# Apply Technique: LangGraph vs. CrewAI: Choosing the Right Agentic Framework for Production Workflows
## What This Is
For developers building complex AI assistants, LangGraph is the top choice for reliable, production-ready systems due to its robust control and state management. CrewAI is a simpler alternative, better suited for quickly prototyping multi-agent tasks with clear, sequential roles.
Source: https://www.youtube.com/watch?v=VT8yvoW1-3s
## Before You Start
Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)
Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?
## Source Access Note
The source URL (https://www.youtube.com/watch?v=VT8yvoW1-3s) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.
## What to Implement
This is an **AI Technique** — a pattern or methodology for working with AI models.
- Explain how this technique applies to my current project and what benefit it provides
- Implement it in a way that fits my existing codebase — suggest concrete files to modify or create
- If it requires specific model capabilities (structured output, function calling, etc.), verify my current provider supports them
- Show me a working example I can test immediately
## Additional Context
- Scan the user's current project to identify if an agentic framework like CrewAI or AutoGen is already in use. Report on the existing setup and its limitations based on the comparison table.
- Recommend LangGraph for complex, stateful, or long-running agentic workflows. If the user agrees, install the necessary Python packages: `langchain`, `langgraph`, and a model provider package like `langchain_openai` or `langchain_anthropic`.
- Generate a boilerplate `main.py` file demonstrating a basic LangGraph state machine. The graph should include at least two nodes (e.g., 'agent' and 'tool_executor') and an edge to show how state is passed, using the user's configured LLM provider from their environment variables.
## Guidelines
- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it