ModuleNotFoundError: No Module Named ‘langgraph’ (2026)

LangGraph is LangChain’s graph-based agent orchestration library, now the default way to build multi-agent AI systems in 2026. If you see ModuleNotFoundError: No module named ‘langgraph’, you need to install the package separately from langchain itself. Here is the full setup with checkpointer and LangSmith integration.

Step 1: Install langgraph

pip install langgraph

# With persistence (SQLite checkpointer):
pip install langgraph langgraph-checkpoint-sqlite

# With Postgres checkpointer:
pip install langgraph langgraph-checkpoint-postgres

# Full stack (most production deployments):
pip install langgraph langchain langchain-openai langgraph-checkpoint-sqlite

Step 2: Minimal agent example

from langgraph.graph import StateGraph, START, END
from typing import TypedDict

class State(TypedDict):
    messages: list

def chat_node(state):
    state['messages'].append("Hello from chat_node!")
    return state

workflow = StateGraph(State)
workflow.add_node("chat", chat_node)
workflow.add_edge(START, "chat")
workflow.add_edge("chat", END)

app = workflow.compile()
result = app.invoke({"messages": []})
print(result)

Step 3: Add checkpointer for state persistence

from langgraph.checkpoint.sqlite import SqliteSaver

memory = SqliteSaver.from_conn_string(":memory:")  # or "sqlite:///state.db"
app = workflow.compile(checkpointer=memory)

config = {"configurable": {"thread_id": "user-123"}}
app.invoke({"messages": []}, config=config)
# State persists across invocations under thread_id

Why this error happens

Diagnostic checklist for “No module named ‘langgraph'”

• Verify pip install target. Run pip show langgraph — if not installed, run pip install langgraph.
• Check the active Python interpreter. which python (mac/Linux) or where python (Windows). Both pip and python must point to the same environment.
• Check virtual environment activation. If you use venv/conda, activate before installing: source .venv/bin/activate.
• Rule out uppercase/lowercase. Python imports are case-sensitive: import PyPDF2 not import pypdf2.
• Rule out the pip-vs-package-name mismatch. Some packages install under a different name than you import (e.g. pip install beautifulsoup4 → import bs4).

Modern install for LLM frameworks

# 2026 recommended workflow — uv is fastest
pip install uv
uv pip install langgraph

# Or classic pip
pip install langgraph

# With extras for LLM providers
pip install "langgraph[openai,anthropic]"

Common “No module named ‘langgraph'” causes

• Version pinning conflict. LLM libraries update fast — pip install --upgrade langgraph if you saw the module before.
• Multiple Python versions. LLM tutorials often use Python 3.11 or 3.12. Verify python --version matches.
• Notebook kernel. Jupyter picks a different kernel than pip installs to. Use %pip install langgraph inside the notebook.
• WSL / Docker paths. Install in the same environment as your Python — not on the host if you run Python inside WSL.

Working code example

# Verify install
import langgraph
print(langgraph.__version__)

# Basic usage skeleton
# (adapt to your specific langgraph version)

Best practices

• Use a virtual environment for every LLM project. Dependencies overlap and pin conflicts are common.
• Pin your versions in requirements.txt or pyproject.toml. LLM libraries move fast.
• Consider uv or Poetry. Modern package managers handle dep resolution far better than pip alone.

Adrian Mercurio

Full-Stack Developer at PIES IT Solution

Specializes in building complete capstone projects with full documentation. Strong background in PHP/MySQL development and database design. Has personally built and tested over 30 capstone-ready projects with ER diagrams, DFDs, and chapter-by-chapter thesis documentation.

Expertise: PHP · Laravel · Database Design · Capstone Projects · C# · C · C++ · Python · AI Projects
 · View all posts by Adrian Mercurio →