Artificial
Intelligence
Foundation models, reasoning, and human-centered AI.
Research
From fundamental research to real-world impact.
ERA Lab advances fundamental research and real-world systems at the intersection of artificial intelligence, intelligent systems, and human-centered applications — organized into five research areas and four long-term programs.
Research areas
Artificial
Intelligent
Systems
Multi-agent systems, human–AI collaboration, and complex systems.
Healthcare AI
AI for health, biomedicine, and clinical decision support.
Research
Infrastructure
Tools, datasets, and platforms for open scientific discovery.
Knowledge
Systems
Knowledge representation, scientific AI, and information systems.
How the research connects
Five areas, four programs, one system.
AIMed
- Healthcare AI
ActantOS
- Intelligent Systems
ScienzaOS
- Research Infrastructure
- Knowledge Systems
Agent Platform
- Intelligent Systems
Featured research programs
Four programs, one goal: AI that is safe, useful, and human-centered.
AIMed
AI for healthcare and Vietnamese traditional medicine.
Applied healthcare AI focused on safe real-world use, medical knowledge, and intelligent assistance.
5,190+ medicinal herbsInteraction checkingAI plant recognition
Public platform — live
Visit aimedvn.net
ActantOS
Runtime safety and verification for multi-agent systems.
A self-hosted enforcement kernel that intercepts tool calls between agents and the systems they act on — evaluating each call against policy before allowing, pausing for approval, or blocking.
Fail-closed enforcementCedar policy engineOne-use human approvals
v1.2.0 “Quiet Open-Core” — shipped, self-hosted
Visit actantos.com
ScienzaOS
Research infrastructure for open science and collaboration.
The platform for academic life: Research Agent, Teaching Studio, and Business Collaboration on one shared foundation of sources, review, rights, and provenance — agents prepare, people retain authority.
Research AgentTeaching StudioBusiness Collaboration
Pre-launch — access by request
Visit scienzaos.com
Agent Platform
Governed AI agents with clear permissions and an auditable record of every action.
An operating layer connecting channels, agents, people, and systems. It applies rules and scoped permissions, requests human approval when needed, and records actions and outcomes.
Scoped permissionsHuman approvalsAction records
In development
Visit agp-ui-pi.vercel.appInterested in building these systems with us?
We welcome research collaborations, dataset partnerships, and joint pilots with clinical and industry partners — from early problem framing to deployment.
Get in touch- Universities
- Research institutes
- Hospitals and healthcare organizations
- Industry partners
- Open science community