An intelligent privacy layer for AI APIs. Kiji automatically detects and masks personally identifiable information (PII) in requests to AI services, ensuring your sensitive data never leaves your control.
Built by 575 Lab - Dataiku's Open Source Office.
When using AI services like OpenAI or Anthropic, sensitive data in your prompts gets sent to external servers. Kiji solves this by:
- 🔒 Automatic PII Protection - ML-powered detection of 16+ PII types (emails, SSNs, credit cards, etc.)
- 🎭 Seamless Masking - Replaces sensitive data with realistic dummy values before API calls
- 🔄 Transparent Restoration - Restores original data in responses so your app works normally
- 🚀 Zero Code Changes - Works as a transparent proxy with automatic configuration (PAC) on macOS
- 🌐 Browser-Ready - Automatic proxy setup for Safari, Chrome - no environment variables needed
- 🏃 Fast Local Inference - ONNX-optimized model runs locally, no external API calls
- 💻 Easy to Use - Desktop app for macOS, standalone server for Linux
Use Cases:
- Protect customer data when using ChatGPT for customer support
- Sanitize logs before sending to AI for analysis
- Comply with privacy regulations (GDPR, HIPAA, CCPA)
- Prevent accidental data leaks in development/testing
macOS (Desktop App):
# Download from releases
# https://github.com/dataiku/kiji-proxy/releases
# Install
open Kiji-Privacy-Proxy-*.dmg
# Drag to Applications folderLinux (Standalone Server):
# Download and extract
wget https://github.com/dataiku/kiji-proxy/releases/download/vX.Y.Z/kiji-privacy-proxy-X.Y.Z-linux-amd64.tar.gz
tar -xzf kiji-privacy-proxy-X.Y.Z-linux-amd64.tar.gz
cd kiji-privacy-proxy-X.Y.Z-linux-amd64
# Run
./run.shTest It:
macOS (with automatic PAC):
# Start with sudo for automatic browser configuration
sudo "/Applications/Kiji Privacy Proxy.app/Contents/MacOS/kiji-proxy"
# Open browser - requests to api.openai.com automatically go through proxy!
# No configuration needed for Safari/Chrome
# For CLI tools, set environment variables:
export OPENAI_API_KEY="sk-..."
export HTTP_PROXY=http://127.0.0.1:8081
export HTTPS_PROXY=http://127.0.0.1:8081
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-4",
"messages": [{"role": "user", "content": "My email is john@example.com"}]
}'Linux (manual proxy configuration):
# Set environment variables
export OPENAI_API_KEY="sk-..."
export HTTP_PROXY=http://127.0.0.1:8081
export HTTPS_PROXY=http://127.0.0.1:8081
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-4",
"messages": [{"role": "user", "content": "My email is john@example.com"}]
}'What happens:
# Check logs - "john@example.com" was masked before sending to OpenAI
# Response contains the original email (restored automatically)# Clone and setup
git clone https://github.com/dataiku/kiji-proxy.git
cd kiji-proxy
# Install dependencies
make electron-install
make setup-onnx
# Run with debugger (VSCode)
# Press F5
# Or run directly
make electronSee full documentation: docs/README.md
- 16+ PII Types Detected - Email, phone, SSN, credit cards, IP addresses, URLs, and more
- ML-Powered - DistilBERT transformer model with ONNX Runtime (model, dataset)
- Automatic Configuration - PAC (Proxy Auto-Config) for zero-setup browser integration on macOS
- Real-Time Processing - Sub-100ms latency for most requests
- Thread-Safe - Handles concurrent requests with isolated mappings
- Desktop UI - Native Electron app for macOS with visual request monitoring
- Production Ready - Systemd service, Docker support, comprehensive logging
- Privacy First - All processing happens locally, no external dependencies
Complete documentation is available in docs/README.md:
- Getting Started - Installation, configuration, first release
- Development Guide - Dev setup, debugging, workflows
- Building & Deployment - Building from source, production deployment
- Release Management - Versioning, changesets, CI/CD
- Advanced Topics - MITM proxy, model signing, troubleshooting
Quick Links:
The PII detection model and training data are published on HuggingFace:
| Resource | Link |
|---|---|
| Quantized ONNX model | DataikuNLP/kiji-pii-model-onnx |
| Trained SafeTensors model | DataikuNLP/kiji-pii-model |
| Training dataset | DataikuNLP/kiji-pii-training-data |
You can train your own model or fine-tune the existing one. See Customizing the PII Model for the full workflow.
┌─────────────────┐ ┌──────────────---───┐ ┌─────────────────┐
│ Your App/CLI │───►│ Kiji Privacy Proxy │───────►│ OpenAI API │
│ │ │ (Port 8080) │ │ (Masked Data) │
│ │◄───┤ - Detect PII │◄───────┤ │
│ Original Data │ │ - Mask/Restore │ │ │
└─────────────────┘ └────────────────────┘ └─────────────────┘
What Happens:
- Your app sends request to Kiji Privacy Proxy
- Kiji detects PII using ML model
- PII is replaced with dummy data
- Request forwarded to OpenAI (with masked data)
- Response received and PII restored
- Original-looking response returned to your app
We welcome contributions! Here's how to help:
- Report Issues - Found a bug? Open an issue
- Submit PRs - See docs/02-development-guide.md for dev setup
- Improve Docs - Documentation PRs are always welcome
- Share Feedback - Start a discussion
- Join our Slack - Slack Community
Quick Contribution Guide:
# 1. Fork and clone
git clone https://github.com/YOUR-USERNAME/kiji-proxy.git
# 2. Create feature branch
git checkout -b feature/my-feature
# 3. Make changes and add changeset
cd src/frontend
npm run changeset
# 4. Test
make test-all
make check
# 5. Submit PRSee CONTRIBUTING.md for detailed guidelines.
If you find Kiji useful, here's how you can support its development:
Click the ⭐ button at the top of this page - it helps others discover the project!
Found a bug or have an idea? Open an issue
Pull requests are welcome! See CONTRIBUTING.md for guidelines.
- Share on Twitter/LinkedIn
- Write a blog post about your experience
- Present at meetups/conferences
- Contribute training data samples
- Improve PII detection accuracy
- Add support for new PII types
- Create video tutorials
- Write integration guides
- Share use cases and examples
Every contribution, big or small, makes a difference!
- Go 1.21+ with CGO enabled
- Node.js 20+
- Python 3.13
- Rust toolchain
# Install dependencies
make electron-install
# Run with VSCode debugger (F5)
# Or run directly
make electronmake help # Show all commands
make electron # Build and run Electron app
make build-dmg # Build macOS DMG
make build-linux # Build Linux tarball
make test-all # Run all tests
make check # Code quality checksSee docs/02-development-guide.md for detailed development guide.
Download the latest release from GitHub Releases:
- macOS:
Kiji-Privacy-Proxy-{version}.dmg(~400MB) - Linux:
kiji-privacy-proxy-{version}-linux-amd64.tar.gz(~150MB)
Automated Builds: CI/CD builds both platforms in parallel on every release tag.
See docs/04-release-management.md for release process.
Reporting Vulnerabilities:
Do not open public issues for security vulnerabilities.
Email: opensource@dataiku.com (or contact maintainers privately)
Security Features:
- All processing happens locally
- No external API calls for PII detection
- Optional encrypted storage for mappings
- MITM certificate for local use only
See docs/05-advanced-topics.md#security-best-practices for security guidelines.
Copyright (c) 2026 Dataiku SAS
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
- ONNX Runtime - Microsoft's cross-platform ML inference engine
- HuggingFace - DistilBERT model and tokenizers
- Electron - Cross-platform desktop framework
- Go Community - Excellent libraries and tools
Made with ❤️ for privacy-conscious developers
GitHub • Issues • Discussions • Slack • Documentation