Langgraph Fundamentals

A comprehensive reference for building agent workflows with LangGraph's state-based approach. Covers the essential patterns you'll need: designing state schemas with proper reducers (so your message lists actually append instead of overwrite), implementing nodes that return partial state updates, and wiring together conditional edges. The 5-step design methodology is solid for mapping complex workflows to graphs. Includes TypeScript and Python examples for StateGraph basics, Command/Send for advanced routing, and streaming patterns. Most useful when you need fine-grained control over agent orchestration beyond what basic LangChain agents provide.

skills.sh installs: 18.9K
GitHub stars: 1.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add langchain-ai/langchain-skills --skill langgraph-fundamentals --agent claude-code

Installs into .claude/skills of the current project.

Files

LangGraph models agent workflows as **directed graphs**:

StateGraph: Main class for building stateful graphs
Nodes: Functions that perform work and update state
Edges: Define execution order (static or conditional)
START/END: Special nodes marking entry and exit points
State with Reducers: Control how state updates are merged

Graphs must be compile()d before execution.

Designing a LangGraph application

Follow these 5 steps when building a new graph:

Map out discrete steps — sketch a flowchart of your workflow. Each step becomes a node.
Identify what each step does — categorize nodes: LLM step, data step, action step, or user input step. For each, determine static context (prompt), dynamic context (from state), retry strategy, and desired outcome.
Design your state — state is shared memory for all nodes. Store raw data, format prompts on-demand inside nodes.
Build your nodes — implement each step as a function that takes state and returns partial updates.
Wire it together — connect nodes with edges, add conditional routing, compile with a checkpointer if needed.

SKILL.md on GitHub