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

How to run a durable agent on your own machine with Durable Pi

Start a device server and web hub so an agent keeps running after you close the browser.

Credentials. The setup writes a bearer token to ~/.dpi/backend.env and copies the OpenRouter key into each device's backend.env, so keep those files private.

Who it is forA developer who wants a long-running AI agent on a laptop or server that survives closing the browser or restarting the terminal.

The problemChat sessions tied to one window stop when the window closes, and resume does not restore which tool call was running.

The outcomeA local device server on port 4780 and a web UI on http://localhost:4781 that show one durable agent you can reopen at any time.

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 cp .env.example .env, then set OPENROUTER_API_KEY in .env.
  2. Run cp dpi-network.example.yaml dpi-network.yaml.
  3. Run just install, then just net up local.
  4. Run just hub build.
  5. In one terminal run just backend run. In a second terminal run just hub start.
  6. Open http://localhost:4781 in a browser and start a session on the local device.

Prompt for your agent

In the Durable Pi repo at <repo path>, follow the Manual Install steps in the README up to starting the hub on http://localhost:4781. Report the URL that responds and the names of the device and session shown in the web UI. Verify that the device appears as local in the network tree.

Caveat. The README says remote devices need passwordless ssh and that exe.dev VMs need an exe.dev account, so start with the local device only.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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