LangChain's low-level orchestration framework, and the most widely used tool specifically for multi-agent systems in production — used internally at Replit, Uber, LinkedIn, and GitLab. Where the other four frameworks optimize for a single agent with tools, LangGraph's core abstraction is the graph itself.
Core concepts
- State, nodes, and edges: The whole framework is three primitives — state stores the current snapshot, nodes perform work (call an LLM, run a tool), edges decide what runs next, including conditional branches and loops. LangGraph Docs
- Why graphs over a single agent loop: Sequential flows, conditional branching, loops, and parallel execution are all explicit in the graph rather than hidden inside one opaque agent loop — easier to debug and reason about at scale.
- Supervisor and multi-agent patterns: A common pattern is a supervisor node routing work to specialist agent nodes, each operating in its own focused context — directly comparable to the handoffs pattern in OpenAI Agents SDK, but with more explicit control over the routing logic.
- Durable execution & human-in-the-loop: LangGraph 1.0 emphasizes persistence and the ability to pause a graph for human approval before a sensitive step, then resume exactly where it left off.
- LangGraph vs CrewAI vs AutoGen: LangGraph is lower-level and more flexible but needs more setup; CrewAI's role-based pattern (each agent has a job title, goal, and tools) and AutoGen are faster to start but less customizable — pick LangGraph when you need fine-grained control, CrewAI for fast iteration on a multi-agent demo.
Why it matters
Support bots and research pipelines have branching you can draw on a whiteboard. Checkpointing lets a run survive a crash or wait for a human to approve something.
Where people get stuck
- Huge graphs nobody can diagram. If the team can't sketch it, debugging will hurt.
- Saving a massive state blob on every step. Checkpoint cost and latency add up quickly.
- Starting with LangGraph before you understand a plain tool loop. Graphs wrap the same primitives.
Try this
Draw classify, retrieve, answer on paper, then build the smallest LangGraph tutorial that matches your sketch.
Interview question
Why use a graph instead of a while loop?
Branching, parallelism, persistence and visualization become explicit. That pays off for non-linear or restartable workflows and is overkill for a straight tool chain.
Resources
- LangGraph Docs
- GitHub: langgraph
- LangGraph Announcement Blog
- LangChain Academy: LangGraph (free course)
- CrewAI · AutoGen/AG2 — worth knowing as the higher-level alternatives
YouTube learning
Core concepts from video walkthroughs:

