close

Your ops teammate that never sleeps.

OpsAgent watches your cloud day and night, read-only. Urgent problems reach you the moment they matter. Everything else waits for a calm morning briefing. It never changes anything. Today it connects to AWS.

Checks for urgent exposures every 15 minutes, day and night, and alerts you right away. Everything else waits for the morning briefing.

Alpha opens in small groups. No spam; one email when your spot is ready.

  • Read-only
  • Every 15 minutes
  • Never reads your stored data

Built for the founding engineer who owns the cloud bill, and for the developer who inherited the infrastructure when the contractor left.

While you slept

22:00–08:00

Sample night
  • Every 15 minutesurgent checks
  • 1 urgent alertsent at 03:12
  • 0 changesto your cloud

  1. Urgent alert sent to #opsDatabase prod-db snapshot left public

  2. Morning briefingOne short briefing in #ops

Everything else waits for your morning briefing.
  • 15 minbetween urgent exposure checks, day and night
  • 10checks run every night against your account
  • 0write permissions: it cannot change anything
  • 1short briefing a morning, skipped when nothing changed

While you sleep, and when you wake

  • While you sleep

    Urgent exposures are checked every 15 minutes.

  • When it's urgent

    An alert in Slack, or email if Slack isn't connected.

  • Every morning

    One short briefing, skipped when nothing changed.

How it works

  1. Connect read-only

    Create a role in one click. It can read how your cloud is set up and what it costs, and it cannot read your stored data or change anything, except what you opt into (see Security). Today that means AWS.

  2. Checks run

    Deterministic checks run against your account. Fixed rules decide what is wrong, with no AI guessing.

  3. Briefing and alerts

    A morning briefing in Slack, exceptions only and skipped when nothing changed, plus a weekly report. Urgent exposures reach you within minutes.

See how it works

Inside OpsAgent

Sample screens from a test account: the dashboard, one finding, and the briefing it sends.

Sample dataSample OpsAgent dashboard: setup checklist and the acme-prod account with its posture score and open findings by severity
Posture score and open findings by severity, per connected account.
Sample dataSample OpsAgent finding: a critical certificate expiring in 3 days, with its next step and the evidence it was based on
Every finding names the resource, the next step and its evidence.
Sample dataSample OpsAgent morning briefing email for acme-prod, listing open findings by severity with a link to the dashboard
The morning briefing, by email when Slack is not connected.

What it checks

Ten checks run every night. Each finding names the resource and shows the evidence, so you can confirm it yourself.

  • Idle resources and cost anomalies

    Things you pay for that nobody uses, and spend that jumps for no clear reason.

  • IAM hygiene

    Old access keys, users without MFA, and admin access nobody needs.

  • Public exposure

    Storage, databases and open ports that anyone on the internet can reach.

  • Backup coverage

    Which resources have backups, and whether the permissions to restore them are in place.

  • Certificate expiry

    Certificates close to expiring, flagged before your users see the error.

  • Logging and detection gaps

    Audit logs and threat detection that are switched off or incomplete.

  • Idle GPUs and stuck training jobs

    GPU machines doing nothing, and training jobs that stopped making progress.

  • Encryption at rest

    Database storage, disks and snapshots that are not encrypted.

  • Instance hardening

    Servers that still accept the older metadata service (IMDSv1).

  • Credential depth

    Access keys never used, users with two active keys, and stale console passwords.

What it will never do

  • Write to your infrastructure

    Its role has no write permissions, so it cannot change, stop or delete anything.

  • Read your data

    It cannot read your stored data (objects, database rows, secret values); it reads configuration, metadata and billing, plus a few scoped reads you opt into, listed on the Security page.

  • Spam you with noise

    Only urgent findings will ever interrupt you, and only on the channels you choose. Everything else waits for your morning briefing.

  • Send your data to AI without asking

    Dashboard AI stays off until an owner turns it on, and MCP traffic never touches OpsAgent's model key.

OpsAgent for iOS and Android: alerts and briefings in your pocket.

Coming soon

Tuesday

03:12

OpsAgentnow

Urgent alert

Database prod-db snapshot left public

Sample

Bring your own AI

Use Dashboard AI, or bring your own agent or model key.

Point Claude, Cursor or any other MCP client at OpsAgent and ask about your findings in plain words. Or ask Dashboard AI for explanations and chat, on OpsAgent's key or your own.

MCP serverhttps://brain.opsagent.dev/mcp

Connect your agent

Get your ops teammate.

The alpha opens to a few teams at a time. Join the waitlist and we will email you when your spot is ready.