Skip to content
Tech News
← Back to articles

Vomit: Clean up Claude 5's token output with a separate LLM

read original more articles
Why This Matters

Vomit offers a local solution to clean up Claude 5's token output by piping it through an independent LLM, enhancing privacy and control for users. While it currently has limitations like speed and potential message misses, it represents a step toward more self-contained AI workflows in the tech industry. This tool is particularly relevant for developers seeking to maintain data privacy and reduce reliance on external APIs.

Key Takeaways

Vomit

Vomit converts Claude's token vomit into English by piping it through a local LLM. It's fully local (no telemetry) and has no external dependencies.

I wrote a small blog post about this project: https://zachahn.com/posts/1787191554

Disclaimer:

The local LLM can only see what Claude tries to communicate (no access to any actions or files), so it hallucinates a bit

It's pretty slow

This is totally vibe-coded, only tested on Mac

There is a possibility you'll completely miss Claude's message. You can use something like AgentsView to get the original messages, as Vomit does not touch anything during runtime (except technically it writes files to your TMPDIR)

Install

# Install the binary to your GOPATH go install github.com/zachahn/vomit@latest # Setup connection details to your LLM vomit init # Instructions on how to replace Claude's output via hooks vomit scrub -claude

... continue reading