PrivAiTe — AI skill for Claude Code
Self-hosted PII redaction proxy for LLM APIs and agent CLIs.
How to install PrivAiTe
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open crp4222/PrivAiTe and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What PrivAiTe does
Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compatible app before requests leave your machine, tool-call arguments included, then restores them in the reply. Local detection, zero telemetry.
Alternatives in AI
- WindsurfAPI — Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A 3k ★
- DontFeedTheAI — Transparent anonymization proxy for AI-assisted pentesting 654 ★
- Update Branch Name — by giselles-ai - Updates branch names with proper prefixes and formats, enforcing naming conventions, supporti 502 ★
README
PrivAiTe
Self-hosted PII redaction proxy for LLM APIs.
[](https://github.com/crp4222/PrivAiTe/actions) [](https://www.python.org/downloads/) [](https://github.com/crp4222/PrivAiTe/blob/main/LICENSE) [](https://pypi.org/project/privaite/)
**A drop-in LLM proxy that replaces PII before it reaches the provider, including inside tool-call arguments and multimodal content, with zero telemetry.**
Told in writing to report its config variables but **never their values**, Claude Code sent 3 of 4 secrets to its provider anyway: the same secrets also sat in a log file the task had it read. Over that session **23 of 24** planted values reached the provider; through PrivAiTe's agent gateway, **2 of 24**. Wire-level captures of real agent sessions, and the two that still get through are documented rather than rounded away: [the measurement](https://github.com/crp4222/PrivAiTe/blob/main/docs/agent-leak-measurement.md), [what it misses](https://github.com/crp4222/PrivAiTe#threat-model).
**Shipped in 0.5.0:** local rules now target the credential fields behind those historical log misses, and overlapping detections respect irreversible and block policies, so a secret overlapping a higher-scored email stays irreversible. See [formats and limits](https://github.com/crp4222/PrivAiTe/blob/main/docs/detection.md#structured-credentials-and-overlapping-types). In the [offline regression replay](https://github.com/crp4222/privaite-bench/blob/main/agent_workflow/STRUCTURED_SECRETS.md), 9 of 10 credential occurrences survived in a 69 KB log before the change; none survived afterward. Processing still takes about 25 seconds with `onnx`.
You type: "Je m'appelle Marie Dupont, email marie@acme.com"
LLM sees: "Je m'appell
Related Skills
Mask2ai
PII redaction for ChatGPT, claude.ai and Claude Code. Masks names, emails, phone numbers, cards, IBANs and IDs
Veil
Local privacy proxy for AI coding agents. The model sees consistent pseudonyms instead of real names, emails a
Local Secure Prompt Agent
Browser extension that redacts PII (emails, phone numbers, Aadhaar/PAN, API keys, names, locations) from promp
Shush
Remove PII & secrets from any file before you paste it into ChatGPT or Claude — a 100% local PII redaction CLI
Claude Code Redact
Claude Code mod that redacts secrets and PII before the model reads them, stores placeholders in the conversat
Keyfence
Local proxy that keeps your API keys and secrets out of LLM requests. Works with Claude Code, Cursor, Codex an
Related Agents
Lmstudio Local
A locally-hosted model served through LM Studio's OpenAI-compatible API,
Openrouter Agent
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against
Verina Pdpa Counsel
Senior legal counsel (Singapore data protection) for Verina. Use to ensure every data flow complies with the P