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

How to launch a task in a Herdr pane with the chosen agent with Agent Router

Let the router pick an agent, open a new Herdr pane, start it, and hand it the task.

Who it is forA developer working inside Herdr who wants to hand a planned task to the best-fitting agent without choosing one by hand.

The problemChoosing between Cursor, Claude Code, Codex, and OpenCode for each task, then starting it and passing the task, is repetitive work.

The outcomeA new Herdr pane running the chosen agent, which has received the task and confirmed it began working.

What you need first

  • Node.js 20 or newer
  • A TypeSafe API key, since routing always calls TypeSafe
  • At least one agent CLI you are logged in to: agent (Cursor), claude (Claude Code), codex, or opencode
  • Herdr, for launching agents without --dry-run
  • A config file with your accounts in the model-router home folder

Steps

  1. Complete the setup steps for installing, building, and linking router, and configure your accounts.
  2. Open a terminal pane inside Herdr so that HERDR_ENV=1 is set.
  3. Run router run "<task description>" from that pane. (inferred, check the README)
  4. Wait for the router to split a new pane, start the agent, and send the task.
  5. Run router session to see the latest launch and its details.

Prompt for your agent

In the agent-router repo, run `router run "<task description>"` from inside a Herdr pane and report the exit code. Verify that a new pane opened with the selected agent running, and that `router session` lists this launch.

Caveat. The router only launches from inside a Herdr pane, so running it from a plain terminal will fail unless you use --dry-run.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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