How to keep an AI agent running for hours in a cloud sandbox

On Runtime an eight-hour agent run costs about 26 cents on a 2 vCPU, 4 GiB sandbox that spends most of its time waiting on its model, because Runtime bills the CPU the agent's commands use, not the CPUs it holds. At the rates in effect on 25 October 2026, that sandbox costs $0.03125 an hour while it waits and $0.08 an hour with both CPUs busy. A busy sandbox is not paused by a timer. If credit or a spending cap runs out, the default is to pause, so the agent's memory and processes are kept rather than lost.

The short answer

Create a paid sandbox with a spending cap and no time limit. Copy the agent into it, and start it as a background process. Save the two ids. They are all you need to come back:

TypeScriptimport { Sandbox } from "withruntime";const sbx = await Sandbox.create({  name: "agent-run-981",  // No timeoutSeconds: it runs while the agent works, however long that is.  maxTotalCostMicros: 5_000_000, // never more than $5 over its life  diskMiB: 8192,  labels: { kind: "long-agent", run: "981" },});await sbx.files.upload("./agent", "/workspace/agent");const agent = await sbx.spawn("python3 main.py --task 'Port the test suite to Vitest'", {  cwd: "/workspace/agent",});console.log(sbx.id, agent.id); // keep these in your database

Pythonfrom withruntime import Sandboxsbx = Sandbox.create(    name="agent-run-981",    # No timeout_seconds: it runs while the agent works, however long that is.    max_total_cost_micros=5_000_000,  # never more than $5 over its life    disk_mib=8192,    labels={"kind": "long-agent", "run": "981"},)sbx.files.upload("./agent", "/workspace/agent")agent = sbx.spawn("python3 main.py --task 'Port the test suite to Vitest'", cwd="/workspace/agent")print(sbx.id, agent.id)  # keep these in your database

A process started with spawn belongs to the sandbox, not to your connection. Your server can restart, deploy or crash, and the agent keeps working.

Come back to it later

Any process that has the ids can reattach, read progress and follow the output from the first byte:

TypeScriptimport { Sandbox } from "withruntime";const sbx = await Sandbox.connect(process.env.SANDBOX_ID!);const agent = await sbx.processes.get(process.env.PROCESS_ID!);console.log(agent.info.state);for await (const event of agent.output({ cursor: 0 })) {  if (event.type === "stdout") process.stdout.write(event.data);  if (event.type === "exit") console.log("agent finished with", event.exitCode);}

Pythonimport osfrom withruntime import Sandboxsbx = Sandbox.connect(os.environ["SANDBOX_ID"])agent = sbx.process(os.environ["PROCESS_ID"])print(agent.info["state"])for event in agent.output(cursor=0):    if event["type"] == "stdout":        print(event["data"], end="")    elif event["type"] == "exit":        print("agent finished with", event["exitCode"])

The sandbox keeps the latest 1 MiB of each process's output. An agent that talks for hours should also append its steps to a file, such as /workspace/progress.jsonl, which files.readText reads at any time.

What decides how long it runs

A single exec can run for up to 24 hours, and a timeout comes back as a result with the output so far, not an exception. Without credit, a sandbox runs the same way within the account's free usage; persistent needs paid credit.

Pause while it waits for a person

Long agents often stop to ask for approval. Pause the sandbox at that point. Compute billing ends once its processors stop. When the answer arrives, the agent is exactly where it was:

TypeScriptimport { Sandbox } from "withruntime";const sbx = await Sandbox.connect(process.env.SANDBOX_ID!);await sbx.pause(); // files, memory and the agent process are kept// ... hours later, when the reviewer answers:await sbx.wake();await sbx.files.write("/workspace/agent/approval.txt", "approved");

A paid pause is kept while your account has credit. While paused it pays only for the disk and memory blocks it alone owns, at $0.08 per GB per 30-day month.

Know when it ends

Ask for a webhook when a sandbox stops, so a crashed or finished agent never goes unnoticed. Also read its CPU and memory while it runs:

TypeScriptimport { Runtime, Sandbox } from "withruntime";const runtime = new Runtime();await runtime.webhooks.create({  url: "https://example.com/hooks/runtime",  events: ["sandbox.stopped", "sandbox.start_failed"],});const sbx = await Sandbox.connect(process.env.SANDBOX_ID!);const { latest } = await sbx.metrics({ range: "1h" });console.log(latest?.cpuPercent);

stopReason on the sandbox.stopped event says why it stopped (metrics and webhooks).

What an hours-long agent needs

What it costs

Take one run of 8 hours on 2 vCPU and 4 GiB, where the agent's commands use on average 0.1 of a vCPU because most of the time goes on model calls:

A hundred such runs a month cost about $26. Runtime charges $0.025 per vCPU-hour of measured CPU and $0.0075 per GiB-hour of memory while running, with no plan fee (pricing).

Start

Terminalnpx withruntime sandboxes run --keep -- python3 --version

Approve the link it prints in your browser, then follow the process of a running agent from a terminal with runtime sandboxes logs <id> <pid> -f (CLI).

Related: background agents, agent memory that persists, pause and resume a sandbox, coding agent sandbox.

Facts on this page were checked on 26 October 2026.