worktick 1.1.0

Local CLI for tracking tasks, git commits, and generating summaries

worktick

Track your work, capture git commits, generate summaries. All local. No cloud. No accounts.

Why

Time tracking shouldn't require browser extensions, web apps, or yet another account. Your org wants quantified task output — they don't care how you track it. But manually logging hours, copy-pasting commit messages, and formatting standup notes is tedious busywork.

worktick runs entirely on your machine. Start a timer, code as usual, and it auto-captures your git commits across repos. When you stop, it generates markdown summaries you can paste directly into Trello, Slack, or standup notes. Optional local AI tools add meeting minutes from mic recordings — no audio leaves your machine.

Quick Start

pip install worktick

wt start "Fix auth bug"
# ... code, commit as usual ...
wt note "Tested in Postman"
wt stop
wt summary today

Output:

## 2026-03-08 (Saturday)

**Fix auth bug** (2h 15m)
- Fix token refresh logic (abc123d)
- Add retry on 401 responses (def456a)
- Tested in Postman

**Total: 2h 15m**

Ready to paste into Trello, Slack, or your standup notes.

Install

pip install worktick

Or with uv (recommended for CLI tools):

uv tool install worktick

This installs two commands: worktick (full name) and wt (short alias). All examples below use wt.

Help

wt --help                # list all commands
wt summary --help        # help for a specific command
wt mom --help            # list subcommands under mom
wt mom stop --help       # help for a nested subcommand
wt config --help         # list subcommands under config

Every command and subcommand supports --help.

Commands

Core

These work out of the box — no extra setup needed.

Command	Description
wt start "title" [--card URL]	Start a new task timer
wt stop [--at HH:MM]	Stop timer, capture git commits
wt status	Show current task and elapsed time
wt pause / wt resume	Pause and resume the timer
wt note "text"	Add a note to the current task
wt list [--days N]	List recent tasks
wt summary [today|yesterday|week] [--edit] [--push]	Generate markdown summary (+ webhook)
wt daily [today|yesterday|week] [--edit] [--push]	Compact hours summary (Ollama optional, + webhook)
wt repo [path]	Register git repo(s)
wt cancel	Discard the current task
wt edit ID [--title T] [--card U]	Edit a past task
wt config set <key> <value>	Set config (e.g. webhook_url)
wt config show	Show current config
wt config unset <key>	Clear a config value

Meeting Minutes

These require optional AI tools (see Setup below).

Command	Description
wt mom listen	Start recording from mic
wt mom pause / wt mom resume	Pause and resume recording
wt mom stop [--model M]	Stop, transcribe, generate minutes
wt mom file <path> [--model M]	Generate minutes from a file or stdin
wt mom list	List all saved meetings
wt mom show <id> [--transcript]	View minutes (or raw transcript with -t)
wt mom edit <id>	Edit minutes in $EDITOR
wt mom push <id> [--edit]	Push meeting minutes to webhook
wt mom retry <id> [--model M]	Retry a failed meeting

What needs what:

Command	Ollama	whisper.cpp	sox/ffmpeg
wt daily	optional	—	—
wt mom file <text-file>	required	—	—
wt mom file <audio-file>	required	required	—
wt mom listen/stop	required	required	required
wt mom list/show/edit/push/retry	—	—	—

Example Workflow

wt start "Fix auth bug" --card https://trello.com/c/xxx
wt repo /path/to/workspace/myorg

# code, commit as usual...
git commit -m "Fix token refresh logic"
wt note "Tested flow in Postman"

wt stop
wt summary today

wt summary output

## 2026-03-08 (Saturday)

**Fix auth bug** (2h 15m) [Trello](https://trello.com/c/xxx)
- Fix token refresh logic (abc123d)
- Add retry on 401 responses (def456a)
- Tested flow in Postman

**Build email automation** (1h 30m) [Trello](https://trello.com/c/yyy)
- Created webhook trigger for new signups
- Connected to SendGrid email node

**Daily standup** (15m)
- Sprint planning for next week

**Total: 4h 00m**

wt daily output

Compact format for quick standups. Titles cleaned up by Ollama if available.

Sat, 08 Mar 2026 - 4.00H

- 2.25H - Fixed auth token refresh and added retry on 401
- 1.50H - Built email automation with SendGrid webhooks
- 0.25H - Daily standup

wt mom — meeting minutes

wt mom listen              # start recording
wt mom pause               # pause during break
wt mom resume              # resume
wt mom stop                # stop → transcribe → generate minutes

wt mom file transcript.txt  # from text file
wt mom file meeting.wav    # from audio file
pbpaste | wt mom file -    # from clipboard (macOS)

Webhook Push

Push summaries to an n8n webhook (or any URL that accepts JSON POST) for forwarding to Trello, Slack, etc.

wt config set webhook_url https://n8n.example.com/webhook/abc123
wt summary today --push     # prints summary + POSTs to webhook
wt daily --push              # prints daily + POSTs to webhook
wt mom push <id>             # push meeting minutes to webhook

Summaries and daily reports always print and copy to clipboard first. --push then sends the markdown to your webhook. For meeting minutes, use wt mom push <id> after reviewing with wt mom show <id>. Webhook failures are warnings — they never block output.

Multi-Repo Git Tracking

Git repos are auto-detected from your working directory. You can also register repos explicitly:

wt repo /path/to/repo              # single repo
wt repo /path/to/workspace/org     # scan children for git repos

On wt stop, commits are scanned from all registered repos.

Setup for AI Features

The core commands work with zero setup. The tools below are only needed for AI-powered features (wt daily title cleanup, wt mom meeting minutes).

1. Ollama — Local LLM

Required for wt mom (meeting minutes). Optional for wt daily (cleans up task titles — falls back to raw titles without it).

macOS:

brew install ollama

Linux:

curl -fsSL https://ollama.com/install.sh | sh

Windows:

Download from ollama.com/download.

Then pull a model and start the server:

ollama pull gemma3             # ~5GB, works well on 16GB RAM
ollama serve                   # keep running in background

2. whisper.cpp — Local Speech-to-Text

Required for audio transcription (wt mom listen/stop and wt mom file <audio-file>). Not needed for text input (wt mom file notes.txt).

macOS:

brew install whisper-cpp

Linux / Build from source:

git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp && cmake -B build && cmake --build build --config Release
sudo cp build/bin/whisper-cli /usr/local/bin/

Windows:

Download pre-built binaries from whisper.cpp releases and add whisper-cli to your PATH.

Then download a model:

mkdir -p ~/.cache/whisper

# Medium model (~1.5GB) — best accuracy
curl -L -o ~/.cache/whisper/ggml-medium.bin \
  https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.bin

# Or base model (~150MB) — faster, slightly lower accuracy
curl -L -o ~/.cache/whisper/ggml-base.bin \
  https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin

All models: huggingface.co/ggerganov/whisper.cpp

3. sox or ffmpeg — Audio Recording

Required only for live mic recording (wt mom listen). sox is preferred for cleaner audio. ffmpeg works as a fallback.

macOS:

brew install sox              # recommended

Linux (Debian/Ubuntu):

sudo apt install sox          # recommended
# or: sudo apt install ffmpeg

Linux (Fedora/RHEL):

sudo dnf install sox
# or: sudo dnf install ffmpeg

Windows:

# With Chocolatey
choco install sox
# or: choco install ffmpeg

# With Scoop
scoop install sox
# or: scoop install ffmpeg

The code tries sox first, falls back to ffmpeg automatically.

Data Storage

All data is stored locally in ~/.worktick/ as JSON files:

File	Purpose
tasks.json	Task entries with timestamps, commits, notes
meetings.json	Meeting minutes with transcript, status, audio path
recording.json	Active recording state — auto-cleaned on stop
config.json	Configuration (webhook URL, audio device)

All writes are atomic (temp file + rename) to prevent corruption. No data leaves your machine.

System Audio Recording

Capture Google Meet, Zoom, or Teams audio with BlackHole:

brew install blackhole-2ch
wt config set audio_device "BlackHole 2ch"

Set up a Multi-Output Device in Audio MIDI Setup so you hear audio AND it routes to BlackHole. See the full README for details.

License

MIT