// Run code in a sandbox
llm-sandbox0.3.45
Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
Open source Maintained For agents
IN ONE PARAGRAPH
llm-sandbox is lightweight and portable LLM sandbox runtime (code interpreter) Python library.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to run code in a sandbox.
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it from the official package registry:
pip install llm-sandbox - 3Add it to your agent’s MCP config — Claude Code:
claude mcp add; Cursor:.cursor/mcp.json; Codex:~/.codex/config.toml.
02Alternatives & comparison
Compare side by side → E2B Open-source, secure environment with real-world tools for enterprise-grade agents. ★ 14k code-interpreter Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app ★ 2.4k firecracker Secure and fast microVMs for serverless computing. ★ 37k gvisor Application Kernel for Containers ★ 20k runtime The runtime behind every E2B stack: Cloud, Enterprise, and your own machine. ★ 1.7k
03Related
- ›BlueDot Impact AI Alignment 课程 · BlueDot ImpactEnglish
- ›BlueDot Impact AI Governance 课程 · BlueDot ImpactEnglish
- ›AI Safety, Ethics and Society 教材 · Center for AI Safety / Dan HendrycksEnglish
- ›OWASP Top 10 for LLM Applications · OWASP GenAI Security ProjectMultilingual (incl. EN/ZH)
- ›MITRE ATLAS · MITREEnglish
- All tutorials →