awesome-agentic-ai: Your Comprehensive Hub for Agentic AI Resources

Introduction

awesome-agentic-ai is a comprehensive GitHub repository dedicated to Agentic AI, offering a curated list of tools, frameworks, and learning resources. Agentic AI refers to artificial intelligence systems that can act autonomously, make decisions, collaborate with other agents, use tools dynamically, and learn from experience. This repository serves as a central hub for anyone looking to dive into this cutting-edge field, from foundational concepts to advanced production systems. It provides structured learning paths, practical examples, and an up-to-date overview of the Agentic AI landscape.

Installation

Getting started with Agentic AI tools from this repository is straightforward. You can use the quick start script or manually install specific frameworks.

For a complete development environment, use the automated setup script:

curl -sSL https://raw.githubusercontent.com/yadavanujkumar/awesome-agentic-ai/main/scripts/setup.sh | bash

To install specific frameworks, use pip:

# For beginners - start with LangChain
pip install langchain langchain-community langchain-openai langgraph

# For multi-agent systems - try AutoGen
pip install autogen-agentchat==0.7.0 autogen-ext

# For role-based agents - use CrewAI
pip install crewai==1.1.0 crewai-tools

# For data-heavy applications - use LlamaIndex
pip install llama-index==0.14.0 llama-index-core

Examples

The repository provides numerous practical examples to help you build your own Agentic AI systems. Here are a couple of highlights.

Customer Support Agent

This example demonstrates a production-ready customer support agent using LangChain and LangGraph, capable of checking order status and searching a knowledge base.

from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langchain_core.tools import tool
from langchain_community.tools import DuckDuckGoSearchRun

@tool
def search_knowledge_base(query: str) -> str:
    """Search company knowledge base for relevant information."""
    knowledge = {
        "refund": "Refunds are processed within 5-7 business days to original payment method",
        "shipping": "Standard shipping takes 3-5 days, Express 1-2 days",
        "returns": "Returns accepted within 30 days with original receipt"
    }
    for key, value in knowledge.items():
        if key in query.lower():
            return value
    return "Please contact our support team for more information"

@tool
def check_order_status(order_id: str) -> str:
    """Check the current status of a customer order."""
    orders = {
        "ORD-12345": "Shipped - Expected delivery Mar 12, 2026",
        "ORD-67890": "Processing - Will ship within 24 hours"
    }
    return orders.get(order_id, "Order not found. Please verify order number.")

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
tools = [search_knowledge_base, check_order_status, DuckDuckGoSearchRun()]
agent = create_react_agent(llm, tools)

result = agent.invoke({
    "messages": [("user", "Hi, I need to check my order ORD-12345 and learn about your return policy")]
})
print(result['messages'][-1].content)

Simple Calculator Agent

A basic agent that uses a calculator tool to evaluate mathematical expressions.

from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langchain_core.tools import tool

@tool
def calculator(expression: str) -> str:
    """Evaluate a mathematical expression safely."""
    try:
        import ast, operator
        ops = {ast.Add: operator.add, ast.Sub: operator.sub, ast.Mult: operator.mul, ast.Div: operator.truediv,}
        def eval_expr(node):
            if isinstance(node, ast.Num): return node.n
            elif isinstance(node, ast.BinOp): return ops[type(node.op)](eval_expr(node.left), eval_expr(node.right))
            else: raise ValueError(f"Unsupported operation: {node}")
        node = ast.parse(expression, mode='eval')
        return str(eval_expr(node.body))
    except Exception as e:
        return f"Error: {str(e)}"

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
agent = create_react_agent(llm, [calculator])
result = agent.invoke({"messages": [("user", "What is 25 * 4 + 10?")]})

Why Use awesome-agentic-ai?

This repository stands out as an invaluable resource for several reasons:

Comprehensive Learning Paths: It offers structured roadmaps for beginners, intermediate, and expert users, guiding them through the complexities of Agentic AI development.
Up-to-Date Information: Regularly refreshed, including the latest July 2026 updates on models, APIs, and frameworks like OpenAI Responses API, Microsoft Agent Framework, and Google ADK.
Practical Frameworks and Tools: Provides a detailed overview and comparison of production-ready frameworks such as LangGraph, CrewAI, LlamaIndex, and AutoGen, alongside emerging technologies and enterprise platforms.
Real-World Use Cases: Features concrete examples for personal assistants, research agents, coding agents, multi-agent collaboration, and enterprise solutions, illustrating the practical applications of Agentic AI.
Rich Resource Collection: Beyond code, it curates essential papers, video tutorials, books, courses, and development tools, making it a one-stop shop for learning and building.