Dayflow is a privacy-focused productivity tool that records screen activity locally and analyzes it with on-device AI. It captures screen frames at one frame per second, stores everything in a local database, and processes all analysis entirely on the machine to keep data private. The system builds a searchable timeline of work activity and enables natural-language queries about past screen time.
The tool distinguishes itself by offering runtime switching between local AI models and cloud providers, allowing users to balance accuracy, privacy, and performance. It automatically runs AI inference every 15 minutes on buffered frames to classify activity and generate narrative summaries. A menu bar controller provides persistent controls for starting, stopping, and pausing recording, while configurable storage limits automatically purge old recordings to prevent disk overflow.
The system generates standup-ready summaries from analyzed recordings, produces daily and weekly activity reviews, and supports exporting the chronological work journal as Markdown for any date range. It answers plain-language questions about past activity using the timeline as a grounded source, and can aggregate weekly data into focus patterns, app usage, and distraction tracking.
