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

How to watch a proactive agent open an incident with Durable Pi

Run the demo where an agent starts on its own, investigates a failing checkout and waits for your deploy approval.

Who it is forAn engineer evaluating proactive AI agents who needs to see how an agent reacts to a production log signal before trusting one with real work.

The problemIt is hard to judge a proactive agent from a description alone, and a deploy step needs a human decision.

The outcomeA running demo at the printed URL in which the agent asks to deploy at about 30 seconds and waits for your decision.

What you need first

  • Node.js 24
  • just
  • zsh
  • An OpenRouter API key for OPENROUTER_API_KEY in .env
  • For remote devices: passwordless ssh, and an exe.dev account for exe.dev VMs

Steps

  1. Run just proactive install.
  2. Run just proactive build.
  3. Run just proactive take and open the URL it prints.
  4. Wait for the agent to ask to deploy, then decline, question or approve the deploy in the web UI.
  5. Run just proactive stop when finished.

Prompt for your agent

In the Durable Pi repo at <repo path>, run `just proactive take` and capture the printed URL. Report the URL and whether the agent asked to deploy within about 30 seconds. Verify that the deploy task is waiting for approval and has not run.

Caveat. The demo uses a mock production log stream, and the README gives per-row and per-incident costs for the Jev and agent models, so check costs against your OpenRouter account before running it repeatedly.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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