Anonymize PII before it reaches the LLM

OpenAI, Anthropic, and Google ship the best models on the market. But every byte of context you send them, including raw user PII, leaves your jurisdiction the moment the request hits the wire. A single prompt becomes a data export.

Self-hosting keeps the data inside your network, but you give up part of the state of the art and you take on the GPU bill and the patching. The privacy gain comes with a permanent operational cost, and the model you can run is rarely the model you wish you were running.

GDPR, HIPAA, and data-residency rules apply whether or not your stack was built with them in mind. Sending raw PII to a third party is a liability you cannot undo once a request has left, and it forces every later product decision through a legal review.

Some teams respond by banning hosted LLMs outright. That protects the data, but it also forfeits the productivity gains everyone else is capturing, and people route around the ban anyway by pasting work into personal accounts the company cannot see.

Combine regex, NER, and LLM detectors in a single pipeline and keep the ones you trust. Built-in chunking splits long documents, so even large files are fully covered.

Every value becomes a stable placeholder and is restored automatically. Your users and your tools always see the real data, while the model only ever sees the placeholder.

The same value keeps the same placeholder for a whole conversation, across every message, tool call, and agent. Nothing drifts, so the model never loses track of who is who.

Describe a whole pipeline in one config file and run it entirely on your own infrastructure. Nothing leaves your walls, and there is no extra service to trust.