
sandbox-agent
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

Let your AI go full send. Your home directory stays home.

Code for paper "ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents"

Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review.

WASM sandbox with capability enforcement for AI agent code. Agents can only call explicitly provided tools with defined constraints. Sandboxed…

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.


Rootless container runtime and sandbox that launches kernel-enforced OCI images in milliseconds with no daemon, featuring resource profiles, seccomp…

Capability-based WASM runtime for executing untrusted AI-generated code with enforced CPU, memory, time, I/O, and filesystem limits. Provides…

Isolated JavaScript sandbox for Node.js that runs untrusted code with restricted access to built-in modules and host resources via Proxy-based…

A secure low code deception runtime framework, leveraging AI for System Virtualization.

Benchmark for evaluating AI agents on real-world tasks including vulnerability resolution, code debugging, and protein assembly in containerized…

PoC exploit for CVE-2026-64561, a KVM/x86 shadow MMU use-after-free enabling guest-to-host escape with kernel root code execution on the host.

Source code of a multiple series of tutorials about the hypervisor. Available at: https://rayanfam.com/tutorials

HyperDeceit is the ultimate all-in-one library that emulates Hyper-V for Windows, giving you the ability to intercept and manipulate operating system…

Macro-header for compile-time C obfuscation (tcc, win x86/x64)

Secure code execution

Sandbox untrusted code with safe access to the host.