- Step1: Clone the GitHub repository and install dependencies with pip install -r requirements.txt.
- Step2: Configure your LLM API keys and tools in the provided YAML config file.
- Step3: Define custom tools by subclassing the base Tool interface and register them in config.
- Step4: Initialize an Agent instance, setting up the planner, memory, and tool registry.
- Step5: Execute the agent with a prompt via CLI or Python API and monitor the output.
- Step6: Extend or customize memory storage by implementing a new memory backend.
- Step7: Iterate on workflows by adjusting planner settings and adding new tools.