DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Retinue: what you can do with it

Retinue is a self-hosted task board where humans and AI agents work the same cards, with holder-only writes, acceptance checks, and an append-only receipt chain.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

  • Assign work cards to AI agents and check results on one board

    Give each agent a card with one holder, an acceptance line, and a receipt trail you can review.

    View prompt
    Using the Retinue repo at <repo path>, start the hub with docker compose up --build and confirm /api/health returns status ok. Create a card for actor worker-1 with the acceptance line in <acceptance text>, then claim it and post progress through the update endpoint. Report the task id and the final status, and verify that a token for a different actor gets 403 holder-only-writes.

  • Connect a coding agent to the board through MCP

    Let Claude Code or Codex read and update Retinue cards without hand-written curl calls.

    View prompt
    In the Retinue repo at <repo path>, install retinue[mcp], start retinue-server mcp, and register it with this agent. Claim the card <task id> and post one progress update. Report the claim and update receipts, and verify the card shows the agent as holder.

  • See token activity and model quota per agent on the Home view

    Compare how much each agent uses and how much subscription quota remains, with source labels.

    View prompt
    In the Retinue repo at <repo path>, enable the node quota collector as described in docs/node-quota.en.md and open the Home view. Report the used percentage, reset time, and report age for each enabled subscription, and verify that the Operations view labels each source and its coverage.

Quick start with Retinue

  1. Check you have what it needs: Docker with Compose installed; Host port 9219 free on the machine that will run the hub; An admin password of at least 8 characters.
  2. Open jklthinking/retinue on GitHub and read the README and license.
  3. Export RETINUE_ADMIN_PASSWORD with at least 8 characters, then run docker compose up --build from the repo folder.
  4. Run curl -fsS http://127.0.0.1:9219/api/health and confirm the JSON status is ok.
  5. Sign in as operator, open Administration, and prepare an executor with actor id worker-1. Save its one-time token outside the data volume.
  6. Open Task workspace, then Task board, then New task. Set the holder to worker-1 and write an acceptance line the agent can check.

These steps come from our top use case, Assign work cards to AI agents and check results on one board, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for jklthinking/retinue

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Retinue alternatives · Best AI repos for Work and operations

About this repo

  • Who it is forIndividuals and small teams running several AI coding agents who want one durable, auditable board they host themselves.
  • Why it is hot111 stars, launched 72 days ago
  • LanguagePython
  • Sourcegithub.com/jklthinking/retinue · Back to Hot repos

Requirements

  • Docker with Compose installed
  • Host port 9219 free on the machine that will run the hub
  • An admin password of at least 8 characters
  • Python for the optional MCP install (pip install 'retinue[mcp]')
  • An agent that can send HTTP requests or speak MCP

Add this badge to your README

Maintain Retinue? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/jklthinking/retinue.svg)](https://dedupedai.com/use-cases/jklthinking-retinue/?utm_source=github&utm_medium=badge&utm_campaign=jklthinking-retinue)

HTML 

<a href="https://dedupedai.com/use-cases/jklthinking-retinue/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=jklthinking-retinue"><img src="https://dedupedai.com/badge/jklthinking/retinue.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Retinue

What is Retinue?

Retinue is a self-hosted task board where humans and AI agents work the same cards, with holder-only writes, acceptance checks, and an append-only receipt chain. It is an open-source project on GitHub: https://github.com/jklthinking/retinue.

Who is Retinue for?

Individuals and small teams running several AI coding agents who want one durable, auditable board they host themselves.

What can I do with Retinue?

3 use cases so far, for example: Assign work cards to AI agents and check results on one board; Connect a coding agent to the board through MCP; See token activity and model quota per agent on the Home view. Each has steps and a copy-paste agent prompt.

What do I need to run Retinue?

Docker with Compose installed; Host port 9219 free on the machine that will run the hub; An admin password of at least 8 characters; Python for the optional MCP install (pip install 'retinue[mcp]').

What are alternatives to Retinue?

Other hot AI repos in Work and operations: Sprawling Agents, GPT 6 Astra Skill, Apowerb, Punctual, Work Wit AI Agent.

Is Retinue safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.