Open products, clinical skills, and tools for traceable AI in radiology and healthcare.
Founded by Bernhard Zechmann — systems architect, 35+ years in the stack, building in public from Nagold, Germany.
From 3D pain mapping to multi-agent AI orchestration — each product solves a specific gap in digital healthcare.
AI-assisted medical image analysis, built for real clinical workflows.
From raw information to trusted insights — one workspace.
Launch your Streamlit app as a real product in days, not months.
Patients show exactly where it hurts — on a real 3D body.
End-to-end digital workflow for radiology second opinions.
Automated German-language news on AI in healthcare.
Watch medical AI agents and clinical skills come alive.
Real commit and release activity across every public repo — pulled at build time, verified in the open.
Specialized skills for AI-powered radiology workflows — from modality detection to structured reporting.
$ npx skillsadd modality-detectionDetails$ npx skillsadd radiology-contextDetails$ npx skillsadd pacs-workflowDetails$ npx skillsadd pubmed-searchDetails$ npx skillsadd dicom-web-queryDetails$ npx skillsadd ai-report-assistDetails$ npx skillsadd ai-detection-pipelineDetails$ npx skillsadd llm-radiology-useDetails$ npx skillsadd ai-quality-reviewDetails$ npx skillsadd radiology-report-analysisDetails$ npx skillsadd structured-reportingDetails$ npx skillsadd imaging-study-reviewDetails$ npx skillsadd imaging-referralDetails$ npx skillsadd followup-trackingDetails$ npx skillsadd care-gap-closureDetails$ npx skillsadd patient-results-letterDetails$ npx skillsadd patient-education-materialDetails$ npx skillsadd radiology-metricsDetails$ npx skillsadd image-quality-auditDetails$ npx skillsadd report-quality-reviewDetails$ npx skillsadd guideline-integrationDetails$ npx skillsadd cross-reference-linkingDetails$ npx skillsadd radiology-researchDetails$ npx skillsadd radiology-dataset-guideDetails$ npx skillsadd dataset-preprocessingDetails$ npx skillsadd model-validationDetailsEssential CLI tools for DICOM handling, image quality, and radiology workflow automation.
$ python -m tools.clis.dicom_qido --url https://pacs.example.com --patient-id ABC123$ python -m tools.clis.dicom_wado --url https://pacs.example.com --study-uid 1.2.3.4.5$ python -m tools.clis.fetch_study --pacs-url https://pacs.example.com --study-uid <uid> --output ./studies/$ python -m tools.clis.dicom_anonymizer --input ./dicom/ --output ./anonymized/$ python -m tools.clis.dicom_info --file ./study.dcm$ python -m tools.clis.image_qc --image ./scan.png --protocol brain$ python -m tools.clis.tat_analyzer --data ./reports.csv --output tat_report.html$ python -m tools.clis.radiology_metrics --data ./logs/ --period month$ python -m tools.clis.pubmed_search --query "lung nodule CT" --max-results 20$ python -m tools.clis.dataset_downloader --dataset rsna --output ./data/$ python -m tools.clis.structured_report --template birads --findings "mass" --output report.json$ python -m tools.clis.trial_matcher --condition lung-cancer --location "Berlin" --radius 50Seamless integration with PACS servers, EHR systems, AI platforms, and healthcare standards.
Available for consulting, collaboration, and product partnerships. Every inquiry gets a personal reply.