DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5
202 stars · Go

How to use Vomit: what you can do with it

What is Vomit? Vomit is a Go tool that rewrites Claude Code's verbose output into plain English by sending it through a local LLM.

How do I use it? Install Llama.app from https://github.com/ggml-org/Llama-macOS, then download GPT-OSS 20B through it (the README's recommended model); then run go install github.com/zachahn/vomit@latest; run vomit init to set up the connection details to your LLM. Full steps below.

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

  • Shorten Claude Code output with a local LLM

    Hook Vomit into Claude Code so a local model rewrites its verbose replies in plain English.

    View prompt
    Install the zachahn/vomit repo with `go install github.com/zachahn/vomit@latest`, then run `vomit init` against the local LLM server at <llm-endpoint> and follow the output of `vomit scrub -claude` to wire up the Claude Code hook. Report the setup steps you completed, and verify by sending one Claude Code prompt and confirming the reply is rewritten, with the original visible after ctrl-o.

  • Follow a Claude session with translated output

    Translate an existing Claude session's tokens from the side without installing the hook.

    View prompt
    Using the zachahn/vomit repo, run `vomit list` to show Claude session identifiers, then run `vomit tail` for the session <session-id>, or for the latest session if none is given. Report the session ID you followed and confirm that translated output is printed. Verify that the output reads as plain English rather than raw Claude tokens.

  • Point Vomit at a different local LLM server

    Use Ollama, Apfel, or another OpenAI-API server as the model behind Vomit.

    View prompt
    Install zachahn/vomit with `go install github.com/zachahn/vomit@latest`, then run `vomit init` pointed at the local server <server-url> that is already running. Report which server and connection details you entered, and verify by checking that a Claude Code reply is rewritten after `vomit scrub -claude` is applied.

Quick start with Vomit

  1. Check you have what it needs: Go toolchain, so `go install` works; Claude Code installed; A local LLM server such as Llama.app or Ollama, with a model downloaded.
  2. Open zachahn/vomit on GitHub and read the README and license.
  3. Install Llama.app from https://github.com/ggml-org/Llama-macOS, then download GPT-OSS 20B through it (the README's recommended model).
  4. Run go install github.com/zachahn/vomit@latest.
  5. Run vomit init to set up the connection details to your LLM.
  6. Run vomit scrub -claude and follow its instructions on replacing Claude's output via hooks.

These steps come from our top use case, Shorten Claude Code output with a local LLM, 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 zachahn/vomit

Add Deduped to Claude Code once

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

Cursor, ChatGPT, others

Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers who use Claude Code on macOS and want shorter, cheaper-to-read replies from a local model.
  • Why it is hot202 stars, launched 76 days ago
  • LanguageGo
  • Sourcegithub.com/zachahn/vomit · Back to Hot repos

Requirements

  • Go toolchain, so `go install` works
  • Claude Code installed
  • A local LLM server such as Llama.app or Ollama, with a model downloaded
  • A Mac, since the README says it was only tested on Mac

Add this badge to your README

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

Markdown 

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

HTML 

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

A static image, no tracking script. About the badge

Questions about Vomit

What is Vomit?

Vomit is a Go tool that rewrites Claude Code's verbose output into plain English by sending it through a local LLM. It is an open-source project on GitHub: https://github.com/zachahn/vomit.

How do I use Vomit?

Install Llama.app from https://github.com/ggml-org/Llama-macOS, then download GPT-OSS 20B through it (the README's recommended model); then run go install github.com/zachahn/vomit@latest; run vomit init to set up the connection details to your LLM. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Vomit for?

Developers who use Claude Code on macOS and want shorter, cheaper-to-read replies from a local model.

What can I do with Vomit?

3 use cases so far, for example: Shorten Claude Code output with a local LLM; Follow a Claude session with translated output; Point Vomit at a different local LLM server. Each has steps and a copy-paste agent prompt.

What do I need to run Vomit?

Go toolchain, so `go install` works; Claude Code installed; A local LLM server such as Llama.app or Ollama, with a model downloaded; A Mac, since the README says it was only tested on Mac.

What are alternatives to Vomit?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Vomit 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.