Skip to content

A lightweight, extensible Python framework for building agentic AI systems with modular agents, tools, planning, memory, and workflow orchestration.

License

Notifications You must be signed in to change notification settings

BlodgettDavid/AgenticAI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AgenticAI Framework

A lightweight, extensible Python framework for building agentic AI systems. The goal of AgenticAI is to provide a clean, modular foundation for agents, tools, planning, memory, and workflow orchestration. It is designed to be simple enough for beginners to understand, yet flexible enough to support advanced multi-agent systems in future iterations.

This repository contains the core framework only. A separate repository (AgenticAI-App) demonstrates how to build applications on top of this framework.


Key Features (Iteration 1)

  • Minimal, backend-agnostic LLM client abstraction
  • ResearchAgent for simple agentic workflows
  • PlanningAgent for step extraction and multi-step detection
  • WorkflowAgent for executing plans and coordinating tool use
  • Modular tool system (definition, summarization, search, math, file)
  • Basic memory abstractions (episodic, vector, base memory)
  • Clean architecture with clear separation of concerns
  • Examples directory for future demos
  • Tests directory for future unit tests
  • Fully editable installation for development

Project Structure

agenticai/
    llm_client.py          – Minimal LLM abstraction layer
    agents/                – High-level agents (ResearchAgent)
    core/                  – Base agent, messages, reasoning utilities
    memory/                – Memory abstractions and MemoryAgent
    orchestration/         – Planner, router, supervisor (future)
    planning/              – Plan model and PlanningAgent
    tools/                 – Built-in tools (search, summarize, define, etc.)
    utils/                 – Config and logging placeholders
    workflow/              – WorkflowAgent for executing plans

docs/
    architecture.md        – Architectural notes (future expansion)
    patterns.md            – Design patterns and usage notes
    roadmap.md             – Future development roadmap

examples/
    simple_agent_demo.py   – Placeholder for basic agent usage
    tool_use_demo.py       – Placeholder for tool demonstration
    multi_agent_demo.py    – Placeholder for multi-agent orchestration

tests/
    (empty for Iteration 1; reserved for future unit tests)

Installation (Development Mode)

Clone the repository and install in editable mode:

pip install -e .

This allows you to modify the framework and immediately test changes without reinstalling.


Basic Usage Example

Below is a minimal example of how to use the ResearchAgent with the built-in tools.
This example assumes you have installed the framework in editable mode.

from agenticai.agents.research_agent import ResearchAgent
from agenticai.tools.definition_tool import DefinitionTool
from agenticai.tools.summarizer_tool import SummarizerTool
from agenticai.llm_client import LLMClient

llm = LLMClient()
tools = [
    DefinitionTool(llm_client=llm),
    SummarizerTool(llm_client=llm)
]

agent = ResearchAgent(llm_client=llm, tools=tools)
response = agent.run("define quantum computing")
print(response)

Design Philosophy

AgenticAI is built around five core principles:

1. Simplicity

The framework should be easy to read, understand, and extend.

2. Modularity

Agents, tools, memory, planning, and workflow are cleanly separated.

3. Extensibility

New tools, agents, and workflows can be added without modifying core components.

4. Backend-Agnostic

The LLMClient abstraction allows you to plug in any LLM provider.

5. Transparency

The framework avoids hidden magic. All logic is explicit and inspectable.


Roadmap (High-Level)

Iteration 2

  • Implement real planning logic
  • Add clarifying question generation
  • Add tool selection improvements
  • Add basic memory retrieval
  • Add real examples in the examples directory
  • Add initial unit tests

Iteration 3

  • Multi-agent orchestration (Supervisor, Router)
  • Advanced workflow execution
  • Tool chaining and intermediate reasoning
  • Vector memory integration
  • Logging and tracing utilities

Iteration 4+

  • Real LLM integration (Azure OpenAI, OpenAI, local models)
  • Streaming responses
  • Retry logic and rate limiting
  • Plugin system for third-party tools
  • Full documentation site

Contributing

Contributions are welcome. The project is intentionally simple in Iteration 1 to allow for clean growth.
Please open issues or submit pull requests for discussion.


License

This project is licensed under the MIT License.

About

A lightweight, extensible Python framework for building agentic AI systems with modular agents, tools, planning, memory, and workflow orchestration.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages