tai/AGENTS.md

# AGENTS.md

## Conventions

- Use plain `import` and `from` statements in Python files.
- Use the `.py` extension for Python source and test files.
- Keep source and test files at the repository top level.
- Name test files `test_*.py`.

## Agent Overview

- `tai`: The main autonomous agent.
- `devops`: A bot that manages the DevPlace DevOps platform.

## Agent Profiles

- `default`: Default agent profile for general tasks.
- `work`: Work-focused agent profile.
- `dev`: Development-focused agent profile.

## Bot Details

- `devops`: A bot that automates DevPlace DevOps operations.
  - Manages workspaces, projects, and deployments.
  - Handles user authentication and access control.
  - Provides development tools and utilities.
  - Integrates with OpenShift Dev Spaces.

## Key Features

- Autonomous decision making
- Multi-profile support
- Background subagent orchestration
- Secure vault storage
- Container sandbox support
- Progress tracking
- Interactive REPL
- Command-line interface

## Usage Examples

1. Start the main agent:
   ```bash
   ./tai.py
   ```

2. Use a specific profile:
   ```bash
   ./tai.py --profile work
   ```

3. Run a one-shot command:
   ```bash
   ./tai.py what is 2+3, use the shell
   ```

4. Check agent status:
   ```bash
   ./tai.py --version
   ```

5. Install the agent:
   ```bash
   ./tai.py --install
   ```

## Development Guidelines

- Write clear, concise code
- Follow Python conventions
- Test thoroughly
- Use the agent for documentation
- Keep code maintainable
- Document decisions
- Version control changes
- Collaborate effectively