cxumol/promptmask
Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless integration with your existing AI tools as a Python library / OpenAI SDK replacement / API Gatetway / Web Server.
Implements a dual-LLM architecture where a lightweight local model identifies and redacts sensitive entities before sending requests to cloud AI APIs, with the local model also reversing the obfuscation in responses. Deploys as a Python SDK drop-in replacement for OpenAI's client, an OpenAI-compatible API gateway, or standalone web server with integrated UI. Supports flexible LLM endpoints (Ollama, llama.cpp, vLLM) and includes benchmarks for model selection based on redaction effectiveness and hardware constraints.
Available on PyPI.
Stars
94
Forks
11
Language
Python
License
MIT
Category
Last pushed
Jan 04, 2026
Monthly downloads
34
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/cxumol/promptmask"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
AgenticA5/A5-PII-Anonymizer
Desktop App with Built-In LLM for Removing Personal Identifiable Information in Documents
sgasser/pasteguard
AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.
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,...