Zero, your trustworthy AI teammate for real work.
-
Updated
Jun 19, 2026 - TypeScript
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.
Zero, your trustworthy AI teammate for real work.
ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers
Agent-Sandbox is an E2B compatible easy-to-use enterprise-grade sandboxes for AI Agents. Allows Agents to securely run untrusted LLM-generated Code, Browser use, Computer use, and deploy Website etc.
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.
Slightly less YOLO version of pi-coding-agent in Docker container sandbox
AI coding agent sandbox: run Claude Code in isolated Docker containers behind an egress firewall — self-hosted & free
mkenv is a fast, secure, reproducible local isolated development environment generator.
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.
Collection of AI CLI wrappers: Run AI CLI tools (OpenAI Codex, Google Gemini, OpenCode, Claude Code) inside Docker to keep your host clean while persisting CLI auth/config on your machine.
An agent sandbox with VFS and bash command-line interface for server-side AI agents. Built with .NET.
Sandbox platform for testing and evaluating autonomous agents
agentmoat moves Kubernetes workloads from the default runc runtime to gVisor (runsc), the user-space kernel that defends against the kernel-exploit step of a container-escape chain.
Use Claude Code credentials for OpenCode Anthropic auth without a separate login or API key
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.
AI Sims meets EVE Online — a real-time virtual economy where AI agents live, trade, build companies, and compete across 80+ regions
Fork of e2b-dev/E2B -- Open-source, secure environment with real-world tools for enterprise-grade agents.
A deny-by-default sandbox for AI coding agents (Claude Code, Cursor, Aider, Codex). One binary. Pure Go. macOS and Linux.
Autonomous software engineering platform. LangGraph multi-agent system (planner → executor → reviewer) with sandboxed execution, security scanning, human-in-the-loop gate, OTel observability, semantic cache, and CI/CD integration. 1,568 tests · 93% coverage.