Skip to main content
Nvisy is an open-source multimodal redaction platform. It detects and removes sensitive information across documents, images, and audio, combining deterministic patterns, NER, computer vision, and LLM-driven classification into auditable, policy-driven pipelines built for organizations that need every redaction to be reviewable and accountable.

Get Started

Quickstart

Get up and running with Nvisy in minutes

Redaction Workflow

Understand the complete redaction process

Core Features

AI Detection

Patterns, NER, vision, and LLM classification, reconciled into a single auditable result

Multimodal Formats

Documents, spreadsheets, images, and audio — each analyzed in its own modality

Audit Trails

Verifiable, per-entity provenance for every detection and redaction

Zero-Knowledge Architecture

Your documents never leave your infrastructure with on-premises deployment

SDKs

TypeScript SDK

Official SDK for Node.js and browser environments with full TypeScript support

Python SDK

Python SDK for server-side applications (coming soon)

API Reference

REST API

Comprehensive REST API documentation for integrating Nvisy into your applications

Deployment Options

Cloud

Fully managed cloud deployment

On-Premises

Complete control in your infrastructure

Support

GitHub

Contribute to the open-source project or report issues

Email Support

Get help from our support team