DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to wake an on-call agent the moment logs or metrics spike with Overtime

A watch on your logs or metrics wakes an agent within seconds to find the cause and fix or roll back.

Credentials. The agent needs access to your logs or metrics and possibly your deploy tooling, so grant only the scopes it needs and protect paths it must not change.

Who it is forAn engineer on call for a service who wants a first responder that is awake even when they are not.

The problemIncidents start at night or during other work, and the first minutes go to finding which change caused the spike.

The outcomeAn agent that wakes on a watch, investigates the cause, rolls back or fixes it, and writes a postmortem for you to review.

What you need first

  • Node.js 22.19 or newer
  • npm to install the package globally
  • One coding agent signed in, such as Claude (built in, uses your Claude Code login)
  • A repo or service the agent can access, with protected paths set if needed

Steps

  1. Run npm install -g @ukanwat/overtime to install the app.
  2. Run overtime and name the agent on-call.
  3. Brief it with the logs or metrics it should watch and what it may do: find the cause, roll back or fix, and write a postmortem.
  4. Set up a watch on your log or metric source as described in the how-it-works guide, using the watch script the agent creates. (inferred, check the README)
  5. Trigger a test event and check that the agent wakes and writes a postmortem.

Prompt for your agent

Using the Overtime repo at ukanwat/overtime, create an on-call agent with a watch on <log or metric source>. Expected output: after a test alert, a cause summary, the action taken, and a postmortem file. Verify that the agent wakes within the watch interval and asks before any change it has not been permitted to make.

Caveat. The README describes the watch as a small script that wakes the agent but does not list which log or metric sources are supported, so check that yours can be watched.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page