Researchers developed HealthClaw, an open-source agent architecture designed to update support as a person's routines, preferences, measurements, and risks change over time. It separates shared safety rules and medical knowledge from private longitudinal memory containing profile facts, reusable procedures, and episodic traces.
- Evaluated on a synthetic year-long benchmark and nine 200-case biomedical tasks, HealthClaw increased answer accuracy from 0.2% to 45.7% across 900 longitudinal support probes.
- Prompt-side context exposure was 71.7% lower than with full-history prompting.
- In 100 privacy probes, it produced higher privacy-aware answer quality and fewer unsafe disclosures than baselines.
- Across biomedical tasks, the mean absolute gain in the primary metric was 27.0 percentage points, with seven gains remaining significant after false-discovery-rate correction.
These offline benchmarks support governed, self-evolving memory for longitudinal personal health agents, although clinical effectiveness requires prospective evaluation.