Updated LLMs · Core Abstractions: Chains vs. State Graphs
Chains vs. State Graphs: Why LangGraph Exists
Linear chains are DAGs. Agents need cycles, shared state, and checkpoints. A look at the abstraction shift.
Patterns
Reference-style write-ups: the production version of each pattern, with trade-offs and failure modes.
LLMs · Core Abstractions: Chains vs. State Graphs
State vs. Memory: Why Context Windows Aren't Enough
A checkpointer remembers one thread. Agents also need to remember users across sessions and search corpora far larger than any context window. Where each kind of memory lives, and how to wire both into a LangGraph agent.
LLMs · Tool Calling Mechanics & Execution Loops
The Execution Loop: Translating LLM JSON into Real-World Action
A model can't do anything; it can only emit JSON that asks for something to be done. How tool schemas reach the model, how the application executes the calls and feeds results back, and what LangGraph's ToolNode handles for you.