@toolkitai/magnetic

magnetic by Toolkit

magnetic is a way to run shareable, and reusable tool-powered LLM / agent workflows. We think of it as an agent/workflow runner & package manager for AI tools and workflows, that can easily be run, expanded and combined to powerful effect.

Here's a few examples to give you the vibe:

Magnetic is still in Beta and may change at any time.

Installation

1. Clone the repository:

   git clone https://github.com/toolkit-ai/magnet-cli-v2.git
   

2. Navigate to the project directory:

   cd magnet-cli-v2
   

3. Install dependencies:

   bun install
   

Usage

magnet-context offers several commands:

• run: Executes a workflow
• create-recipe: Creates a new recipe (composition of workflows)
• list-recipes: Lists available recipes (compositions of workflows)
• list-models: Lists available AI models
• list-workflows: Lists available workflows
• create-workflow: Creates a new workflow file
• pipe: Runs a series of workflows, piping the output of each to the next similar to the UNIX pipe command
• agent: (Coming soon, an agent that composes and runs workflows for you)

Example usage:

# Create a new recipe
bun run start create-recipe

# Run a workflow from a recipe file
bun run start run --recipe recipes/project-overview.yaml

# Run a workflow with CLI parameters
bun run start run --workflow generate-knowledge-from-codebase --context.directory . --context.instructions "Please write a project overview" --metadata.title "Project Overview" --metadata.description "Writes an overview of the current project including general pattern, stack, and structure"

# List available workflows
bun run start list-workflows

# Create a new workflow
bun run start create-workflow

# Pipe multiple workflows together
bun run start pipe read-file count-words write-file

Development

To run tests:

bun run test

Configuration

The tool supports various configuration options, including:

• Debug mode
• Custom directories for output and logs
• AI model selection

These can be set via command-line options or environment variables.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.