A local tool scrubs private details before using ChatGPT or Claude
`vault-engine` runs on Ollama and cleans sensitive text before it is sent to such as ChatGPT or Claude. Its default setup uses the `qwen3.6:27b` to find parts of the text that may identify a person. The model only detects where those parts are; the code then replaces them with stable tokens using fixed rules.
This means the original wording is not rewritten, and the changes can be reversed later. The map between the tokens and the original private details stays on the user’s own computer. Files can be cleaned with `vault-engine scrub notes.txt`, and clipboard text can be cleaned with `vault-engine clip`.
The detection model can be swapped with one option. The tool has no , uses the , and is described as best-effort de-identification, not full anonymization.
Key points
- It cleans private details before text is sent to ChatGPT, Claude, or another .
- The default detection model is `qwen3.6:27b`, but it can be changed.
- The tool replaces detected details with stable tokens and can restore them later.
- The stays local on the user’s computer.
- It is best-effort de-identification, not full anonymization.