|
sandboxicon.com, shared kernel, or its own?
A field guide to container and VM isolation, and what your AI coding agent actually runs with by default. Every claim is labeled by how well it's sourced.
|
88 % |
|
Sistemo — Run AI code in real microVMs
Firecracker microVMs for AI agents and untrusted code. Prepaid EU cloud, Python & TypeScript SDKs. Safer than containers, simpler than raw VMs.
|
85 % |
|
kern - rootless container runtime and sandbox
kern: rootless container runtime and sandbox with no daemon. Runs agent tool calls and LLM-generated code in kernel-enforced containers.
|
85 % |
|
Zeish: Git-like Cloning for MicroVM Sandboxes
Clone AI agent environments like git. Hardware-isolated MicroVM sandboxes with instant boot from snapshots: snapshot, branch, and fork reproducible agent wor...
|
84 % |
|
sandboxd — run AI coding agents in disposable cloud sandboxes
Give Claude Code, Codex, Cursor and other AI agents full root inside a throwaway, hardware-isolated cloud sandbox — never your own laptop. Each sandbox boots...
|
83 % |
|
Capsem -- The fastest way to ship with AI securely.
The fastest way to ship with AI securely.
|
82 % |
|
aibox — run every AI CLI in a sealed container
A Docker sandbox that runs Claude Code, Codex, and Gemini isolated from your machine: non-root, with all capabilities dropped and a separate profile per acco...
|
82 % |
|
Hotcell | Hardened Execution Environments
Hotcell runs code inside tiny virtual machines. Hardware-level isolation, sub-second boot, standard OCI images.
|
82 % |
|
Kastellan — the trustworthy personal AI agent
A personal, always-on AI agent built so that security is its foundational property. Every tool in its own kernel sandbox; every plan reviewed before it runs....
|
82 % |
|
brig: the microVM sandbox for AI coding agents
Run Claude Code, Codex and other agents inside an ephemeral microVM on Mac or Linux. Free and open source, under Apache 2.0.
|
82 % |
|
nd7 — kernel sandbox and secure audit log for AI coding agents
nd7 runs Claude Code and OpenAI Codex CLI inside a sandbox enforced by the operating system and keeps a secure audit log of what the agent did. Open source,...
|
82 % |
|
SafeYolo: Sandboxed coding agents with controlled network and service access
SafeYolo runs Claude Code, OpenAI Codex and other coding agents in isolated Linux sandboxes with controlled network, service and credential access.
|
81 % |
|
Beachead — AI Sandbox Orchestrator
Beachead — Run AI agents in isolated Docker Sandbox microVMs from your desktop. Keep your CLI agent workflow while giving agents access only to the folders a...
|
81 % |
|
Motor OS
Motor OS is a simple, fast, and secure operating system for the cloud, built entirely in Rust for virtual machines.
|
81 % |
|
SlicerVM | Real Linux, in milliseconds
Boot full Linux microVMs with systemd in milliseconds for AI sandboxes, edge workloads, and production services on Mac, Linux, and bare-metal.
|
81 % |
|
Beepod — Sandboxed environments for AI agents
Launch a sandboxed Linux environment for your AI agent. Instant terminal in your browser. Root access with strong isolation. Invite-only beta.
|
81 % |
|
Coding Sandbox — Docker Sandboxes for AI Coding Agents
Spin up isolated Docker environments for AI coding agents like Claude, Copilot, and Gemini. One click. Zero config. Download free for Mac, Windows, and Linux.
|
81 % |
|
Mentat — Private Workload Platform for Firecracker, Containers, and Binaries
Run isolated workloads on your own infrastructure. Mentat orchestrates Firecracker microVMs, Docker containers, and static binaries with a lightweight contro...
|
81 % |
|
Dangerous Sandbox — agents, off your machine
An isolated environment where AI agents can edit files, run code, and experiment — without touching your machine. Remote, kernel-isolated containers with str...
|
81 % |
|
Visor.js — The 64-Bit Linux Kernel in Native WebAssembly
A user-space Linux kernel and POSIX runtime built for 64-bit WebAssembly (wasm64). Run unmodified multi-process server daemons with native apk packages and s...
|
81 % |
Detected social media networks