Run This Ai
EN DE

OpenMed

Local-first healthcare AI for clinical NER and HIPAA PII de-identification, running 100% on your own hardware.

★ 5,158 GitHub Apache-2.0 healthcarepiinerlocal-llmprivacymlxhipaa LLM & Chat

Overview

OpenMed is a local-first healthcare AI platform that turns clinical text into structured, de-identified insight on hardware you control. It performs clinical named-entity recognition (NER) and HIPAA-compliant PII de-identification fully on-device — no cloud, no patient data leaving your network. With 2,200+ medical models covering 21 languages and 33 model-backed PII languages, OpenMed runs on Apple Silicon (MLX), Python (CPU/CUDA), Android (ONNX Runtime Mobile), and even in the browser via WebGPU. The Apache-2.0 SDK includes a Python API, a REST service with /analyze and /pii/deidentify endpoints, batch processing, and an MCP server, plus Dockerfiles for self-hosting.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Related tools

Guides & articles