Code, browsers, containers, and Claude self-hosted — where your agent actually does the work.
Agents need somewhere to run code. We give them four places.
Python and Node runtimes for short evals, Chromium-based headless browsers for screenshots and agentic web use, full Alpine/Debian containers for longer-lived tasks, and Claude Managed Agents self-hosted sandboxes for teams keeping Claude tool execution off Anthropic's cloud. All four are tenant-isolated, restartable from your control plane, and metered on actual CPU-seconds — not wall-clock idle.
Why this exists
Code execution belongs next to inference.
Local round-trip
Sandboxes share a Kathmandu network with our inference and hosted-agents runtimes. The agent loop stays inside one fast path.
Tenant isolation
Each sandbox call gets a fresh, locked-down environment. Per-tenant volumes are opt-in and encrypted at rest.
Dependency-aware
Upload uv.lock, requirements.txt, package.json, or an OCI image. We cache warm environments per manifest hash.
CPU-second billing
Pay for the time your code actually runs, not idle wall-clock. Hosted-agent tenants get an included quota.
Four runtimes
Pick what your agent actually needs.
Each type is tenant-isolated, restartable from your control plane, and bills on CPU-seconds — not wall-clock idle.
Code Runtime
Python and Node sandboxes for short evals, code generation, and tool use.
See Code Runtime → →Headless Browser
Chromium-based browser sessions for screenshots, scraping, and agentic web use.
See Headless Browser → →Linux Container
Full Alpine or Debian environments — Docker-compatible, persistent, agent-accessible.
See Linux Container → →Claude Self-Hosted
Be the sandbox provider for your Claude Managed Agents — agent loop on Anthropic, tool execution on our Kathmandu GPUs.
See Claude Self-Hosted → →Comparison
Default sizes, default egress, default prices.
Sandboxes scale up per-session if needed. The defaults below are what you get without any tenant overrides.
| Type | Runtimes | Memory | CPU | Egress | Pricing |
|---|---|---|---|---|---|
| Code Runtime | Python 3.12 · Python 3.11 | 512 MB | 1 vCPU burst, 0.25 vCPU sustained | 100 Mbps | EUR 0.05 / hour |
| Headless Browser | Chromium 130+ · Playwright | 2048 MB | 2 vCPU burst, 0.5 vCPU sustained | 250 Mbps | EUR 0.18 / hour |
| Linux Container | Alpine 3.20 · Debian 12 | 2048 MB | 2 vCPU burst, 0.5 vCPU sustained | 200 Mbps | EUR 0.12 / hour |
| Claude Self-Hosted | Anthropic ant CLI (always-on poll worker) · Anthropic SDK EnvironmentWorker (Python / TypeScript / Go) | 4096 MB | 4 vCPU burst, 1 vCPU sustained | 250 Mbps | EUR 0.12 / hour |
Hosted-agent tenants get sandbox-hours included.
If you are on a Hosted Agents tier, sandbox usage at fair-use levels comes out of your tenant quota — no separate sandbox subscription needed. Standalone sandbox customers (no Hosted Agents plan) are billed at the per-hour rates above, with a transparent monthly cap.
Sandbox safety
Code execution is risky. We treat it that way.
Defaults are conservative. Network is default-deny outbound. Tenant filesystems are isolated. Abuse cuts the call before it cuts the cohort.
Get sandbox API access
No deposit. No waitlist. Tell us what you need to run.
Sandboxes are pay-per-use against the rates above — no founding cohort, no upfront fee. Tell us about your workload and we'll send your API key and dispatcher endpoint within one working day.
- Pay-per-CPU-second on standalone sandbox usage — no monthly minimum.
- Hosted Agents tenants get an included sandbox-hour quota at fair-use level.
- No deposit, no annual commitment.
- Bring your own dependency manifest (uv / requirements.txt / package.json / OCI image).
Practical questions
What to know before you reserve.
How does this compare to E2B / Modal / Daytona?
Different positioning. E2B and Modal are excellent global sandbox products; we are the obvious choice when your agent or inference is *also* running on ScaLabs Cloud — same network, lower per-call latency, single bill. We are deliberately not trying to be a global hyperscaler.
Are these sandboxes included with Hosted Agents?
Yes — hosted-agent tenants get a per-tier included quota of sandbox-hours across all three types. Standalone usage (no Hosted Agents subscription) is billed per CPU-second at the rates shown in the comparison table.
Can I run a long-lived service in a sandbox?
Code Runtime and Headless Browser sandboxes have per-session limits — they are not for daemons. Linux Container sandboxes can run long-lived processes; if they run 24/7 for months, consider converting to a VPS — usually cheaper at that point.
What about GPU sandboxes?
Not in the founding cohort. If you need GPU-backed code execution, use our Inference product (the model already runs on our GPUs) and call it from a CPU sandbox. We may add GPU sandboxes after the launch network is stable.
Do you support BYO container images?
Yes, on Linux Container sandboxes. Bring an OCI image; we run a basic security review before allowing it in the tenant. Reviewed images can be pushed by your CI and pulled on demand.
How is residential egress handled?
Off by default. Available on Headless Browser sandboxes via a separate add-on; capped per session, billed separately, and we monitor for abuse patterns. Talk to us before you build a workflow that depends on it.