Metadata-Version: 2.4
Name: probegpt
Version: 0.1.0
Summary: Automated red-team discovery for AI models
License-Expression: MIT
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: pydantic-ai>=1.63.0
Requires-Dist: openai>=2.0.0
Requires-Dist: azure-identity>=1.15.0
Requires-Dist: rich>=13.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: httpx>=0.27.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: textual>=8.0.0

# outofthebox

Automated red-team discovery for AI models. Generates probe prompts, sends them to a target model, judges responses against your objective, and iteratively refines the best-scoring probes.

## Install

```bash
pipx install probegpt
```

## Usage

```bash
probegpt
```

Full-screen TUI. Set up your models in **Config**, then go to **Run Discovery**, enter your objective, and hit **Run**.

## Models

Supports two providers per role (target / generator / judge):

- **Azure OpenAI** — uses `az login` credentials automatically
- **OpenRouter** — set `OPENROUTER_API_KEY` in a `.env` file or your environment

Config is saved to `~/.outofthebox/config.json`.

## How it works

1. Loads 9 seed probes covering known red-team techniques
2. **Iteration 1** — generator writes N probes targeting your objective
3. **Iteration 2+** — top-scoring probes from the previous round seed mutation + fresh objective variants
4. Each probe is sent to the target model; the judge scores the response against your objective (0.0 → 1.0)
5. Results optionally exported to JSON

## Requirements

- Python 3.11+
- For Azure: `az login` with access to your deployment
- For OpenRouter: `OPENROUTER_API_KEY` env var
