AIFIRST Vomit: Clean Up Claude's Token Output with a Separate LLM
The brief
Vomit is a small open-source tool that intercepts Claude agent mode's intermediate reasoning output and pipes it through a local LLM to produce more readable English summaries.
Key points
- It runs fully locally with no telemetry, supports Llama.app and Ollama backends, and can be used either as an integrated hook replacing Claude's displayed output or as a standalone session monitor via the 'vomit tail' command.
- The tool targets the verbosity of Claude's token output during agentic tasks.
Sources
- HNgithub.com
- Source codegithub.com