AI for Linux system operations.
Tell rootuno what you need in plain English. It reads your system's actual state before touching anything, makes the change, and reports back — the way a careful sysadmin would, on call at any hour.
> the disk is almost full on this box, sort it out running: df -h / running: du -sh /var/log/* | sort -rh | head running: journalctl --disk-usage ⚠ agent wants to run: journalctl --vacuum-size=200M proceed? [y/N] y running: journalctl --vacuum-size=200M ✓ freed 4.1G — journal logs were the culprit (was 91% full, now 58%). rotated old logs, left everything else untouched. nothing else on this host looks abnormal.
One agent, three different reasons to trust it
rootuno isn't a chatbot bolted onto a terminal. It's designed so engineers can inspect exactly what it did, and leadership can trust what it's allowed to do unsupervised.
Real commands, not a black box
Every action is an actual shell command, file read, or file write — visible, inspectable, and no different from what you'd run by hand. The agent loop is a small, readable Go codebase, not a hidden framework.
Investigates before it acts
rootuno reads logs, config, and current state first, then makes the smallest change that solves the problem — the same discipline you'd expect from a careful on-call engineer.
Nothing destructive without sign-off
Commands that could cause real damage — deletions, service removals, firewall changes — are held for a human "yes" before they run. Automation you can put in front of a production server.
Three steps, every time
No playbooks to write, no YAML to maintain. You describe the outcome; rootuno figures out the path.
Describe the task
"Free up disk space," "find out why nginx is 502ing," "add a swap file" — say it the way you'd say it to a colleague.
It investigates first
rootuno inspects logs, processes, and config to confirm what's actually going on before changing anything.
It acts, and reports back
Non-destructive steps run immediately. Anything risky pauses for your approval — then you get a plain-English summary of what happened.
Root access, held accountable
Giving an agent root on a real server only works if there's a hard line between "look around" and "change something irreversible." rootuno draws that line automatically.
Destructive-command detection
Deletions, disk operations, reboots, firewall flushes, and service/package removal are pattern-matched and flagged automatically — before they run, not after.
Protected system paths
Writes to /etc, /boot, systemd units, SSH configuration, and other sensitive locations require explicit confirmation, regardless of how the change was requested.
Human-in-the-loop by default
Flagged actions stop and wait for an explicit yes/no. Decline, and rootuno explains what it wanted to do and why — it doesn't retry silently.
Nothing hidden
Every command it runs is a real, visible command — never an opaque API call into your infrastructure you can't audit afterward.
Bring it to your infrastructure
rootuno currently administers a single host at a time, with fleet-wide control on the roadmap. If you're evaluating it for your own servers, we'd like to hear from you.
status: single-host control live · multi-host fleet management in development