apcore
Cognitive Interface for AI Agents
apcore is an AI-native module standard that provides a Cognitive Interface for AI Agents. It ensures every module is inherently understandable by AI through enforced schemas, directory-as-ID discovery, and behavioral annotations. The framework organizes the AI Collaboration Lifecycle into four key stages: Discovery, Strategy, Governance, and Recovery. Featuring a secured execution lifecycle with a unified APCore client and enterprise-grade observability, apcore enables self-healing agents through standardized AI Guidance. Built to be language-agnostic, it provides seamless consistency across Python, TypeScript, and Rust.
Interactive apcore-js Demo
Experience schema-enforced module development with our TypeScript SDK.
Features
Get Started
Python reference implementation of the apcore specification.
$ pip install apcorefrom apcore import APCore
client = APCore()
@client.module(id="math.add", description="Add two numbers")
def add(a: int, b: int) -> dict:
return {"sum": a + b}
result = client.call("math.add", {"a": 10, "b": 5})
