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

What you can do with Quackd

quackd is a Python command line that connects robots you own, gives each one an LLM as its pilot, and lets you command one robot or a flock with a goal.

Trended earlier

rokbenko/quackd on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

Authorization notice. This tool is dual-use. Only use it on software, sites and systems you own or have explicit permission to test, and follow the relevant licenses and terms of service.

What do you want to do?

5 use cases

  • Try a duck goal in the simulator with no robot

    Run a goal like find the ball and kick it on a simulated Microduck with no hardware.

    View prompt
    Using the rokbenko/quackd repo, install quackd[microduck], register a simulated Microduck under the name <robot-name>, then run quackd run --goal "Find the ball and kick it" against it. Report the final status and the list of skills the model called. Verify that the run ends with success rather than an abort.

  • Command a real SO-101 arm with a plain-English goal

    Give an SO-101 arm a goal from the terminal and let an LLM pick each joint call.

    View prompt
    Using the rokbenko/quackd repo, register an SO-101 arm over lerobot:real under the name <arm-name> with a rest pose, then run quackd run --goal "Wave to the camera with an extended arm". Report the list of calls the model made and whether the arm returned to rest. Verify that the arm is at its rest pose after the run before starting another goal.

  • Rehearse arm task files in simulation before the arm

    Test an SO-101 task file in the arm's simulator before it touches real hardware.

    View prompt
    Using the rokbenko/quackd repo, pick a task file from docs/examples/lerobot/, run it against a simulated SO-101 arm registered as <arm-name>, and report whether the run completed. Verify that the same task file is then run against the real arm only after the simulated run succeeds.

  • Command a robot from a Claude chat window

    Send a goal to one of your registered robots from Claude over MCP.

    View prompt
    Using the rokbenko/quackd repo, set up the MCP connection so Claude can reach quackd, then send the goal "Find the ball and kick it" to a robot registered as <robot-name>. Report what Claude returned and the final status. Verify that quackd applied the robot's skill list and step limit to the run.

  • Split one goal across a flock of simulated robots

    Give a flock a goal so each robot's model divides the work by messaging the others.

    View prompt
    Using the rokbenko/quackd repo, register two simulated robots as <robot-a> and <robot-b>, group them into a flock named <flock-name>, and run the goal "Split the search, the closest duck kicks." Report which robot kicked and the calls each robot made. Verify that both robots received their own model pilot and that the goal completed.

How to use Quackd

  1. Check you have what it needs: Python installed on a laptop or computer; An API key for one hosted model (Claude, OpenAI, Gemini, Grok and others), or a local model served by Ollama, vLLM, llama.cpp or LM Studio; For the simulated duck: the quackd[microduck] extra.
  2. Open rokbenko/quackd on GitHub and read the README and license.
  3. Install Quackd with the microduck extra: pip install "Quackd[microduck]" (inferred, check the README)
  4. Register the simulated Microduck once by name using the Quackd registration command in the README (inferred, check the README)
  5. Run: Quackd run --goal "Find the ball and kick it"
  6. Read the run output and confirm the ball kick succeeded

These steps come from our top use case, Try a duck goal in the simulator with no robot, which also has a copy-paste agent prompt.

Quackd alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forRobotics hobbyists and developers who own or plan to build a supported robot and want to drive it with a language model from a terminal or chat.
  • Why it is hot
  • LanguagePython
  • Sourcegithub.com/rokbenko/quackd · Back to Hot repos

Requirements

  • Python installed on a laptop or computer
  • An API key for one hosted model (Claude, OpenAI, Gemini, Grok and others), or a local model served by Ollama, vLLM, llama.cpp or LM Studio
  • For the simulated duck: the quackd[microduck] extra
  • For real hardware: a supported robot such as the SO-101 arm over LeRobot, plus its serial or USB connection
Maintain Quackd? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/rokbenko-quackd.svg)](https://dedupedai.com/use-cases/rokbenko-quackd/?ref=badge)

More badge styles and HTML

Questions about Quackd

What is Quackd?

quackd is a Python command line that connects robots you own, gives each one an LLM as its pilot, and lets you command one robot or a flock with a goal. It is an open-source project on GitHub: https://github.com/rokbenko/quackd.

Who is Quackd for?

Robotics hobbyists and developers who own or plan to build a supported robot and want to drive it with a language model from a terminal or chat.

What can I do with Quackd?

5 use cases so far, for example: Try a duck goal in the simulator with no robot; Command a real SO-101 arm with a plain-English goal; Rehearse arm task files in simulation before the arm. Each has steps and a copy-paste agent prompt.

What do I need to run Quackd?

Python installed on a laptop or computer; An API key for one hosted model (Claude, OpenAI, Gemini, Grok and others), or a local model served by Ollama, vLLM, llama.cpp or LM Studio; For the simulated duck: the quackd[microduck] extra; For real hardware: a supported robot such as the SO-101 arm over LeRobot, plus its serial or USB connection.

What are alternatives to Quackd?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Quackd 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.