Metadata-Version: 2.4
Name: zenobs
Version: 0.1.0
Summary: Zenobs is a tool for managing your inbox and projects.
Author-email: Juan Cobo Celdrán <jcoboceldran@gmail.com>
License: MIT
Keywords: ai,automation,cli,gemini
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Version Control :: Git
Classifier: Topic :: Utilities
Requires-Python: >=3.12
Requires-Dist: pydantic-ai>=1.70.0
Requires-Dist: pyyaml>=6.0
Description-Content-Type: text/markdown

# zenobs

**zenobs** is a small CLI that pairs an [Obsidian](https://obsidian.md/)-style vault with an AI agent. It helps you manage tasks, projects, meetings, people notes, and a per-project inbox from the terminal.

## Features

- **Interactive chat** (`zo chat`) — talk to the agent about your vault; it can read context and create or update tasks, projects, meetings, and people.
- **Inbox processing** (`zo inbox`) — the agent reads quick notes grouped by project, turns them into the right vault updates, and marks inbox entries as handled so they are not processed again.

The agent is built with [pydantic-ai](https://ai.pydantic.dev) and uses **Google Gemini** (see `MODEL` in `zenobs/agent.py`).

## Requirements

- **Python** 3.12 or newer
- A **vault directory** on disk: each top-level folder (except ignored names like `Inbox`, `inbox`, `.obsidian`, `People`) is treated as a project; vault-level people live under `People/` as Markdown notes.

Configure **Google Gemini API access** the way pydantic-ai expects for the `google-gla` provider (for example API keys or Vertex, depending on your setup). See the [pydantic-ai documentation](https://ai.pydantic.dev) for provider configuration.

## Installation

From the repository root, install in editable mode (recommended while developing):

```bash
pip install -e .
```

This exposes the **`zo`** command (see `[project.scripts]` in `pyproject.toml`).

## Usage

Run commands **from your vault root** (the folder `VaultManager` uses as `dir_path` — typically the current working directory).

```bash
zo chat    # interactive session
zo inbox   # process the inbox with the agent
```

## License

MIT — see `pyproject.toml` for authorship.
