workflowstacks
local-ai

openmed – On‑device Clinical NLP & HIPAA De‑identification for Health Startups

Run 1,000+ medical models in 12 languages entirely on‑device, keeping patient data in‑house. Ideal for founders building secure, cloud‑free health apps. 5.5k+ GitHub stars
5,647 stars+198★ this week719 forksPythonGuide quality 9/10 · reviewed Oct 9Updated 10/13/2026100% free · open source
What it does

Openmed is a local-first solution that performs clinical named entity recognition (NER) and HIPAA protected health information (PHI) de-identification on-device, without sending patient data to the cloud.

When to use it
  • •You're building a healthcare application that requires analyzing medical text data while keeping patient information secure and compliant with HIPAA regulations.
  • •Your startup needs to process large volumes of medical records or clinical notes without relying on cloud services for data processing.
  • •You want to leverage the power of AI in medical text analysis but are restricted by data privacy concerns or limited internet connectivity.
Ready-to-paste prompt
python openmed/cli.py --text "The patient, John Doe, was diagnosed with diabetes." --model models/en_ner_bc5cdr_md
Heads up: Ensure your development environment has the necessary dependencies installed, including Python and the Apple MLX framework if you plan to integrate openmed with iOS applications, as the tool leverages these frameworks for on-device processing.
Saves to your device
Use with Claude
New

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

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/openmed && curl -fsSL https://workflowstacks.com/api/skills/openmed/claude-skill -o ~/.claude/skills/openmed/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 openmed – On‑device Clinical NLP & HIPAA De‑identification for Health Startups works
Codeflow
Free to inspect

Openmed – On‑device Clinical NLP & HIPAA De‑identification for Health Startups is a very large Python project (~603k lines across 1252 code files, plus 1116 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~603k lines · 1252 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 74 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Python · Docker
Python 93%Swift 3%Kotlin 1%TypeScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    openmed/__init__.py
    Inside openmed/ — the main logic begins here
  4. 4
    examples/__init__.py
    A worked example — copy this to get going
What's in each folder
openmed/Core code — the actual logic1118 files
skills/Prompts, skills & agent definitions86 files
web/Frontend / UI15 files
integrations/Sub-packages / plugins1 files
docs/Documentation603 files
examples/Examples you can copy118 files
recipes/Examples you can copy1 files
swift/Folder164 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
maziyarpanahi
Language
Python
Category
local-ai
Published
10/4/2025

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/openmed.svg)](https://workflowstacks.com/skills/openmed?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.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Puppeteer (browser) MCP config

Let Claude control a headless browser — navigate, screenshot, scrape.

Related skills

More local-ai tools founders pair with this one.

local-ai★ 131,013
Run Powerful LLMs Locally with llama.cpp – Fast C++ Inference
Empower your product with on‑device LLM inference using llama.cpp’s efficient C++ engine. Ideal for founders who need privacy, speed, and no cloud costs. 130k+ GitHub stars.
local-ai★ 94,111
Stirling-PDF: Edit PDFs Anywhere
Edit PDFs on any device with Stirling-PDF, a tool for startup founders, backed by 80k+ GitHub stars
local-ai★ 37,841
Run AI Locally with llmfit
Find compatible AI models for your hardware with llmfit, a tool for founders, with 29k+ GitHub stars.
local-ai★ 670
sno-station
Sno Station — your Claude Code and Codex working as one squad on your own machine. Shared encrypted memory, agent-to-agent messaging (Reach), squad skills for handoff and cross-vendor review, and a nightly loop that rewrites the agents' own skills with your approval. Open source, no daemon, no cloud required. Assembled in public.
local-ai★ 271
uteke: AI Memory Engine
Store and recall AI memories offline with uteke. For founders building local AI tools.
local-ai★ 5,705
Maka-agent: Local AI Assistant
Get a local-first AI desktop assistant with Maka-agent, for startup founders.