Skip to content
Tech News
← Back to articles

Clean up Claude 5's token vomit with a separate LLM

read original more articles
Why This Matters

Vomit offers a privacy-focused solution for translating Claude's token output into readable English by utilizing a local LLM, eliminating external dependencies and telemetry. While it enhances user control and privacy, it is currently slow and primarily tested on Mac systems, with some limitations in message accuracy. This tool highlights ongoing efforts to improve privacy and control in AI interactions within the tech industry.

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.

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

Usage

... continue reading