A Self-Evolving Agent for Longitudinal Personal Health Management
Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolation. We developed HealthClaw, an open-source agent architecture that updates support as a person's routines, preferences, measurements and risks change. It separates shared safety rules and medical knowledge from private longitudinal memory containing profile facts, reusable procedures and episodic traces. After each episode, induction determines what should update the profile, revise a procedure, remain episodic or be excluded. We evaluated HealthClaw with a synthetic year-long
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “A Self-Evolving Agent for Longitudinal Personal Health Manag” ≈ “AgentCore-8B””
- PossiblePossibly related (embedding) · 59%Build self-service AWS Health analytics to find actionable health insights with AI agents powered by Amazon Bedrock →
- PossiblePossibly related (embedding) · 58%New research shows how AMIE, our medical AI, could help manage health conditions. →
- PossiblePossibly related (embedding) · 55%Building an agentic AI solution at Bluesight with Amazon Bedrock →
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “A Self-Evolving Agent for Longitudinal Personal Health Manag” ≈ “zhayujie/CowAgent””
- FuzzyOverlapping authors or contributors · 62%ultralytics/ultralytics →
“Shared author/contributor keys: han”
- FuzzyOverlapping authors or contributors · 62%HKUDS/LightRAG →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%DietrichGebert/ponytail →
“Shared author/contributor keys: cheng”