Redacta
Pseudonymise medical and clinical documents before they're processed by AI or
shared. Redacta replaces patient identifiers with labelled tokens —
[PATIENT_NAME_1], [NHS_NUMBER_1], [DATE_OF_BIRTH_1], … — while leaving the
clinical meaning intact, and returns a redaction report alongside the cleaned
text.
It started as an Agent Skill and is now one engine shipped across eight surfaces — an iOS app, agent skill, MCP server, two libraries, a CLI, and two whiteboard apps.
One engine, many surfaces
<p align="center"> <img src="ios-app/docs/architecture.svg" width="100%" alt="One detection engine feeds eight surfaces: the iOS app, Share Extension and widget run it on-device via JavaScriptCore; the MCP server, CLI, TypeScript library and FigJam/Miro plugins consume it directly; a Python package mirrors it; and the agent skill adds LLM reasoning." /> </p>| Surface | Folder | Get it |
|---|---|---|
| iOS app — iPhone (app, Share Extension, widget) | ios-app/ | Build with Xcode — see ios-app/README.md |
| Agent skill (Claude Code / apps / API) | SKILL.md, scripts/ | openclaw skills install redacta (ClawHub) |
| MCP server (Claude Desktop, Cursor, …) | mcp-server/ | npx -y redacta-mcp (npm · MCP Registry · Anthropic MCP Directory) |
| TypeScript library | npm-package/ | npm i @pharmatools/redacta (npm) |
| Python library | python-package/ | pip install redacta (PyPI) |
| Command-line tool | cli-package/ | npx redacta-cli (npm) |
| Miro app | miro-app/ | getpatiently.ai → Redacta |
| FigJam plugin | figjam-plugin/ | Figma Community |
The detection logic lives in one place — the TypeScript engine
(@pharmatools/redacta, in npm-package/), which the MCP server and both
whiteboard apps consume, and which the iOS app runs on-device via JavaScriptCore.
The Python package mirrors it for pip users; the agent skill adds LLM reasoning
for free-text names on top of the deterministic patterns.
How it works
Two layers:
- Patterns (deterministic). A bundled script (
scripts/redact_structured.py, Python standard library only, no network) matches fixed-format identifiers: NHS numbers (Modulus-11 validated), UK National Insurance numbers, dates of birth, UK postcodes, phone numbers, emails, and hospital/MRN numbers. US SSN and ZIP codes are also handled. - Reasoning (judgement). The skill then has the agent handle what patterns can't: patient names (told apart from the clinicians treating them), relatives and carers, postal addresses, and identifying ages.
- Self-check. A final pass re-reads the output for any identifier that slipped through before the report is written.
It also works in reverse. Re-identification (scripts/reinstate.py) takes the
token map from an earlier redaction and restores the original values — so you can
redact a document, run it through another AI tool, and put the real details back
locally. Redact → process → re-identify is a complete round trip, and identifiers
only ever exist on your machine.
Safe Harbor mode. Ask for HIPAA Safe Harbor (or "US de-identification") and Redacta applies a stricter pass: all dates (not just the date of birth), all specific ages, and the remaining HIPAA identifiers — fax, certificate/licence, device serial, VIN, and health-plan beneficiary numbers.
Install
Claude Code
git clone https://github.com/nickjlamb/redacta ~/.claude/skills/redacta
Then invoke it with /redacta, or let it trigger automatically when you ask to
redact or de-identify clinical text.
Claude apps / API
Zip the repository folder and upload it as a skill.
Contents
| Path | What it is |
|---|---|
SKILL.md | The skill — instructions plus metadata |
reference.md | Pattern specs, the Modulus-11 algorithm, NI prefix rules, the date-of-birth vs clinical-date rule, token vocabulary, limitations |
scripts/redact_structured.py | The deterministic pattern layer |
scripts/reinstate.py | The re-identification layer (restore originals from a token map) |
scripts/test_redact_structured.py | Tests for the pattern layer |
scripts/test_reinstate.py | Tests for the re-identification layer |
evaluations.json | Example evaluation scenarios |
Run the tests:
python3 scripts/test_redact_structured.py
python3 scripts/test_reinstate.py
A note on limits
Redacta is a strong first line of defence, not a guarantee. It won't catch every possible identifier and isn't a substitute for formal data-protection processes. Always review the redaction report before sharing text.
License
MIT-0 (MIT No Attribution). Built by PharmaTools.AI.