Cloak is an open-source proxy that replaces personally identifiable information (PII) in your prompts with realistic fake entities before sending them to cloud LLMs, then restores the real entities in the answer, all without your actual PII ever leaving your device.
57
No data
5
0
NOASSERTION
2026-06-29
It performs round-trip substitution with realistic stand-ins (not redaction) and uses a two-stage local model pipeline (span detection + relevance filtering) to preserve answer quality while minimizing PII exposure.
Chat with cloud LLMs while a local model swaps your PII out before the prompt leaves your machine — and rehydrates the answer back to your real entities.
Every time you ask a cloud AI about something personal — a city you're moving to, a company you work for, a name — you're sending that data to an external server. Cloak intercepts each prompt, runs a local PII detector, replaces sensitive entities with realistic stand-ins (not [REDACTED] — actual fake names and cities), sends the scrubbed prompt to the cloud, then maps the answer back to your real entities before you see it.
The round-trip substitution is the differentiator: the cloud model sees a coherent, answerable prompt; you get a useful, real answer; and the actual PII never left your device.
This is disclosure control, not a privacy guarantee. The pipeline reduces PII exposure significantly — but a determined adversary with enough queries could still reconstruct context. The goal is to make routine LLM use substantially less leaky, without sacrificing answer quality.
Prerequisites: Ollama installed and running.
# 1. Install Ollama (if not already):
# https://ollama.com/download
# 2. Clone and launch:
git clone https://github.com/praxis-society/praxis-cloak.git
cd praxis-cloak
./scripts/run.sh
run.sh will:
praxis/spanfinder-3b and praxis/relevance-3b from HuggingFace and build them into Ollama locally (first run only, ~3.8 GB total — no Ollama account needed)npm is not found)http://127.0.0.1:8765 and open it in your browserSettings: Paste your Anthropic or OpenAI API key in Settings to route scrubbed prompts through your preferred provider.
| Model | Weights | Size (q4_k_m) | Role |
|---|---|---|---|
praxis/spanfinder-3b | HuggingFace | ~1.8 GB | Detects PII spans in the prompt |
praxis/relevance-3b | HuggingFace | ~1.8 GB | Decides which detected entities to scrub vs. keep (needed to answer the question) |
run.sh downloads these GGUFs from HuggingFace and builds them into Ollama for you (the relevanc
On-device PII scrub + rehydration for cloud LLMs — chat with Claude/GPT while a local model swaps your PII out before the prompt is sent, then maps the answer back to your real entities. Built with Qwen.
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.