CogniCoreAI: Build, Test, and Deploy Robust Conversational AI

CogniCoreAI is a modular Python framework for building sophisticated conversational AI agents. It is designed from the ground up to be extensible, testable, and easy to use.

Whether you’re building a simple chatbot or a complex, tool-using agent, CogniCoreAI provides the foundational blocks you need, with a unique focus on behavioral simulation to ensure your agents are reliable and perform as expected.

CogniCoreAI Logo

Key Features

  • Modular & Extensible: Swap out components like LLMs, memory, and tools with ease thanks to a clean, abstraction-based design.

  • Powerful Tool Integration: Equip your agents with tools to interact with APIs, databases, or any other external service.

  • Built-in Simulation Framework: Go beyond unit tests. Write behavioral scenarios to validate your agent’s reasoning and decision-making process.

  • LLM Agnostic: Ships with an OpenAI client but is designed to work with any Large Language Model.

  • Modern & Tested: Built with modern Python practices and a comprehensive test suite.

Quick Start

Get up and running in minutes. First, install the library:

uv pip install cognicoreai

Now, create and chat with your first agent. Make sure your OPENAI_API_KEY environment variable is set.

 1from cognicoreai import Agent, OpenAI_LLM, VolatileMemory, CalculatorTool
 2
 3# 1. Assemble the agent's components
 4llm = OpenAI_LLM()
 5memory = VolatileMemory()
 6tools = [CalculatorTool()]
 7
 8# 2. Create the agent
 9agent = Agent(llm, memory, tools)
10
11# 3. Start chatting!
12response = agent.chat("What is 125 divided by 5?")
13print(response)

Table of Contents

Explore the documentation to learn more about how to use and extend CogniCoreAI.

Documentation