JettsonTHE AGENT SANDBOX THAT SURVIVES CRASHES

Thesandboxyouragentneverloses.

Crash, restart, and pick up exactly where it left off — with memory intact. Spawn a sandboxed Linux agent in one API call: filesystem, headless browser, shell, HTTP, persistent memory, and a signed identity, all pre-wired. Bring your own model key.

No credit cardFree tier · 1 agent-hourWORKS WITH:Anthropic SDKOpenAI SDK

THE PROBLEM

Agents demo beautifully. Then they hit production.

A stateless sandbox looks brilliant — until real traffic shows up. The host restarts mid-task, the box is wiped, and the agent loses its place. It re-runs expensive steps it already finished, or simply dies halfway through. What breaks long-running agents in production usually isn't the model. It's the infrastructure forgetting everything the moment something goes wrong.

When the host crashes
Most sandboxes: The agent loses its context and starts the task over
Jettson: Auto-restarts and resumes from the last completed step
Work already done
Most sandboxes: Re-runs steps it already finished
Jettson: Skips finished steps — no repeated work
The workspace
Most sandboxes: Wiped when the box dies, then purged on a timer
Jettson: Persists on a volume until you delete it
Memory across runs
Most sandboxes: Bolt it on yourself — or there isn't any
Jettson: Persistent memory, built in
Crash recovery
Most sandboxes: DIY checkpointing you have to build and maintain
Jettson: Built in — state is checkpointed after every step

HOW IT WORKS

Spawn a crash-proof agent in one call.

No Dockerfile, no Kubernetes, no checkpointing code to build and babysit.

  1. Spawn in one call

    One API call returns a sandboxed Linux agent — filesystem, headless browser, shell, HTTP, persistent memory, and a signed identity, already wired. Bring your own model key.

  2. It runs — and remembers

    Your agent works on a real machine with memory that persists across runs and a signed identity, so every action it takes is attributable and auditable.

  3. It crashes? It resumes.

    If the process or the host dies mid-task, the agent auto-restarts and picks up from the last completed step — finished work isn't repeated.

$ npm install @jettson/sdk
import { Jettson } from "@jettson/sdk"; const jettson = new Jettson({ apiKey: process.env.JETTSON_API_KEY }); // One call → a Linux box with memory, browser, shell + a signed identity.const agent = await jettson.agents.spawn({  task: "Research 10 vendors and email the top 3",}); // If the host crashes mid-task, it auto-resumes from the last step.const result = await jettson.agents.wait(agent.agent_id);console.log(result.final_result);

SEE IT RESUME

We hard-killed it mid-task. It finished anyway.

Proven end-to-end on real hardware: an agent wrote to memory, got hard-killed mid-task, auto-restarted with no human in the loop, resumed from the last completed step, and read its memory back out — without repeating completed work.

agent-run.log
DEMO · REPLAY

Illustrative replay of the exact event sequence we verified on real hardware.

BATTERIES INCLUDED

Everything a long-running agent needs, pre-wired.

One API call gives your agent a real computer — plus the two things that make it survivable and trustworthy.

Filesystem

A persistent /workspace. Files survive a crash and are still there when the agent resumes.

Headless browser

Chromium via Playwright — navigate, click, scrape, and fill forms.

Shell

Run real commands, install packages, and execute code in an isolated box.

HTTP

Outbound requests with SSRF protection — call whatever API the task needs.

SO IT SURVIVES

Persistent memory

Agents remember across runs — facts, preferences, and context persist. It survives a crash too, so a resumed agent still knows what it learned.

SO IT'S TRUSTWORTHY

Signed identity + audit trail

Every agent carries a signed identity (ES256), and every action it takes is logged. Together that's a replayable audit trail — who the agent was and exactly what it did. The trust layer regulated teams need before they deploy.

WHO IT'S FOR

Built for agents that run long enough to crash.

If your agent finishes in two seconds, you don't need us. If it runs for minutes, hours, or overnight — across many steps — losing state isn't an annoyance. It's a re-run and a double bill.

Overnight & long-running jobs

Agents that work for minutes to hours. A crash at hour two shouldn't throw the whole job away and start over.

Multi-step workflows

Research → scrape → draft → send. Every step costs tokens and time — none of them should run twice.

Stateful, memory-heavy agents

Agents that build up context as they go and can't afford to forget it the moment the host restarts.

Teams priced out of enterprise

You shouldn't need a $3,000-a-month enterprise minimum to get durable agents. Start on a $9 plan.

Just firing a single quick call? A plain stateless sandbox is fine — and cheaper. Jettson earns its keep when your agent runs long enough that losing state actually hurts.

Pricing

Durable agents, flat pricing.

Start free. Every plan runs your agents on a persistent computer that survives crashes and resumes where it left off — not raw compute you have to babysit. No surprise overage, cancel anytime.

Liftoff

$9/mo

For prototypes and side projects that still shouldn't lose state.

Monthly only · cancel anytime
Includes:
1 concurrent agent
2 agent-hours per month
15-min max single run
Persistent workspace — survives crashes & resumes
Community support
Most Popular

Lightyear

$29/mo

For agents shipping to real users — that can't afford to lose state.

Monthly only · cancel anytime
Includes:
3 concurrent agents
8 agent-hours per month
Persistent workspace per agent — survives crashes & resumes
Memory + signed identity built in
Email support

Enterprise

Custom

For teams with scale, security, and compliance needs.

Contact sales
Custom terms · annual contract
Includes:
Everything in Lightyear
Custom agent-hours & concurrency
SSO/SAML (on request)
Dedicated infrastructure (on request)
SLA & custom contracts

START FREE

Give your agent a sandbox it never loses.

Spawn a crash-proof agent in one API call — it survives crashes and resumes where it left off. Free to start, no credit card.