Skip to content
#

AI Sandbox

ai-sandbox logo

An AI sandbox is a secure, isolated runtime environment designed to execute AI-generated code, run autonomous agents, and evaluate large language model (LLM) outputs without risk to the host system. Sandboxes prevent untrusted code from accessing the network, filesystem, or other sensitive resources. Common approaches include container-based isolation (Docker, gVisor), WebAssembly runtimes, and MicroVM hypervisors. AI sandboxes are foundational to agentic AI systems where LLMs write and execute code on behalf of users.

Here are 28 public repositories matching this topic...

Lightweight MicroVM engine built on Cloud Hypervisor. Features include OCI and cloud image support, instant snapshot and clone via reflink, Windows 11 guest support, CNI networking with TC redirect, memory balloon, hugepages, and a Docker-like CLI. Designed for AI sandboxing, cloud desktops, and ephemeral dev environments.

  • Updated Jun 15, 2026
  • Go

Agent Reference Stack for Kubernetes (kars) - an open source stack from Microsoft for running AI agents safely on Kubernetes. Multi-runtime, Foundry-aware, hardened per-agent sandboxes, governed egress, end-to-end encrypted inter-agent mesh.

  • Updated Jun 19, 2026
  • Rust
Fire-Gem

FIREGEM is a high‑speed cyborg LLM shell for running GGUF models locally on Windows. A native FIREGEM.exe kernel‑style console, built for desktop power and instant offline AI. Fast, lightweight, and fully local your god‑tier Windows LLM environment. It does what you expect from LLM Studio in a small CVBGOD Open Source Shell. AI uses GGUF and LLMA.

  • Updated Jun 4, 2026
  • Batchfile