Unlock the power of healthcare data with CogStack AI.

This GitHub organization hosts the open-source code for CogStack AI, including our core NLP pipelines, data workflows, and research tools.

• Improve productivity and reduce clinical risk through better data with Deep Phenotypes and Search
• Free-up staff time through health data insights from CogStack Language Models and Generative AI
• Works with any digital health record system and interoperable to international data standards

NLP pipelines for healthcare, including the Medical Concept Annotation Tool (MedCAT) for entity recognition and linking.
CogStack NLP powers downstream analytics by structuring unstructured clinical data.

A collection of example workflows using Apache NiFi as the core orchestration engine.
These recipes connect NLP components and data services, supporting tasks such as Text Extraction, Natural Language Processing, and Secure Routing of Clinical Documents

Cogstack ModelServe (CMS) is a model-serving and model-governance system created for a range of CogStack NLP tasks. Targeting language models with NER and entity linking capabilities, CMS provides a one-stop shop for serving and fine-tuning models, training lifecycle management, as well as monitoring and end-to-end observability.

Research framework for deep generative modeling of patient timelines using Electronic Health Records (EHRs).
Enables exploration of predictive modeling and risk stratification through modern generative techniques.

Framework for building grounded instruction-based datasets and training domain-specific LLMs.
Focused on safe, explainable, and healthcare-aligned conversational AI.

We welcome contributions from clinicians, researchers, and developers passionate about healthcare AI.

• Explore our repos and open issues
• Share your ideas via discussions or feature requests
• Join the mission to make healthcare data truly interoperable and intelligent

Each project has its own license. Please check the relevant repository for details.