Metadata-Version: 2.4
Name: voxn
Version: 0.3.1
Summary: Local voice note-taking suite
Project-URL: Homepage, https://github.com/okrinoggen33/voxn
Project-URL: Repository, https://github.com/okrinoggen33/voxn
Project-URL: Issues, https://github.com/okrinoggen33/voxn/issues
Author: okrinoggen
License: MIT
License-File: LICENSE
Keywords: fts5,local-first,notes,ollama,sqlite,voice
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: End Users/Desktop
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Utilities
Requires-Python: >=3.11
Requires-Dist: typer>=0.12
Provides-Extra: dev
Requires-Dist: build; extra == 'dev'
Requires-Dist: pytest-cov; extra == 'dev'
Requires-Dist: pytest>=8; extra == 'dev'
Requires-Dist: twine; extra == 'dev'
Provides-Extra: whisper
Requires-Dist: faster-whisper; extra == 'whisper'
Description-Content-Type: text/markdown

# voxn

`voxn` is a local-first note and memory CLI for Linux. It captures voice or text
notes, stores them as Markdown under `~/.local/share/voxn/`, indexes them into
SQLite FTS5, and exposes search, context, browse, ingest, and digest commands.

The default LLM path uses local Ollama. Remote OpenAI-compatible providers are
optional; storage remains local.

## Install

For a Python-only install:

```bash
pipx install 'voxn[whisper]'
# or
pip install 'voxn[whisper]'
```

For the full voice workflow, install system tools separately:

```bash
# Arch example
sudo pacman -S sox fzf sqlite wl-clipboard libnotify poppler
sudo pacman -S ollama    # or ollama-rocm
```

Then start Ollama and pull a model:

```bash
systemctl enable --now ollama
ollama pull gemma3:12b
voxn doctor
```

## Quick Start

```bash
voxn add -p my-project "Capture this decision"
voxn doctor
voxn index --rebuild
voxn search -p my-project "decision"
voxn context -p my-project
```

Voice capture uses the bare command as a toggle:

```bash
voxn          # start recording
voxn          # stop, transcribe, format, and save
```

## Main Commands

- `voxn add`: save direct text or stdin as a structured note.
- `voxn ingest`: summarize a file, URL, PDF, video, or stdin into notes.
- `voxn index`: rebuild the SQLite search index from Markdown notes.
- `voxn remove`: remove one indexed note from Markdown and SQLite.
- `voxn search`: search indexed notes by text, project, category, tag, or date.
- `voxn context`: emit a prompt-ready project memory block for agents.
- `voxn browse`: browse notes or generated wiki pages interactively with `fzf`.
- `voxn digest`: generate local wiki pages from notes.
- `voxn doctor`: check dependencies and bootstrap configured data paths.

## Configuration

Default local paths:

- Notes: `~/.local/share/voxn/voxns.md`
- SQLite DB: `~/.local/share/voxn/notes.db`
- Wiki output: `~/.local/share/voxn/wiki/`

`voxn doctor` creates those paths and initializes the DB when they are missing.

Configuration is read from `${XDG_CONFIG_HOME:-~/.config}/voxn/config.toml`
when present, then overridden by environment variables. Common environment
variables:

- `VOXN_CONFIG_FILE`
- `VOXN_NOTES_FILE`
- `VOXN_DB`
- `VOXN_DIGEST_DIR`
- `VOXN_LLM_PROVIDER`
- `VOXN_LLM_MODEL`
- `VOXN_LLM_BASE_URL`

## More Documentation

The repository README contains the full install guide, systemd user units, AUR
packaging notes, architecture details, and contributor documentation:

https://github.com/okrinoggen33/voxn
