Key API Ideas

This section highlights some of the key technical aspects of the library.

Tip

The tutorials provide an annotated step-by-step guide with a domain.

Overview

  • Knowledge-Augmented Decision Process (KADP): (hierarchical) agent orchestration using a declarative, state-driven execution machine that continually matches against policy directives.

  • Cognitive Agent (Cogent): integrating the cognitive agent loop with custom environmental sensors and/or actuators (similar to a harness in LLM-based systems).

  • Knowledge Representation Module: declaring, relating, and querying dynamic domain knowledge.

  • Planning: integrating symbolic reasoning to efficiently & verifiably solve sub-problems.

  • Language: model-agnostic language tasks that are automatically infused with domain knowledge.

Guiding Principles

Flexible

The library gives you wings to build impactful agents your way, for your problems, with your tools.

Opinionated

Through layered modules, the API guides you towards our view of strong agent design.

Collaborative

The library, in coordination with amazing imports, tries to play nice with Python tooling (e.g., IDE, type checking).

Declarative(‘ish)

Where reasonable, the library makes encourages you to describe what (vs how).

Clean/Fun

Where possible, abstract away boilerplate.