Canonical page: https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/

Language: English. Source snapshot: 2026-10-21. Generated: 2026-10-21T13:31:28.274Z.

[Home](https://koalavps.com/) / [Explore](https://koalavps.com/resources/) /  The KoalaVPS field notes

The KoalaVPS field notes

# Make an agent a service, not a forgotten terminal.

Run long-lived workers with explicit state, bounded permissions and a recovery plan.

[Find your VPS](https://koalavps.com/vps/)

## IN THIS DOCUMENT

[Package the worker](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-1)[Save progress before actions matter](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-2)[Add useful observability](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-3)[Set a clear ceiling](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-4)[Use a supervisor and a deliberate schedule](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-5)[Set a daily budget and a duplicate boundary](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-6)[Give a periodic job an explicit catch-up policy](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-7)[Differentiate a crash loop from a stalled worker](https://koalavps.com/guides-run-ai-agent-24-7-on-a-vps/#section-8)[Knowledge base](https://koalavps.com/resources/)

## Package the worker

Use a supported runtime, pinned dependencies and a service manager or container. Configure restart limits and a dedicated service user. Keep private provider credentials in protected configuration outside the application’s public files.

## Save progress before actions matter

Use a durable queue or database for jobs. Assign a unique operation identifier, record external requests and reconcile uncertain outcomes. A restart should not send a second email, create a second order or charge twice.

## Add useful observability

Monitor job completion, queue age, error rate and cost rather than checking only whether a process exists. Keep logs small enough to review and redact tokens, prompts and documents that do not need to be retained.

## Set a clear ceiling

Limit model spending, browser concurrency, runtime and retry count. Keep an easy pause switch and a human review path for consequential actions. A smaller, well-observed worker is easier to trust than an unrestricted one.

## Use a supervisor and a deliberate schedule

Systemd and Docker are common ways to make a process survive a terminal disconnect. For a systemd service, Type=exec can report execution failure more directly than a simple background launch, and Restart=on-failure can restart failures with a bounded policy. Scheduled jobs should avoid overlapping runs. Keep the working directory, service user and environment explicit. The example assumes the koala-agent user, virtual environment, worker module and private environment file already exist; adapt them before installing a unit.

- Use a dedicated service account

- Set a restart delay and failure ceiling

- Check the previous job state before starting a scheduled run

```
[Unit]
Description=Example agent worker
After=network-online.target

[Service]
Type=exec
User=koala-agent
WorkingDirectory=/opt/koala-agent
EnvironmentFile=/etc/koala-agent.env
ExecStart=/opt/koala-agent/.venv/bin/python -m worker
Restart=on-failure
RestartSec=10
NoNewPrivileges=true

[Install]
WantedBy=multi-user.target
```

Official documentation: [Systemd service semantics](https://www.freedesktop.org/software/systemd/man/latest/systemd.service.html)

## Set a daily budget and a duplicate boundary

Give the worker a maximum request count, spend limit and execution timeout. Use a durable idempotency record for actions that affect the outside world. A successful browser click can occur before the process receives a response; inspect the external state before trying it again. Docker Compose secret mounts can keep a secret out of the image, but permissions and the consuming application still need review.

Official documentation: [Docker Compose secrets](https://docs.docker.com/compose/how-tos/use-secrets/)

## Give a periodic job an explicit catch-up policy

Use a long-running service for a persistent queue worker and a timer-triggered oneshot service for a bounded scheduled task. With a systemd calendar timer, Persistent=true can trigger one missed activation after downtime; it does not recreate an entire business backlog. Decide whether that catch-up is desirable. RandomizedDelaySec can spread starts, while an application-level lease prevents two replicas from processing the same scheduled work.

- Record the intended timezone and inspect the next run times before enabling the schedule.

- Keep the task’s execution deadline shorter than an interval that must not overlap, or use a durable lease with expiry and ownership.

- Make the job select outstanding work from stored state rather than assuming that every previous timer event ran.

- Check the installed systemd version before using a directive from the latest manual.

```
# Read-only checks after creating your own matching units.
systemctl list-timers --all
systemctl status koala-agent.service
journalctl -u koala-agent.service --since today --no-pager
```

Official documentation: [systemd: timer scheduling](https://www.freedesktop.org/software/systemd/man/latest/systemd.timer.html)

## Differentiate a crash loop from a stalled worker

A restart policy can recover a failed process, but repeating an invalid credential or broken migration every few seconds makes a fault noisier. Bound service starts and alert on repeated failure. A live process can also be stuck: measure age of the oldest job and the last completed operation. Test an API outage, an empty disk and a process stop with disposable jobs, then verify that the durable state prevents duplicate external actions.

- Set a provider budget and request timeout in the application as well as a CPU/memory boundary on the runtime.

- Docker containers have no useful workload-specific memory limit just because they are containers; configure and test limits deliberately.

- Store a secret outside the image and public tree, then test that crash logs and diagnostics redact it.

- Keep a manual stop route and require appropriate review for spending, production writes or external messages.

Official documentation: [systemd: service supervision](https://www.freedesktop.org/software/systemd/man/latest/systemd.service.html) · [Docker: container resource constraints](https://docs.docker.com/engine/containers/resource_constraints/)

KEEP EXPLORING

## Continue reading.

[Products ### A dependable habitat for your agents. Run schedulers, browser workers, queues and automation processes on infrastructure you control. Keep every agent inside a clear pe…](https://koalavps.com/agentic-vps/)[Guides ### Automation with a clear stop button. A good automation system has a narrow job, visible state and a predictable response to uncertainty.…](https://koalavps.com/automation-safety/)[Products ### Keep the intelligence. Own the runtime. Host the services around your AI workflow: retrieval, document processing, tool execution, webhooks and observability. Build a sys…](https://koalavps.com/ai-agent-hosting/)

CONFIGURE YOUR INFRASTRUCTURE

## Take control. Deploy on your terms.

No identity paperwork. Full administrator access. Crypto-native billing.

[Select a configuration](https://koalavps.com/vps/)