Dayflow Download

Native macOS app that records screen at 1 FPS and generates AI-powered timeline of daily activities with Gemini, Ollama, or ChatGPT Claude, featuring distraction highlights and privacy-first design.

⭐ 5,126 stars on GitHub
Latest Release: v1.4.5

About Software

Dayflow is a native macOS SwiftUI app that records your screen at 1 FPS, analyzes it every 15 minutes with AI, and generates a clean timeline of activities with summaries and distraction highlights. The app is lightweight (25MB, ~100MB RAM) with configurable storage limits and auto-cleanup. Users can watch timelapses of their day and export timelines as Markdown.

Privacy-minded by design, users choose their AI provider: Gemini (bring your own API key), local models (Ollama/LM Studio for on-device processing), or ChatGPT/Claude CLI (requires paid subscription). Features include auto-updates with Sparkle, Daily Journal beta with intentions and reflections, and MIT licensing for full transparency. Built for macOS 13+ with Xcode 15+. Data stored locally in ~/Library/Application Support/Dayflow/ with complete user control.

Use Cases:

  • Native macOS app that records screen at 1 FPS and generates AI-powered timeline of daily activities
  • Automatic 15-minute analysis intervals with concise summaries and distraction highlights using Gemini, Ollama, or ChatGPT Claude
  • Watch timelapses of your day with configurable auto storage cleanup (1GB-20GB or unlimited)
  • Daily journal beta with morning intentions, evening reflections, AI summaries, and scheduled reminders
  • Privacy-first design with local-only processing options and MIT licensed open source

Downloads

v1.4.5 December 10, 2025
Dayflow.dmgdmg
v1.4.4 December 09, 2025
Dayflow.dmgdmg
v1.4.3 December 09, 2025
Dayflow.dmgdmg
v1.4.1 December 09, 2025
Dayflow.dmgdmg
v1.4.0 December 09, 2025
Dayflow.dmgdmg
v1.3.6 December 05, 2025
Dayflow.dmgdmg
v1.3.5 December 04, 2025
Dayflow.dmgdmg
v1.3.4 December 03, 2025
Dayflow.dmgdmg
v1.3.3 December 03, 2025
Dayflow.dmgdmg
v1.3.2 December 01, 2025
Dayflow.dmgdmg
v1.3.1 November 26, 2025
Dayflow.dmgdmg
v1.3.0 November 26, 2025
Dayflow.dmgdmg
v1.2.0 November 13, 2025
Dayflow.dmgdmg
v1.1.21 November 12, 2025
Dayflow.dmgdmg
v1.1.20 October 23, 2025
Dayflow.dmgdmg
v1.1.16 October 17, 2025
Dayflow.dmgdmg
v1.1.11 October 14, 2025
Dayflow.dmgdmg
v1.1.10 October 13, 2025
Dayflow.dmgdmg
v1.1.9 October 13, 2025
Dayflow.dmgdmg
v1.1.8 October 11, 2025
Dayflow.dmgdmg
v1.1.7 October 10, 2025
Dayflow.dmgdmg
v1.1.6 October 09, 2025
Dayflow.dmgdmg
v1.1.5 October 07, 2025
Dayflow.dmgdmg
v1.1.4 October 07, 2025
Dayflow.dmgdmg
v1.1.2 October 07, 2025
Dayflow.dmgdmg
v1.1.1 October 06, 2025
Dayflow.dmgdmg
v1.1.0 October 03, 2025
Dayflow.dmgdmg
v1.0.40 October 01, 2025
Dayflow.dmgdmg
v1.0.37 September 30, 2025
Dayflow.dmgdmg
v1.0.36 September 28, 2025
Dayflow.dmgdmg

Package Info

Last Updated
Dec 10, 2025
Latest Version
v1.4.5
License
MIT
Total Versions
30

README

A timeline of your day, automatically. Turns your screen activity into a clean timeline with AI summaries and distraction highlights.

Quickstart • Why I built Dayflow • Features • How it works • Installation • Data & Privacy • Automation • Debug & Developer Tools • Auto‑updates • Contributing


What is Dayflow?

Dayflow is a native macOS app (SwiftUI) that records your screen at 1 FPS, analyzes it every 15 minutes with AI, and generates a timeline of your activities with summaries. It's lightweight (25MB app size) and uses ~100MB of RAM and Privacy‑minded by design: You choose your AI provider. Use Gemini (bring your own API key), local models (Ollama / LM Studio), or ChatGPT/Claude (requires paid subscription). See Data & Privacy for details.

Why I built Dayflow

I built Dayflow after realizing that my calendar wasn't the source of truth for how I actually spent my time. My screen was. I wanted a calm, trustworthy timeline that let me see my workday without turning into yet another dashboard I had to maintain.

Dayflow stands for ownership and privacy by default. You control the data, you choose the AI provider, and you can keep everything local if that's what makes you comfortable. It's MIT licensed and fully open source because anything that watches your screen all day should be completely transparent about what it does with that information. The app should feel like a quiet assistant: respectful of your attention, honest about what it captures, and easy to shut off.


Features

  • Automatic timeline of your day with concise summaries.
  • 1 FPS recording - minimal CPU/storage impact.
  • 15-minute analysis intervals for timely updates.
  • Watch timelapses of your day.
  • Auto storage cleanup - configurable storage limits.
  • Distraction highlights to see what pulled you off‑task.
  • Timeline export — export your timeline as Markdown for any date range.
  • Native UX built with SwiftUI.
  • Auto‑updates with Sparkle (daily check + background download).

Daily Journal BETA

Set intentions, reflect on your day, and get AI-generated summaries of your activity.

  • Morning intentions — plan what you want to accomplish.
  • Evening reflections — review how your day actually went.
  • AI summaries — get auto-generated insights from your timeline.
  • Scheduled reminders — configurable notifications for intentions and reflections.
  • Weekly view — see patterns across your week.

Note: Journal is currently in beta with limited access. Enter your access code in the app to unlock it.

Coming soon

  • Infinitely customizable dashboard — ask any question about your workday, pipe the answers into tiles you arrange yourself, and track trends over time.

How it works

  1. Capture — Records screen at 1 FPS in 15-second chunks.
  2. Analyze — Every 15 minutes, sends recent footage to AI.
  3. Generate — AI creates timeline cards with activity summaries.
  4. Display — Shows your day as a visual timeline.
  5. Cleanup — Auto-manages storage based on your configured limits (1GB–20GB or unlimited).

AI Processing Pipeline

The efficiency of your timeline generation depends on your chosen AI provider:

flowchart LR
    subgraph Gemini["Gemini Flow: 2 LLM Calls"]
        direction LR
        GV[Video] --> GU[Upload + Transcribe1 LLM call] --> GC[Generate Cards1 LLM call] --> GD[Done]
    end

    subgraph Local["Local Flow: 33+ LLM Calls"]
        direction LR
        LV[Video] --> LE[Extract 30 frames] --> LD[30 descriptions30 LLM calls] --> LM[Merge1 call] --> LT[Title1 call] --> LC[Merge Check1 call] --> LMC[Merge Cards1 call] --> LD2[Done]
    end

<!-- truncated for display -->
See full README on repository.