PrivAiTe

Quick start

Docker: the detection model is baked in, so it runs offline. PRIVAITE_API_KEYS is the key your client sends to PrivAiTe (pick any value); OPENAI_API_KEY is your real provider key, which stays in the container.

docker run -d -p 8400:8400 \
  -e PRIVAITE_API_KEYS=change-me \
  -e OPENAI_API_KEY=sk-... \
  ghcr.io/crp4222/privaite:0.7.3

pip: the same proxy with the same shipped config, which exposes gpt-4o-mini and gpt-4o.

python -m pip install --upgrade "privaite>=0.7.3"
python -m spacy download en_core_web_lg && python -m spacy download fr_core_news_md
curl -fsSLO https://raw.githubusercontent.com/crp4222/PrivAiTe/v0.7.3/config/privaite.openai.yaml
OPENAI_API_KEY=sk-... PRIVAITE_API_KEYS=change-me python -m privaite --config privaite.openai.yaml

Connect: point any OpenAI-compatible client at http://localhost:8400/v1 with the key change-me (from Open WebUI running in Docker: http://host.docker.internal:8400/v1). For Ollama, Azure or any other provider, write your own config and mount it in Docker. The image is also on Docker Hub as crp4222/privaite:0.7.3, and client snippets are in examples/.

See it work in one command, no API key

docker run --rm \
  ghcr.io/crp4222/privaite:0.7.3 \
  python -m privaite verify

  value                                          where                  direct   proxied
  Marie Dupont                                   message text             LEAK     clean
  marie.dupont@example.invalid                   tool-call argument       LEAK     clean
  4111 1111 1111 1111                            tool-call argument       LEAK     clean
  SERVICE_API_KEY=sk-demo-0000-not-a-real-key    tool output              LEAK     clean
RESULT: PASSED, every planted value was replaced before the request left.

It starts a throwaway provider on 127.0.0.1, sends the same agent-shaped request straight to it and then through PrivAiTe, and prints what each request body contained: every planted value shows LEAK when sent directly and clean through the proxy. About 20 seconds on a laptop CPU once the image is pulled (it carries the detection model and takes about 3 GB on disk). With pip, privaite verify does the same after the install below; its first run downloads the model (about 900 MB). It exits non-zero if a value leaks: docs/verify.md.

Integrations

• Open WebUI filter (setup, hub listing): the engine in-process, no separate proxy. Open WebUI sends its title, tag and follow-up calls without running filters, so with a cloud model use the standalone proxy instead: it sees those calls too.
• LiteLLM guardrail (setup): a custom guardrail for teams already on the LiteLLM proxy. It anonymizes requests and restores responses inline, including tool-call arguments, which LiteLLM's built-in Presidio guardrail does not scan.