Appendix C: Quick Overview of Agentic Frameworks

Quick reference guide comparing major agentic frameworks and their capabilities

Beginner12 min readInteractive Playground

Appendix CBeginner

Quick Overview of Agentic Frameworks

Comprehensive comparison of LangChain, LangGraph, Google ADK, CrewAI, and other major agentic frameworks

Framework Quick Reference

The landscape of agentic frameworks offers a diverse spectrum of tools, from low-level libraries for defining agent logic to high-level platforms for orchestrating multi-agent collaboration. This guide provides a comprehensive comparison to help you choose the right tool for your project.

🦜

LangChain

The Universal Orchestrator - Linear Workflows

LangChain is a framework for developing applications powered by LLMs. Its core strength lies in its LangChain Expression Language (LCEL), which allows you to "pipe" components together into a chain. This creates a clear, linear sequence where the output of one step becomes the input for the next. It's built for workflows that are Directed Acyclic Graphs (DAGs), meaning the process flows in one direction without loops.

Use it for:

Simple RAG: Retrieve a document, create a prompt, get an answer from an LLM
Summarization: Take user text, feed it to a summarization prompt, and return the output
Extraction: Extract structured data (like JSON) from a block of text

Key Strengths:

Largest ecosystem with 50+ integrations
Strong memory handling
Production-ready architecture

Considerations:

Steeper learning curve
Can be heavy for simple tasks

📊

LangGraph

Stateful Workflows with Cycles

LangGraph is a library built on top of LangChain to handle more advanced agentic systems. It allows you to define your workflow as a graph with nodes (functions or LCEL chains) and edges (conditional logic). Its main advantage is the ability to create cycles, allowing the application to loop, retry, or call tools in a flexible order until a task is complete. It explicitly manages the application state, which is passed between nodes and updated throughout the process.

Use it for:

Multi-agent Systems: A supervisor agent routes tasks to specialized worker agents
Plan-and-Execute Agents: An agent creates a plan, executes a step, and loops back to update the plan
Human-in-the-Loop: The graph can wait for human input before deciding which node to go to next

Key Strengths:

Cyclical workflows with loops
Explicit state management
Built-in checkpointing

🔷

Google's ADK

Enterprise Gemini Integration

Google's Agent Development Kit (ADK) provides a high-level, structured framework for building and deploying applications composed of multiple, interacting AI agents. It contrasts with LangChain and LangGraph by offering a more opinionated and production-oriented system for orchestrating agent collaboration. ADK abstracts away much of the low-level graph construction, providing pre-built architectural patterns for multi-agent interaction.

Key Features:

Built-in agent types (SequentialAgent, ParallelAgent)
Native Gemini support
Enterprise-grade security
Managed infrastructure

Considerations:

Tied to Google ecosystem
Less granular control than LangGraph

👥

CrewAI

Role-Based Task Execution

CrewAI offers an orchestration framework for building multi-agent systems by focusing on collaborative roles and structured processes. It operates at a higher level of abstraction than foundational toolkits, providing a conceptual model that mirrors a human team. Instead of defining the granular flow of logic as a graph, the developer defines the actors and their assignments, and CrewAI manages their interaction.

Core Components:

Agents: Defined by role, goal, and backstory
Tasks: Discrete units of work with clear descriptions
Crew: Cohesive unit containing agents and tasks
Process: Sequential or hierarchical workflow

Key Strengths:

Easy to learn and use
Natural task delegation
Built-in replay features

Other Notable Frameworks

Microsoft AutoGen

Multi-Agent Conversations

AutoGen is a framework centered on orchestrating multiple agents that solve tasks through conversation. Its architecture enables agents with distinct capabilities to interact, allowing for complex problem decomposition and collaborative resolution. The primary advantage is its flexible, conversation-driven approach that supports dynamic and complex multi-agent interactions.

LlamaIndex

Data Framework for LLMs

LlamaIndex is fundamentally a data framework designed to connect large language models with external and private data sources. It excels at creating sophisticated data ingestion and retrieval pipelines, which are essential for building knowledgeable agents that can perform RAG. While its data indexing and querying capabilities are exceptionally powerful, its native tools for complex agentic control flow are less developed compared to agent-first frameworks.

Haystack

Production-Ready Search Systems

Haystack is an open-source framework engineered for building scalable and production-ready search systems powered by language models. Its architecture is composed of modular, interoperable nodes that form pipelines for document retrieval, question answering, and summarization. The main strength is its focus on performance and scalability for large-scale information retrieval tasks.

Strands Agents (AWS)

Lightweight and Flexible SDK

An AWS lightweight and flexible SDK that uses a model-driven approach for building and running AI agents. It is designed to be simple and scalable, supporting everything from basic conversational assistants to complex multi-agent autonomous systems. The framework is model-agnostic and includes native integration with the MCP for easy access to external tools.

Appendix C: Quick Overview of Agentic Frameworks

Quick reference guide comparing major agentic frameworks and their capabilities

Beginner12 min readInteractive Playground

Appendix CBeginner

Quick Overview of Agentic Frameworks

Comprehensive comparison of LangChain, LangGraph, Google ADK, CrewAI, and other major agentic frameworks

Framework Quick Reference

🦜

LangChain

The Universal Orchestrator - Linear Workflows

Use it for:

Simple RAG: Retrieve a document, create a prompt, get an answer from an LLM
Summarization: Take user text, feed it to a summarization prompt, and return the output
Extraction: Extract structured data (like JSON) from a block of text

Key Strengths:

Largest ecosystem with 50+ integrations
Strong memory handling
Production-ready architecture

Considerations:

Steeper learning curve
Can be heavy for simple tasks

📊

LangGraph

Stateful Workflows with Cycles

Use it for:

Multi-agent Systems: A supervisor agent routes tasks to specialized worker agents
Plan-and-Execute Agents: An agent creates a plan, executes a step, and loops back to update the plan
Human-in-the-Loop: The graph can wait for human input before deciding which node to go to next

Key Strengths:

Cyclical workflows with loops
Explicit state management
Built-in checkpointing

🔷

Google's ADK

Enterprise Gemini Integration

Key Features:

Built-in agent types (SequentialAgent, ParallelAgent)
Native Gemini support
Enterprise-grade security
Managed infrastructure

Considerations:

Tied to Google ecosystem
Less granular control than LangGraph

👥

CrewAI

Role-Based Task Execution

Core Components:

Agents: Defined by role, goal, and backstory
Tasks: Discrete units of work with clear descriptions
Crew: Cohesive unit containing agents and tasks
Process: Sequential or hierarchical workflow

Key Strengths:

Easy to learn and use
Natural task delegation
Built-in replay features

Other Notable Frameworks

Microsoft AutoGen

Multi-Agent Conversations

LlamaIndex

Data Framework for LLMs

Haystack

Production-Ready Search Systems

Strands Agents (AWS)

Lightweight and Flexible SDK