Metadata-Version: 2.4
Name: judy-cli
Version: 0.8.6
Summary: multiple-agent code cli
Author-email: wonx314 <kunjinkao2@gmail.com>
Requires-Python: >=3.13
Requires-Dist: aiofile>=3.9.0
Requires-Dist: aiofiles>=24.1.0
Requires-Dist: contexttimer
Requires-Dist: dotenv>=0.9.9
Requires-Dist: google-auth>=2.49.1
Requires-Dist: judy-core==0.8.6
Requires-Dist: judy-env==0.8.6
Requires-Dist: litellm
Requires-Dist: prompt-toolkit>=3.0.52
Requires-Dist: pydantic
Requires-Dist: pyfiglet>=1.0.2
Requires-Dist: rich
Requires-Dist: toml>=0.10.2
Requires-Dist: typer>=0.24.1
Description-Content-Type: text/markdown

# Installation
```bash
uv tool install judy-cli
# Start
judy
```

# Configuration
After starting, enter `/config` to set the model and API key parameters. For the model name format, please refer to the litellm documentation: https://docs.litellm.ai/docs/providers .
For example, if you are using the gemini model from google ai studio, the model name is: gemini/gemini-3.1-pro-preview .
Other provider-specific parameters should be set via environment variables before starting.

# Usage
```bash
judy --task "what is this project about"
judy --task "write an example of calling openai llm"

# Or after starting, enter tasks interactively
judy
```

In interactive mode: Press `!` at the beginning of the sentence or double-press `escape` to toggle between command mode and task mode.
