Open-source multimodal redaction runtime. Detect, redact, and audit PII and sensitive data across documents, images, audio, and video.
- Multimodal Codecs: read, edit, and write PDF, DOCX, images, audio, CSV, JSON, and plain text
- AI-Powered Detection: regex, dictionary, checksum, NER, and LLM-driven entity recognition
- Span-Aware Redaction: mask, replace, hash, encrypt, blur, block, pixelate, and synthesize
- Pipeline Engine: DAG compiler and executor with retry and timeout policies
- Python Extensions: PyO3 bridge for AI-powered NER and OCR via embedded CPython
The fastest way to get started is with Nvisy Cloud.
For self-hosted deployments, refer to docker/ for compose files and
infrastructure requirements, and .env.example for configuration.
See docs/ for architecture, security, and API documentation.
See CHANGELOG.md for release notes and version history.
Apache 2.0 License, see LICENSE.txt
- Documentation: docs.nvisy.com
- Issues: GitHub Issues
- Email: support@nvisy.com