A personal, local-first work activity log and review tool.
Automatically organizes the apps you used, websites you visited, window titles, and optional screenshot records throughout your day into a reviewable, question-answerable work timeline.
All data is stored locally by default and never uploaded to any server. AI features are entirely optional; the app works fine with them turned off.
Work Review is designed for individuals who want to answer questions like these:
- What did I actually do today?
- What have I been focusing on over the past few days?
- Roughly how much time did a particular task take?
- Which pages, windows, and context did I look at back then?
- How can I quickly put together today's daily report?
The focus is not on "monitoring" but on helping you recall, organize, and review your own work process.
- Automatic work trail recording — Automatically captures foreground apps, website visits, window titles, optional screenshots, and OCR text, minimizing manual note-taking and after-the-fact recall
- A unified work timeline — Overview, timeline, work assistant, and daily report all share the same underlying records, letting you view statistics and drill down to specific pages and context
- Direct answers to work questions — Answers questions like "What did I do today?", "What have I been focusing on recently?", and "What are my pending items?" based on local records
- Daily report generation and export — Structured daily reports, historical review, Markdown export with auto-export, AI-enhanced prompt attachments and paragraph-level editing
- Desktop Avatar Beta — The first step toward a personal work Agent, evolving into a desktop partner that can sense work context, proactively remind, and assist with decisions
- Privacy-first, locally controllable — Data stored in local SQLite; AI can remain disabled by default, model calls use your own API Key without third-party relay
Work Review is designed for personal use from the ground up. It is not intended for: employee monitoring · team attendance · performance evaluation · covert tracking
You can control the recording scope as needed:
- Per-app settings: Normal / Anonymize / Ignore — anonymize mode automatically skips screenshots and OCR
- Automatic sensitive keyword filtering · domain blacklist
- Auto-pause on screen lock · manual pause/resume
- AI only activates after you configure a model; disabled by default
- Automatically detects the foreground app, tracking usage duration, window titles, and categories
- Identifies browser URLs and aggregates visit records by site/page
- Periodic screenshots with OCR text extraction, supporting multi-display strategies
- Keyboard/mouse + screen idle detection to reduce false records during idle time
- Timeline replay to review specific context from any time period
- Work assistant: Q&A based on local records, with multi-model switching support
- Automatically understands natural language time ranges like "yesterday", "this week", "last N days"
- Fragments grouped into continuous work sessions
- Extracts potential follow-up to-dos from pages, window titles, and context
- Two response modes: basic template and AI-enhanced
- Generate structured daily reports with historical review
- Markdown export and automatic export
- Hourly activity summaries
- AI-enhanced prompt attachments and paragraph editing
- Website semantic categorization: changing a domain category automatically backfills history
- Multi-segment work time: e.g. morning + afternoon, break time excluded
The core of Work Review is always local recording. AI's role is to make records easier to read and review, not a prerequisite for usage.
| Mode | Description |
|---|---|
| Basic Template | Zero configuration, outputs stable structured results |
| AI Enhanced | Calls your self-configured model service for more natural Q&A and summaries |
Supported providers: Ollama (local) / OpenAI compatible / DeepSeek / Qwen / Zhipu / Kimi / Doubao / MiniMax / SiliconFlow / Gemini / Claude
- Download the installer for your platform from Releases
- On macOS, grant Screen Recording and Accessibility permissions
- Let it run in the background for a while
- Check the Overview / Timeline / Daily Report to see your recorded activity
| Platform | Installer |
|---|---|
| macOS (Apple Silicon / Intel) | .dmg |
| Windows | .exe |
| Linux x86_64 (X11 / Wayland) | .deb / .AppImage |
| Linux ARM64 (aarch64) | .deb |
macOS: Screenshots require the "Screen Recording" permission, and avatar linkage requires "Accessibility + Input Monitoring". If you see a "damaged" warning on first launch: sudo xattr -rd com.apple.quarantine "/Applications/Work Review.app"
Windows: Depends on Microsoft Edge WebView2 Runtime.
Linux: Screenshots and window tracking depend on the current session type and toolchain.
Dependency details
# Base
sudo apt install xprintidle tesseract-ocr
# X11
sudo apt install xdotool x11-utils scrot
# Wayland: gdbus (GNOME) / kdotool (KDE) / swaymsg (Sway) / hyprctl (Hyprland)
# Screenshots: grim / gnome-screenshot / spectacleDesktop Avatar
Uses a standalone desktop pet window to reflect idle / working / reading / meeting / music / video states.
Still being actively refined — interaction linkage, expressions, and preset details will continue to improve.
Bot Integration (Telegram / Feishu)
Query records and generate daily reports remotely from Telegram / Feishu via local API + multi-device registration. Supported commands: /devices, /report, /generate, etc. Restricted to personal and own multi-device use only.
MCP Server
Connects work records to AI coding tools (Claude Code / Cursor / VS Code Copilot, etc.) via the stdio protocol.
cargo build --release -p work-review-mcp-server{
"mcpServers": {
"work-review": {
"command": "/path/to/work-review-mcp-server",
"env": {
"WORK_REVIEW_DB_PATH": "/path/to/work_review.db",
"WORK_REVIEW_CONFIG_PATH": "/path/to/config.json"
}
}
}
}npm install
npm run tauri:dev # Development
npm run tauri:build # BuildRequires: Node.js 18+ / Rust stable / Tauri 2 CLI · Tech stack: Tauri 2 + Rust + Svelte 4 + SQLite
WeChat Group
If the QR code has expired, follow the official account below for the latest group invitation, or join the TG group
WeChat Official Account
- Thanks to the linux.do community for discussion and feedback
- Desktop Avatar BongoCat resources adapted from ayangweb/BongoCat (MIT License), see THIRD_PARTY_NOTICES.md
MIT