UCSF BioRouter
An integrated research environment that connects commercial, institution-hosted, and local AI models in one interface, built for biomedical discovery.
Why BioRouter
AI tools built for biomedical research
Sensitive patient data, on-prem datasets, reproducibility requirements, cross-institution collaboration. BioRouter handles each of these in a single interface.
Institutional security
Run inference on UCSF-hosted Azure OpenAI or Amazon Bedrock, or fully local Ollama. Patient data and proprietary research stay in your institutional environment.
Connected agents
Plug in specialized AI agents over the Model Context Protocol. Query clinical databases, biomedical knowledge graphs, and the literature from one session.
Federated collaboration
Package any analysis as a shareable Workflow. Collaborate across institutions without moving the underlying data. The Workflow carries the instructions, not the records.
Multi-provider routing
Switch between Claude, GPT, Gemini, and more. Commercial, institution-hosted, and local providers all use the same interface.
Automation and scheduling
Automate repeat research tasks with Workflows. Schedule pipelines on cron: literature reviews, data pulls, and analyses run on their own.
Desktop and CLI
A desktop GUI for interactive exploration and a command-line interface for scripting and integration into existing bioinformatics pipelines.
Provider ecosystem
One platform, every provider
BioRouter connects to every major LLM provider. Pick the one that fits your security requirements and research needs, and switch any time.