JerryZLiu/Dayflow

The automatic work journal/time tracker. Privately turns your screen into a timeline of what you actually accomplished. Open-source and local-first.

What it solves

Dayflow solves the problem of manual time tracking and vague activity logs. Instead of just recording which application was open, it captures the actual context of your work to create an automatic, searchable work journal, eliminating the need for timers or manual note-taking.

How it works

The application runs in the background on macOS, capturing lightweight screen chunks and system audio. It analyzes these captures using an AI provider of the user's choice (local models via Ollama/LM Studio or cloud APIs like Gemini, ChatGPT, and Claude) to transform raw screen activity into a chronological timeline of activity cards.

Who it’s for

It is designed for Mac users who want to maintain a detailed record of their workday for standups, weekly reviews, or personal productivity analysis without the friction of manual logging.

Highlights

  • Automatic Timeline: Converts screen activity into a clear, chronological record of work.
  • Context-Aware Summaries: Understands what is happening on screen rather than just tracking window titles.
  • Chat with Journal: A natural-language interface to ask questions about past activity and recover details.
  • Local-First Privacy: Stores all recordings and databases locally on the Mac, with the option to use entirely local AI models for analysis.
  • Standup & Review Tools: Automatically generates daily highlights, priorities, and blockers, and provides weekly analytics on focus patterns.
  • Flexible AI Backend: Supports multiple providers including local LLMs and major cloud AI services.

Related

  • Project
    openclaw/Peekaboo

    Peekaboo is a macOS‑only CLI and menu‑bar app that captures the screen, reads the accessibility tree, and performs native UI actions (click, type, press, etc.). It includes an LLM‑driven “agent” that can translate natural‑language instructions into sequences of these commands, and it can be exposed to external AI clients via a Model‑Control‑Protocol (MCP). Install via Homebrew, npm, or a signed DMG; configure model providers in `~/.peekaboo`. Ideal for GUI automation, testing, and building AI agents that control the desktop.

  • Project
    nossa-y/activity-frames

    activity‑frames records your screen locally, compiles raw snapshots into deterministic “activity frames”, and exposes them as compact context blocks or executable scripts for AI agents, dramatically reducing token cost and improving reliability of repeated computer‑use tasks.

  • Project
    FutureUniant/WorkShadow

    A local-first desktop work log application that uses AI for semantic search, automated report generation, and Q&A over personal work history while keeping data on the user's machine.

  • Project
    Git-Agni/prod-FARM-IOS-Core

    An open-source application for managing physical iOS devices to run scheduled automation workflows, featuring a built-in TikTok plugin and remote control capabilities.

  • Project
    Deyweaver/DeyWeaver

    An AI-integrated productivity tool that auto-schedules your day, breaks down large tasks, and provides burnout prediction based on work patterns.