openmed

openmed is a local-AI tool - Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 1,000+ medical models, 12 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0.

Overview

Turn clinical text into structured insight with one line of code. Entity extraction, PII de-identification, and 1,000+ specialized medical models that run entirely on your own hardware — from a one-liner in Python to a native Swift app on iPhone, powered by Apple MLX. No cloud. No vendor lock-in. No patient data leaving your network.

OpenMed runs entirely on the device — clinical text never leaves it. Here it is on iPhone, fully offline:

On iPhone via OpenMedKit — scan a clinical note, de-identify it, and extract clinical signals, all locally with Apple MLX. Nothing is uploaded.

Real-time PII de-identification — the Nemotron Privacy Filter redacting names, addresses, IDs, and billing data from a clinical discharge packet, entirely on-device. (All values shown are synthetic.)

A state-of-the-art clinical NER model running locally — no API key, no network call.

• Specialized models — 1,000+ curated biomedical & clinical models, many outperforming proprietary stacks. - HIPAA-aware de-identification — all 18 Safe Harbor identifiers, smart entity merging, format-preserving fakes. - Runs everywhere — CPU, CUDA, Apple Silicon (MLX), and natively in iOS/macOS apps via OpenMedKit. - One-line deployment — Python API, Dockerized REST service, or batch pipelines. - Zero lock-in — Apache-2.0, your infrastructure, your data.

openmed is open-source, written primarily in Python, with 3,593 GitHub stars under the Apache 2.0 license. The latest release is v1.5.5 (2026-06-08).

Key capabilities

From the project's documentation:

• Specialized models — 1,000+ curated biomedical & clinical models, many outperforming proprietary stacks.
• HIPAA-aware de-identification — all 18 Safe Harbor identifiers, smart entity merging, format-preserving fakes.
• Runs everywhere — CPU, CUDA, Apple Silicon (MLX), and natively in iOS/macOS apps via OpenMedKit.
• One-line deployment — Python API, Dockerized REST service, or batch pipelines.
• Zero lock-in — Apache-2.0, your infrastructure, your data.
• Python on Apple Silicon too: pip install "openmed[mlx]".

Install

A quick way to get started (always check the official docs for the latest):

pip install "openmed[hf]"

How it fits a local-AI stack

openmed runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related local-AI tools in the directory:

• "algernon"
• "blinko"
• Continue
• "exo"

Sources

• Source code & docs: maziyarpanahi/openmed
• Official website: https://openmed.life/

Stats from GitHub, 2026-06-18.