The data are from a pragmatic cluster-randomised trial in Ethiopia. Seventy-eight health facilities (clusters) were randomised to three arms (1:1:1): smart pillbox, medication labels, or standard of care. Adults (≥18 years) with drug-sensitive pulmonary tuberculosis on a fixed-dose combination tuberculosis treatment regimen were enrolled and followed-up for 12 months after treatment initiation. Those in the pillbox arm received a pillbox with customisable audio-visual reminders, while participants in the label arm received their TB medication with a weekly unique code label. Opening the box or texting the code prompted real-time dose logging on the adherence platform, facilitating differentiated response to individual’s adherence by a healthcare worker. The primary outcome comprised death, loss to follow-up, treatment failure, switch to drug-resistant tuberculosis treatment, or recurrence; secondary outcomes included loss to follow-up. Analysis accounted for clustered design with multiple imputation for the primary outcome. The trial is registered with PACTR202008776694999.