Background: High-resolution digital cognitive tools administered at frequent intervals enable the study of age-related cognitive change at a previously unattainable level of granularity. Computational modeling further enables the simultaneous examination of multiple aspects of cognitive performance. Objective: The objective of this study was to examine whether repeated digital multiday learning assessments can detect age-related cognitive decline over short time frames in cognitively unimpaired older adults and to quantify age-related differences in process-based cognitive markers derived from computational modeling. Methods: A total of 209 cognitively unimpaired older adults (mean age 73.6, SD 8.2 years; n=136, 65.1% female) from the Harvard Aging Brain Study and affiliated studies were administered the Boston Remote Assessment for Neurocognitive Health, which includes the face-name task, a paired associative learning task. Daily median response times for correct responses were used as the primary outcome. A new version of the face-name task was administered across up to 4 testing intervals over a mean of 2.8 (SD 0.4) years. Using computational modeling, we estimated longitudinal changes in peak performance, a practice-adjusted marker of an individual’s best expected response time, as an indicator of age-related cognitive decline. We further examined age-related differences in peak performance, stability (within-person variability), learning within and across testing intervals, and between-interval forgetting, with embedded linear regressions for age, sex, years of education, and device type. Results: Peak performance slowed by 0.04 seconds per year (95% credible interval 0.02-0.06; approximately 2% per year), indicating age-related cognitive decline. Higher age (+1-SD) was associated with slower peak performance (+0.19 seconds, 95% credible interval 0.12-0.26), steeper annual slowing in peak performance (+0.036 seconds per year), greater within-person variability (+0.043 seconds), reduced learning across testing intervals, and more forgetting. Conclusions: Our findings indicate that a digital multiday learning paradigm combined with computational modeling of response times sensitively detects age-related cognitive decline over short timescales (