Public platform — live
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
Projects
Long-term research programs.
Four programs carry the lab’s work across healthcare AI, agent runtime safety, governed AI agents, and open-science infrastructure. Each profile includes its current status and a link to the source project.
Long-term programs
v1.2.0 “Quiet Open-Core” — shipped, self-hosted
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 approvalsHash-chained audit trailFrozen /v1 API
Pre-launch — access by request
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 CollaborationEvidence lineageApproval workflows
In development
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
Partner with a program.
Each program grows through partners — hospitals and clinicians for AIMed, platform and safety teams for ActantOS, universities and publishers for ScienzaOS, and teams exploring governed agent deployment with Agent Platform.
Get in touch- Clinical pilots
- Research collaborations
- Dataset partnerships
- Student theses
- Open-source contributions