传统计时器只记录应用停留时长，复盘与计费仍靠人工补记。Dayflow 用视觉模型把屏幕切片转成可检索的活动时间线，并支持本地模型运行，让个人与自由职业者在不出本机的前提下获得自动化的工作日志与周报复盘。

• 自动记录，免手动计时开单
• 识别上下文，还原实际所做
• 汇总轨迹，生成站会要点
• 对话检索，问答回溯工作
• 本地存储，守护屏幕隐私
• 支持本地与云端多种模型
• 采用MIT协议，社区可自由二次开发

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

A private, automatic work journal for Mac.

Dayflow understands the work you do on your Mac and turns it into a clear timeline of your day. Built from the ground up for privacy, it’s open source, local-first, and can run entirely with local AI.

Automatic Timeline

Dayflow turns raw screen activity into a chronological timeline of what you actually did, so you can reconstruct the day without timers or manual notes.

Daily Standup

See a GitHub-style activity grid of your day, plus yesterday's highlights, today's priorities, and blockers, so you can walk into standup with the update already written.

Weekly Review

See your week at a glance: when you were focused, where time went, which apps dominated, and what pulled you off track.

Chat With Your Work Journal

Ask questions about your day/week/year and get answers grounded in your timeline instead of digging through notes, screenshots, or memory.

What Dayflow Does

Dayflow runs quietly on your Mac and builds a useful record of your day from your screen activity.

Why People Use It

Most time trackers tell you which app was open. Dayflow tries to understand what you were doing.

Cursor for two hours could mean shipping a feature, debugging auth, reviewing a PR, or getting lost in setup. Dayflow gives you the context, not just the window title.

Privacy

Dayflow is local-first and open source.

Your recordings, timeline, and database live on your Mac at:

~/Library/Application Support/Dayflow/

You choose how AI analysis runs:

• Local models through Ollama or LM Studio
• Gemini with your own API key
• ChatGPT or Claude through their local CLI tools

If you choose a cloud provider, activity data needed for analysis is sent to that provider. If you choose local models, analysis stays on your machine.

Install

Download

Download the latest Dayflow.dmg from GitHub Releases:

Open the DMG, drag Dayflow into Applications, then grant macOS Screen & System Audio Recording permission when prompted.

Homebrew

brew install --cask dayflow

Requirements

• macOS 14+
• Screen & System Audio Recording permission
• Optional: Gemini API key, Ollama, LM Studio, Codex CLI, or Claude Code depending on your preferred AI provider

Build From Source

git clone https://github.com/JerryZLiu/Dayflow.git
cd Dayflow
open Dayflow/Dayflow.xcodeproj

Select the Dayflow scheme in Xcode and run it.

Contributing

Issues and pull requests are welcome. If you are planning a larger change, open an issue first so the scope is clear.

License

Dayflow is licensed under the MIT License.