Agents & code interpreters
Sandboxes for AI agents
Give every AI agent its own disposable computer with full root. Let it install packages, run shell commands, and browse a filesystem — all sealed inside an isolated Cube.
Why run this on a Cube
A real computer, fully sandboxed
An agent gets root on its own microVM with its own kernel — free to install anything and run any command, while the per-cube sandbox keeps it walled off from your other workloads.
Disposable by design
Snapshot a clean base, hand a copy to each agent run, and delete it when the task finishes. Every run starts from a known-good state and leaves nothing behind.
One API call from your agent loop
Provision, run, and tear down Cubes straight from your code with the typed SDK, or let an MCP-aware assistant manage them in natural language through the Krova Cloud MCP server.
Only pay for active runs
Sleep a Cube the instant an agent finishes and wake it in under a second for the next step. Compute is billed by the minute, so idle agents cost nothing.
How it works on a Cube
Back each agent session with a fresh Cube it can drive as its own machine.
- 1
Prepare a base image with your tools pre-installed and capture it as a snapshot.
- 2
Create a Cube from that snapshot for each agent run, so it starts clean every time.
- 3
Let the agent execute commands over SSH or the API with full root inside the Cube.
- 4
Sleep or delete the Cube when the run ends — take a snapshot first if you want to inspect it later.
Frequently asked questions
Can the agent install its own packages and run arbitrary commands?
Yes. The agent has full root inside its Cube — package managers, systemd, kernel modules, anything. The microVM boundary keeps that freedom safely contained.
What happens if an agent breaks its environment?
Nothing outside the Cube is affected. Delete it and create a fresh one from your base snapshot, or restore the snapshot to roll back instantly.
How do I connect this to my agent framework?
Use the typed TypeScript SDK or REST API to manage Cubes from your agent loop, or point an MCP client at the Krova Cloud MCP server to let the model manage them directly.
Ready to build on a Cube?
Create your account and launch an isolated Cube in under a minute. Your first $5 top-up doubles to $10 in credit — one-time.