NoPII – One line of code to protect PII before it hits your LLM
Change one base_url to tokenize PII — blocks requests if the service is unreachable.

Reversible tokenization for LLM prompts, but this exact problem has competing solutions.
AI/LLM application developers handling sensitive data (healthcare, finance, SaaS)
Anthropic (prompt guards) · Presidio (Microsoft's open-source PII detection) · AWS Macie
Change one base_url to tokenize PII — blocks requests if the service is unreachable.
Yet another PII redaction proxy when Lakera and Portkey already dominate this space.
Phonetic embeddings catch ASR-mangled names across cultures before LLM sees them.
Local-first agent observability without cloud signup — LangSmith alternative that keeps data on your machine.
Dependency-free Go binary with Luhn validation — Presidio and Nightfall already cover this space.
OpenAI-compatible proxy with PII masking and token budgets—but LiteLLM, Helicone already do this.