is a lightweight and portable Python library designed to run large language model (LLM) generated code in a safe and isolated environment. It supports various container backends like Docker, Kubernetes, and Podman, and offers multi-language execution (Python, JavaScript, Java, C++, Go, R). The project sees frequent minor releases, addressing features, fixes, and security enhancements, and now supports the Model Context Protocol (MCP) server for direct AI assistant integration.","language":"python","status":"active","version":"0.3.38","tags":["llm","sandbox","code execution","security","ai","containerization","code interpreter","mcp"],"last_verified":"Sun May 24","install":[{"cmd":"pip install llm-sandbox","imports":["from llm_sandbox import SandboxSession"]},{"cmd":"pip install 'llm-sandbox[docker]' # For Docker backend\npip install 'llm-sandbox[kubernetes]' # For Kubernetes backend\npip install 'llm-sandbox[podman]' # For Podman backend","imports":[]}],"homepage":"https://vndee.github.io/llm-sandbox/","github":"https://github.com/vndee/llm-sandbox","docs":"https://vndee.github.io/llm-sandbox/","changelog":null,"pypi":"https://pypi.org/project/llm-sandbox/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":3.2,"avg_import_s":0.58,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/llm-sandbox/compatibility"}}