// Run code in a sandbox
agent-sandbox
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
Open source Maintained For agents
IN ONE PARAGRAPH
agent-sandbox is agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to run code in a sandbox.
Not for: people who don’t want to install and run tools themselves.
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it as the official guide describes.
- 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side → firecracker Secure and fast microVMs for serverless computing. ★ 37k gvisor Application Kernel for Containers ★ 20k pyodide Pyodide is a Python distribution for the browser and Node.js based on WebAssembly ★ 15k E2B Open-source, secure environment with real-world tools for enterprise-grade agents. ★ 14k kubernetes Production-Grade Container Scheduling and Management ★ 128k
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 →
Versions, why it is listed, for AI to read
For AI agents
- Interfaces：its own app or website
- Machine-readable record：/api/v1/software/agent-sandbox.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22