Dayflow
Dayflow is a macOS productivity tool that automatically records screen activity and converts it into a structured work journal using AI analysis. It runs locally and privately on your Mac, with optional integration to cloud AI providers like ChatGPT, Claude, or Gemini.
Key facts
Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.
| Field | Value |
|---|---|
| Repository | JerryZLiu/Dayflow |
| Owner | JerryZLiu |
| Primary language | Swift |
| License | MIT — OSI-approved |
| Stars | 6.6k |
| Forks | 372 |
| Open issues | 72 |
| Latest release | v2.0.0 (2026-07-03) |
| Last updated | 2026-07-03 |
| Source | https://github.com/JerryZLiu/Dayflow |
What Dayflow is
Swift-based macOS application that captures lightweight screen recordings, processes them through pluggable AI backends (local Ollama/LM Studio or cloud APIs), and maintains a local SQLite-style database of timeline events. Provides natural-language chat interface over accumulated activity data.
Get the Dayflow source
Clone the repository and explore it locally.
git clone https://github.com/JerryZLiu/Dayflow.gitcd Dayflow# follow the project's README for install & configurationNeed it deployed, integrated, or customized instead? DEV.co ships production installs.
Best use cases
Implementation considerations
- Requires explicit macOS Screen & System Audio Recording permissions; users must grant and maintain access in System Preferences.
- AI provider setup is user-selected: choose between local models (Ollama/LM Studio setup required), free Gemini API, or CLI-based ChatGPT/Claude. Each path has different latency and privacy tradeoffs.
- Storage grows over time with screen recordings; configure automatic cleanup via storage limits to prevent disk exhaustion.
- Screen recording may impact system performance on older Macs or under heavy workload; monitor CPU/memory during continuous capture.
- Data lives in ~/Library/Application Support/Dayflow/ and is not automatically synced or backed up; user is responsible for retention and disaster recovery.
When to avoid it — and what to weigh
- Regulatory data residency requirements — If using cloud AI backends (Gemini, ChatGPT, Claude), screen summaries are sent to external providers. On-premises or regulated environments may require local AI only, which depends on third-party tool availability.
- Centralized team surveillance — Dayflow is single-device, local-first. Organizations needing centralized employee monitoring across many users should use purpose-built MDM or workforce analytics platforms.
- Real-time compliance or audit logging — Dayflow is designed for personal reflection, not forensic audit trails or legal hold. It lacks immutable logging, chain-of-custody controls, or integration with SIEM systems.
- Windows or Linux environments — macOS-only application (requires macOS 14+). No Windows or Linux support mentioned.
License & commercial use
MIT License: permissive, allows commercial use, modification, and distribution with attribution and inclusion of license text. No restrictions on proprietary applications built on top.
MIT License permits commercial use, including bundling or reselling. However, verify that your intended use (e.g., white-label SaaS, hardware appliance) aligns with MIT terms. If bundling cloud AI provider code or integrations, review those providers' separate ToS. No commercial support or warranty mentioned in source data.
DEV.co evaluation signals
Editorial assessment — not user reviews. Directional, with an explicit confidence level.
| Signal | Assessment |
|---|---|
| Maintenance | Active |
| Documentation | Adequate |
| License clarity | Clear |
| Deployment complexity | Low |
| DEV.co fit | Good |
| Assessment confidence | High |
Local-first design reduces exposure if using local AI backends. If using cloud AI, screen summaries are sent to third-party providers (Google, OpenAI, Anthropic, etc.); review their privacy policies and data retention terms. macOS permissions model gates access; app can only record screens when permission is granted. No mention of encryption at rest, secure deletion, or audit logging. Screen recordings are stored plaintext on disk; deletion via automatic cleanup or manual removal. No signature verification or code signing claims provided.
Alternatives to consider
RescueTime
Mature commercial time tracking with cloud analytics, integrations to 100+ tools, and team dashboards. Requires sending activity data to servers; less privacy-focused than Dayflow.
Toggl Track
Popular manual and automatic time tracking with team features, invoicing, and reporting. Cloud-based; requires user action to start timers. Simpler than Dayflow but less AI-driven context.
Hugging Face / Local LLM workflows
If you only need the AI/NLP layer, you can run local models (Ollama, LM Studio, vLLM) independently. Requires building your own screen capture and timeline UI.
Build on Dayflow with DEV.co software developers
Download Dayflow for Mac or review the source on GitHub. Choose your AI backend (local, Gemini, ChatGPT, or Claude) and start capturing your day.
Talk to DEV.coRelated open-source tools
Surfaced by semantic similarity across the DEV.co open-source index.
Related on DEV.co
Explore the category and the services that help you build with it.
Dayflow FAQ
Does Dayflow upload my screen recordings to the cloud?
Can I export my timeline data?
Is there a Windows version?
How much disk space does Dayflow use?
Work with a software development agency
DEV.co helps companies turn open-source tools like Dayflow into production software. Our software development services cover the full lifecycle — architecture, web development, integration, and maintenance — delivered by software developers and web developers who ship. Engage our software development agency to implement or customize it for your ai frameworks stack.
Ready to automate your work journal?
Download Dayflow for Mac or review the source on GitHub. Choose your AI backend (local, Gemini, ChatGPT, or Claude) and start capturing your day.