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

How to define custom Agents with your own models and tools with Pi Herdsman

Write Agent definitions that use your own models, tools, skills, and workflow.

Who it is forA developer with a fixed review or test workflow who wants the delegated Agents to follow it.

The problemDefault delegation may not match how a team models, tools, or steps its work.

The outcomeCustom Agent definitions that delegate with your chosen models, tools, skills, and extensions.

What you need first

  • Linux or macOS for the released install script
  • Pi and herdr installed, or the install script to set them up
  • A Git project to work in

Steps

  1. Run pi install npm:pi-herdsman
  2. Read the Agent definitions guide at docs/guides/agent-definitions.md
  3. Create one Agent definition with your chosen model, tools, and skills
  4. Run pi inside a herdr pane
  5. Type: Use <your agent name> to <task>.

Prompt for your agent

Using the pi-herdsman repo and its Agent definitions guide, create a custom Agent named <agent name> that uses <model or tool list> and delegate <task> to it in <project path>. Expected output: a completed result from the custom Agent. Verify that /agents shows the custom Agent running under the Lead session.

Caveat. The README only says you can bring your own Agent definitions, so the file format and fields are documented in the Agent definitions guide, not here.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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