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.
A local AI firewall for coding agents. Secrets are replaced by placeholders before they leave your machine, and restored when the reply comes home — the model, the relay and the provider never see the value.