sgasser/pasteguard
AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.
Detects 30+ types of sensitive data (names, emails, API keys, tokens) across 24 languages using Microsoft Presidio, then masks them in real-time before requests reach LLM providers. Runs as a local HTTP proxy that intercepts API calls to OpenAI, Anthropic, and self-hosted models—requiring only a single URL change in client code. Includes Route Mode to automatically redirect sensitive requests to local LLMs while routing non-sensitive queries to cloud providers, with a dashboard for auditing what was detected and masked.
546 stars. Actively maintained with 2 commits in the last 30 days.
Stars
546
Forks
18
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/sgasser/pasteguard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cxumol/promptmask
Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless...
AgenticA5/A5-PII-Anonymizer
Desktop App with Built-In LLM for Removing Personal Identifiable Information in Documents
QWED-AI/qwed-verification
Deterministic verification layer for LLMs | AI hallucination detection | Model output validation...
rpgeeganage/pII-guard
🛡️ PII Guard is an LLM-powered tool that detects and manages Personally Identifiable Information...
subodhkc/llmverify-npm
AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency,...