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

How to attach a terminal to a running agent and steer it with Durable Pi

Reconnect from the terminal to an agent on a device and send it follow-ups or interrupts.

Who it is forA developer who prefers the terminal and wants to check on or redirect an agent that is already working on a device.

The problemClosing a terminal normally loses the working context, and the agent should not stop when the client does.

The outcomeA terminal view of the agent where you can send, steer, queue or interrupt work, and where the agent keeps running after you exit.

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. Make sure the device server is running with just backend run.
  2. Run just tui attach local to open the local device.
  3. Press Enter to send or steer, Alt+Enter to queue a follow-up, and Esc to interrupt.
  4. Press Ctrl+C on an empty prompt to exit, then run just tui attach again to reattach.

Prompt for your agent

In the Durable Pi repo at <repo path>, run `just tui attach local` against a running device server. Report the session and agent names shown. Verify that after Ctrl+C the agent is still running by reattaching and seeing its latest transcript.

Caveat. The terminal client needs a registered device, so complete the local setup first with `just net up local`.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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