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

What you can do with Paddock

Paddock is a native Rust inference server that runs open AI models on NVIDIA GPUs and Apple Silicon, with OpenAI and Anthropic compatible APIs and a built-in web Studio.

Trended earlier

truespar/paddock 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

  • Serve an open model to several coding agents at once

    Run one local model behind an OpenAI-compatible API that multiple agent sessions can share.

    View prompt
    Using the Paddock repo at truespar/paddock, configure my coding agent to use the locally served model at <local-server-address> through its OpenAI-compatible chat completions API. Return the base URL and model name the agent should use. Verify by sending one short chat completion request and confirming a non-empty reply.

  • Compare a local model with a cloud model in Studio

    Send the same prompt to a model on your box and a model behind OpenRouter, then view the answers together.

    View prompt
    Using the Paddock repo at truespar/paddock, set up a side-by-side comparison in the Studio between a local model at <local-model-name> and a cloud model at <cloud-endpoint>. Output the prompt and both replies. Verify that both answers appear in the same view for the same prompt.

  • Turn scanned pages and PDFs into text with OCR

    Read a page as plain text or as labelled blocks with their positions, using a local OCR model.

    View prompt
    Using the Paddock repo at truespar/paddock, run the LightOnOCR-3 model on the PDF at <path-to-pdf> and return the text of the first page. Verify by comparing the output with the page visually for any obvious missed or wrong words.

  • Fill a missing table column from labelled rows

    Paste a table with labelled rows and let Kumo Tabular predict the missing column for new rows.

    View prompt
    Using the Paddock repo at truespar/paddock, send the labelled rows in <table-file> to the /v1/tabular/predictions endpoint with Kumo Tabular and return the predicted values for the unlabelled rows. Verify by checking that the number of predictions equals the number of unlabelled rows.

  • Transcribe a recording and show who spoke when

    Get a transcript and a speaker timeline for a recording of up to 10 minutes on your own machine.

    View prompt
    Using the Paddock repo at truespar/paddock, transcribe the audio file <path-to-audio> and run speaker diarization on it. Return the transcript with speaker labels. Verify that the audio is under 10 minutes long before running diarization.

How to use Paddock

  1. Check you have what it needs: An NVIDIA GPU with the NVIDIA driver installed, or an Apple Silicon Mac running macOS 26 or later; Download access to the Paddock release page on GitHub (Windows, Linux, Linux arm64 on DGX Spark, or macOS); Disk space for the model checkpoints you choose to download.
  2. Open truespar/paddock on GitHub and read the README and license.
  3. Install the NVIDIA driver on the machine, since that is the only requirement on NVIDIA systems.
  4. Download the Paddock release for your platform from the GitHub releases page.
  5. Run paddock to start the manager and open the browser-based Studio.
  6. In the Studio, download a model from the Models tested list, such as a Qwen or Gemma 4 model, and start serving it.

These steps come from our top use case, Serve an open model to several coding agents at once, which also has a copy-paste agent prompt.

Paddock alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forWritten for developers, ML engineers and small teams that want to run open models on their own NVIDIA or Apple Silicon hardware.
  • Why it is hot
  • LanguageRust
  • Sourcegithub.com/truespar/paddock · Back to Hot repos

Requirements

  • An NVIDIA GPU with the NVIDIA driver installed, or an Apple Silicon Mac running macOS 26 or later
  • Download access to the Paddock release page on GitHub (Windows, Linux, Linux arm64 on DGX Spark, or macOS)
  • Disk space for the model checkpoints you choose to download
  • For cloud comparison: an account with an OpenRouter or other OpenAI-compatible endpoint, if you want to compare against a cloud model

Add this badge to your README

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

Markdown 

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

HTML 

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

A static image, no tracking script. About the badge

Questions about Paddock

What is Paddock?

Paddock is a native Rust inference server that runs open AI models on NVIDIA GPUs and Apple Silicon, with OpenAI and Anthropic compatible APIs and a built-in web Studio. It is an open-source project on GitHub: https://github.com/truespar/paddock.

Who is Paddock for?

Written for developers, ML engineers and small teams that want to run open models on their own NVIDIA or Apple Silicon hardware.

What can I do with Paddock?

5 use cases so far, for example: Serve an open model to several coding agents at once; Compare a local model with a cloud model in Studio; Turn scanned pages and PDFs into text with OCR. Each has steps and a copy-paste agent prompt.

What do I need to run Paddock?

An NVIDIA GPU with the NVIDIA driver installed, or an Apple Silicon Mac running macOS 26 or later; Download access to the Paddock release page on GitHub (Windows, Linux, Linux arm64 on DGX Spark, or macOS); Disk space for the model checkpoints you choose to download; For cloud comparison: an account with an OpenRouter or other OpenAI-compatible endpoint, if you want to compare against a cloud model.

What are alternatives to Paddock?

Other hot AI repos in Software and DevOps: Omarchy Local AI, Hermes Plan Mode, Agent 2, Agnes Harness, Skills.

Is Paddock 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.