Introduction
CrowNest gives AI agents and developers safe cloud sandboxes for running commands, managing files, exposing previews, and collecting artifacts.
CrowNest provides safe cloud sandboxes for AI agents and developers. Each sandbox is an isolated live execution environment where you run commands, manage files, expose authenticated previews, preserve logs, and collect artifacts through a simple API.
Who it's for
CrowNest is built for AI application developers whose agents run code, install packages, process files, or host preview services. It also serves teams running many agent sessions who need org-scoped API keys, project separation, usage visibility, and quotas.
Core resources
CrowNest's API surface is organized around a small set of resources. Each one maps to a section of the API reference.
| Resource | What it is |
|---|---|
| Sandbox | An isolated live execution environment with a requested lifetime (TTL). |
| Command | A top-level process invocation record with captured logs and an exit code. |
| Workspace | The working filesystem area inside a live sandbox, rooted at /workspace. |
| Artifact | A durable, indexed output you explicitly export from a sandbox to object storage. |
| Preview | An authenticated exposed HTTP service with a URL like https://p-a1b2c3.preview.crownest.dev. |
The workspace is a descriptive term rather than a resource: every file
operation acts on paths inside /workspace, and the
file APIs are confined to it.
How it fits together
A typical session moves through the resources in order. You create a sandbox, do work inside it, export anything you want to keep, and then kill it.
- Create a sandbox from a template (
base,python,node, orpython-node). The sandbox moves throughcreatingandstartingtoready. - Run commands inside the sandbox. Each invocation becomes a command record with streamed logs, an exit code, and full stdout/stderr.
- Read and write files in
/workspaceto stage inputs and inspect outputs. - Export important outputs as artifacts. The workspace is ephemeral, so only explicit exports survive the sandbox.
- Expose a port as a preview when your code hosts an HTTP service, and share its authenticated URL.
- Kill the sandbox when you're done, or let it expire at its TTL. Logs, artifacts, and the sandbox record persist after the environment is gone.
[!IMPORTANT] Artifact export is always explicit. When a sandbox is destroyed, its filesystem is gone — nothing is copied out automatically.
Where to go next
Pick the path that matches how you want to work.
- Quickstarts — get a sandbox running in minutes with the TypeScript SDK, the Python SDK, or the CLI.
- Concepts — understand sandboxes, commands, files, artifacts, previews, API keys, and usage and billing.
- References — browse the TypeScript SDK reference, the Python SDK reference, the CLI reference, and the REST API reference, including authentication and error handling.