llm-council 0.1.3

Use LLM to generate and execute commands in your shell

llm-council

Get a council of LLMs to advise consult for you!

Installation

This plugin should be installed in the same environment as LLM.

llm install llm-council

Supported models/providers

The models themselves are fixed as of now with:

• openai: gpt-4o
• anthropic: clause-3.5-sonnet
• google: gemini-1.5-flash-latest

The necessary llm plugins are already installed. But you still need to set the keys

llm keys set openai
llm keys set claude
llm keys set gemini

Usage

I usually run every query on all LLMs just to see what they have to say. And I love the llm library. You can now assemble your own council of advisors by simply running llm council like this:

llm council 'whats the california traffic law around double white lines?'

By default, it uses openai and anthropic. But you can specify the providers by:

llm council -p openai -p anthropic 'tell me a joke'

Press Q or Ctrl + C to exit.

The system prompt

This is the prompt used by this tool:

Keep your answers brief and to the point.

Feel free to modify it by passing the --system arg.

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-council
uv venv
source .venv/bin/activate

uv pip install -r pyproject.toml

Now install the plugin with:

llm install -e .