local-ai

DataInfra-RedactionEverything: Seamlessly Redact All Data Locally

Use local LLMs and VLMs to automatically redact sensitive information from any dataset—ideal for founders needing privacy‑first AI pipelines. 1.1k+ GitHub stars.

From the repo · “DataInfra Series. Redact EVERYTHING with local llms and vlms.”

intermediate⏱ 30 minutes💵 Free (self-hosted)
1,131 stars168 forksTypeScriptGuide quality 8/10 · reviewed Oct 20Updated 9/2/2026100% free · open source
What it is

Redacts everything in data with local large language models and vector databases.

Real use case example

"A data analyst uses this automation to remove credit card numbers from a dataset and exports the scrubbed data to Google Sheets for reporting."

Best insideClaude DesktopSelf-hostedAny AI Client
When to use it
  • •When working with sensitive customer data that requires redaction for compliance
  • •When building a data pipeline that needs to anonymize personally identifiable information (PII)
  • •When testing data-driven applications that require realistic, redacted data samples
Ready-to-paste prompt
const redactor = new Redactor(); const redactedText = redactor.redact('My name is John Doe, and my email is johndoe@example.com');
Heads up: Ensure you have Node.js and TypeScript installed on your system, as DataInfra-RedactionEverything is built with TypeScript and relies on Node.js for execution
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/datainfra-redactioneverything && curl -fsSL https://workflowstacks.com/api/skills/datainfra-redactioneverything/claude-skill -o ~/.claude/skills/datainfra-redactioneverything/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How DataInfra-RedactionEverything: Seamlessly Redact All Data Locally works
Codeflow
Free to inspect

DataInfra-RedactionEverything: Seamlessly Redact All Data Locally is a very large Python project (~110k lines across 455 code files, plus 110 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit 2 months ago, Other license, has a test suite.

Size
Very large codebase
~110k lines · 455 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Docker
Needs API keys (.env)
Python 55%TypeScript 43%Shell 1%JavaScript 1%CSS 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    package.json
    Dependencies and the commands it exposes
  3. 3
    .env.example
    The API keys and settings you must provide
What's in each folder
backend/Backend / API283 files
frontend/Frontend / UI259 files
docs/Documentation18 files
deploy/Deployment / infrastructure33 files
tools/Helper scripts11 files
scripts/Helper scripts2 files
e2e/Tests — proof it works36 files
.github/CI / automation (GitHub Actions)6 files
READMEHas testsDocumentedCI checksDocker readyOther licenseUpdated 2 mo ago
Quick Actions
Details
Creator
TracyWang95
Language
TypeScript
Category
local-ai
Published
1/28/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/datainfra-redactioneverything.svg)](https://workflowstacks.com/skills/datainfra-redactioneverything?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.