Get the weekly radar
One short email with the freshest products, every week.
Dayflow journals your workday on Mac by screenshotting your activity, no manual tracking.
Grounded in available product and source data
Manually logging what you worked on is the part of time tracking almost everyone abandons within a week. Dayflow is an automatic AI work journal for Mac built around skipping that step entirely — it takes periodic screenshots and uses AI to understand actual work context, not just which app happened to be in the foreground.
That context becomes a Timeline view showing a visual record of the day's work with timestamps, rolled up into daily and weekly summaries, with a chat interface for asking questions about past activity instead of scrolling back through raw logs. Work gets sorted into categories — Research, Coding, Communication, Planning, and Distraction — and a dedicated standup-update feature turns the day's tracked activity into something ready to paste into a status update, rather than requiring a user to reconstruct it from memory.
Where the AI processing actually runs is a real choice, not a fixed default: local AI through Ollama or LM Studio keeps everything fully offline, while cloud options through Gemini, ChatGPT, or Claude trade that for more capable models, with ChatGPT and Claude requiring a paid plan with their respective services. Switching providers is available at any time, so a user isn't locked into whichever option they picked during setup. Privacy in local mode is specific rather than a marketing line: the site states nothing leaves the computer, screenshots stay stored locally, and the underlying code is open source on GitHub for anyone who wants to verify that claim directly.
Dayflow is free under the MIT License, backed by Y Combinator, and the site cites 6.1k GitHub stars along with users from companies like Meta and Google. One real constraint worth flagging: it currently requires macOS 14 Sonoma or later and runs only on Mac, with a Windows version announced as coming but not yet available — Windows users would need to wait or look elsewhere for now.
Not in local mode — the site states nothing leaves the computer when using local AI through Ollama or LM Studio, with screenshots stored locally and full user control over deletion.
No — activity gets categorized automatically into types like Research, Coding, and Communication based on what the AI interprets from screenshots, rather than requiring a user to tag each block of time themselves.
Yes — cloud AI options include Gemini (with a free tier), ChatGPT, and Claude, though the latter two require a paid plan with that respective service, and a user can switch providers at any time.
Wait for the announced Windows release or use a different tool in the meantime — there's no timeline given for when it ships, so anyone needing cross-platform tracking now shouldn't plan around it arriving soon.
Yes — it's free and open source under the MIT License, though using a cloud AI provider like ChatGPT or Claude for processing requires a separate paid plan with that service.
These 1 comments were collected from the discovery source. ProductVisit does not host replies in Release A.
Hey Product Hunt 👋 I'm Jerry, founder of Dayflow. Here's a bitter lesson that everyone learns first-hand: the person who gets promoted isn't the one who did the best work. It's the one who can remember it and come with receipts. You know the feeling. Your manager asks "what did you ship this quarter," and your mind goes blank. You spent three months heads-down, debugging the gnarly thing, unblocking teammates, rewriting the pipeline that was about to fall over, and now you're squinting at a git log trying to reverse-engineer your own life. The work was real. The memory of it just evaporated. So the people who are great at narrating their work get ahead, and the people heads-down doing it get overlooked. That always felt backwards. So we built Dayflow. Dayflow runs quietly on your Mac, and uses your screen data + AI to turn your day into a clean timeline of what you actually worked on. No timers, no tagging. You just work, and at the end of the day there's an honest record of it. Come review season, your brag doc is already written. When you wonder where the week went, there's an answer instead of a shrug. 🔒 Local-first and open source. The recording stays on your machine, and the code's on GitHub. 🧠 A witness, not a manager. It's yours, built to help you see your own work, not score you. ⚡ Zero effort. No categorizing, no Pomodoro guilt. It just runs. 🎁 For Product Hunt: a month of Dayflow Pro free. Or use Dayflow for free forever by bringing your own AI, whether that's a local model or plugging in your ChatGPT/Claude subscription. I'll be around all day. I'd love to know: when someone asks what you got done this week, do you actually have an answer, or do you go blank too? Show more