Skip to content

Enterprise-grade multimodal redaction runtime that detects and removes sensitive information from unstructured documents, images, and mixed-media files, powering secure, end-to-end pipelines.

License

Notifications You must be signed in to change notification settings

nvisycom/runtime

Repository files navigation

Nvisy Runtime

Build

Open-source multimodal redaction runtime. Detect, redact, and audit PII and sensitive data across documents, images, audio, and video.

Features

  • 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

Quick Start

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.

Documentation

See docs/ for architecture, security, and API documentation.

Changelog

See CHANGELOG.md for release notes and version history.

License

Apache 2.0 License, see LICENSE.txt

Support

About

Enterprise-grade multimodal redaction runtime that detects and removes sensitive information from unstructured documents, images, and mixed-media files, powering secure, end-to-end pipelines.

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Contributors

Languages