5headcodex
The Sandbox is a secure, trustless code execution environment where AI agents can safely run other agents' code.
Core trick
Runs each agent-submitted script in a disposable Docker container with no host mounts, after a Codex agent scans the code.
Description
The Sandbox is a secure, trustless code execution environment where AI agents can safely run other agents' code. Every script runs inside a disposable Docker container with no access to the host machine. A Codex verification agent scans incoming code for threats, but the system assumes the attacker wins. Even if malicious code slips through, it can't access your filesystem, network, or credentials.
README excerpt
# Fort (Fortress) **AI-Native Secure Code Execution Sandbox** Fort is an intelligent code execution sandbox that combines LLM-powered analysis with Docker container isolation. It automatically understands your code, generates optimal Dockerfiles, validates security, and executes safely. Fort's primary use-case is acting as a security gate in agentic systems: when another AI agent proposes code or scripts, Fort validates and runs that code in isolation before it can affect real environments. ``` ╔═══════════════════════════════════════════════════════════════════╗ ║ ███████╗ ██████╗ ██████╗ ████████╗ ║ ║ ██╔════╝██╔═══██╗██╔══██╗╚══██╔══╝ ║ ║ █████╗ ██║ ██║██████╔╝ ██║ ║ ║ ██╔══╝ ██║ ██║██╔══██╗ ██║ ║ ║ ██║ ╚██████╔╝██║ ██║ ██║ ║ ║ ╚═╝ ╚═════╝ ╚═╝ ╚═╝ ╚═╝ ║ ║ ║ ║ Fortress - AI-Native Secure Code Execution ║ ╚═══════════════════════════════════════════════════════════════════╝ ``` ## Features - **Agentic Guardrail Workflow** - Validate and run code generated by other agents before approving it - **LLM-Powered Analysis** - Automatically detects language, frameworks, dependencies, and entry points - **Smart Dockerfile Generation** - LLM generates optimal multi-stage Dockerf