Metadata-Version: 2.4
Name: chad-ai
Version: 0.3.3
Summary: Chad: YOLO AI
Author: Team Chad: AI Police
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Build Tools
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.31.0
Requires-Dist: bcrypt>=4.0.0
Requires-Dist: cryptography>=41.0.0
Requires-Dist: gradio>=4.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.4.0; extra == "dev"
Requires-Dist: black>=23.0.0; extra == "dev"

# Chad: YOLO AI

Coding agents need hand holding to implement complex features, but no one holds Chad's hand.

- Installs and logs you in to Codex, Claude Code, Gemini, or Mistral Vibe coding agent sessions
- Chad can break your tasks down in a management session, and prompt the coding agent running in a separate session
- When a coding agent starts equivocating or half-baking Chad can verify and reprompt until the task is complete

<p style="text-align: center;">
  <img src="docs/Chad.png" alt="Chad Code" width="80">
</p>

**The First Warning:** Chad was developed with...  Chad. Yes, this material writes itself. No, high quality robust code 
this is not. 

**World Warning II:** Chad is a risk-taker who knows no limits. Chad has access to everything on your hard drive and 
your internet connection. Responsible models will stop Chad if they have the right context to do so, and I added a 
safety prompt which will try to give them that context. However, if Chad REALLY wants to complete your task there
are only so many ways I can explicitly prohibit it from ruining your life.

### Blah blah how do I run it?
```bash
pip install chad-ai
chad 
```

### How is this better than $Grug?

- Gradio ui to make it easy to add and remove agents, assign them to roles, change their preferred model, and view their usage
- Provider tokens encrypted with a master password you create and supply every session, which can be wiped by specifying a new password at login

<p style="text-align: center;">
  <img src="docs/screenshot.png" width="800">
</p>

### Is this satire?

Sadly, no. "As a society, what are we even doing here?" might be a better question.
