This release is a pre-release and may not be stable for production use.
Workday
AI 驱动的工作时间追踪工具。自动以 1 FPS 录制屏幕,通过两阶段 LLM 分析生成每日活动时间线。
参考 Dayflow 设计,Python 跨平台实现,桌面 GUI 基于 CustomTkinter。
快速开始
环境要求:Python >= 3.12,uv
# 安装依赖
uv sync
# 启动 GUI
uv run workday
启动后在「设置」页面填写 API Base URL、API Key 和模型 ID。支持任何兼容 OpenAI API 的服务(OpenAI、火山引擎 ARK、本地 Ollama 等)。
使用方法
uv run workday # 启动桌面 GUI
uv run workday --version # 查看版本
启动 GUI 后:
- 点击左下角「开始录制」开始屏幕录制
- 录制数据自动提交后台 AI 分析
- 在「时间线」视图查看生成的活动卡片
- 在「仪表盘」查看 Token 用量统计
- 在「设置」修改录制和分析参数
工作原理
屏幕截图 (1 FPS)
│ 每 15 秒打包为视频片段
▼
Stage 1 LLM:视频 → 3-5 条观察记录
▼
Stage 2 LLM:观察记录 → 活动卡片(15-60 分钟/张)
▼
时间线(工作 / 学习 / 娱乐 / 其他)
数据存储
所有数据本地保存,不上传云端(仅调用 LLM API 时传输屏幕内容):
workday.db # SQLite 数据库(配置 + 活动数据)
recordings/ # 屏幕录制视频片段
logs/ # 运行日志
开发
uv sync --all-extras # 安装开发依赖
uv run pytest # 运行测试
uv run ruff check src/ # Lint
uv run ruff format src/ # 格式化
许可证
MIT
Release files for workday-py 0.1.0b1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| workday_py-0.1.0b1.tar.gz | 959.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| workday_py-0.1.0b1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.1 MB
Release files / workday_py-0.1.0b1.tar.gz
| Download URL | workday_py-0.1.0b1.tar.gz |
|---|---|
| Size | 959.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5b5edee1a114c6648685e487b44f30e175863b23a851e3799cf7eb0bf2434021
|
|
BLAKE2b-256 checksum How to use checksums |
8d6ab09aebc4af0e84fd8c0ed7441422d7fdd0b5fb9da97a8061ce7ed7558c60
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 2, 2026.
Transparency logRelease files / workday_py-0.1.0b1-py3-none-any.whl
| Download URL | workday_py-0.1.0b1-py3-none-any.whl |
|---|---|
| Size | 182.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b18019340cf3f42b948c49cfc7516e2823959403b3daf0ecec84146d9aa6cdd4
|
|
BLAKE2b-256 checksum How to use checksums |
a376aee84addea7b03a88281d7dd92d0481992a3627c7a21471697bb68f6b10d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 2, 2026.
Transparency log