Skills

Chapter 18 of 22

Langgraph Python Quickstart

Scaffold a minimal local LangGraph agent in Python by following the official quickstart.

1 minute · 212 words · 1 sections

Follow the live docs — do not invent an alternate API from memory:

https://docs.langchain.com/oss/python/langgraph/quickstart (opens in a new tab)

Fetch that page (Docs MCP or HTTP) and implement what it shows (calculator / math agent with the Graph API). Prefer the Graph API path over the Functional API unless the user asks otherwise. Skip IPython graph visualization.

Local setup constraints

Apply these on top of the quickstart (they keep setup minimal and model-agnostic):

Ask which provider/model to use. Showcase that LangGraph works with any LangChain chat model. Suggested prompt:

Which model should this agent use? Pass a provider:model string — e.g. openai:gpt-5.5, anthropic:claude-sonnet-5, google_genai:gemini-2.5-flash-lite. Default if you’re unsure: anthropic:claude-sonnet-5.

The docs often hardcode Anthropic — replace with init_chat_model("<MODEL>") (or equivalent) using their choice. If using Claude Sonnet 5+, omit temperature / top_p / top_k (unsupported).
Create a new directory (e.g. langgraph-agent/) and do all work there — do not pollute the open project.
Only secret: the provider API key in .env (gitignored). No LangSmith / Tavily unless they ask. Prefer they edit .env themselves — don’t paste keys into chat.
Install packages from the quickstart plus the provider package for their model.
Run the example (e.g. “Add 3 and 4.”), show output, then stop. Point to langgraph-fundamentals for next steps. For a higher-level agent API, use LangChain create_agent instead.

Install this repository

$ npx skills add langchain-ai/langchain-skills

» /plugin marketplace add langchain-ai/langchain-skills

Skills install per repository, not per chapter — the CLI has no documented per-skill form, so we do not print one.

About this skill

Trigger

Scaffold a minimal local LangGraph agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally.

The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.

Colophon for this issue

Colophon

How this issue was made

Source

github.com/langchain-ai/langchain-skills, branch main, last pushed 7 August 2026.

Licence

Discovery

22 chapters found by walking the repository tree for SKILL.md, not by matching a directory convention. One layout observed: config/skills/*/SKILL.md.

Issue colours

Resolved from a curated brand profile — hue 224°, chroma 0.190. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.

Heading repairs

1 repair applied to this chapter so the document has one h1 and no skipped levels:

Removed “LangGraph Python quickstart”, a leading h1 that duplicated the chapter title.

Spec compliance

Every chapter satisfies the Agent Skills specification’s frontmatter rules.

Images

Images inside a chapter come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.

Marketplace

A plugin manifest is published at .claude-plugin/marketplace.json by LangChain, declaring 1 plugin. It is read for editorial metadata only — never as the skill index, which is always the repository tree.

Signal

Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.

Agent surfaces

The whole issue is available as one markdown document at /langchain-ai/langchain-skills.md, and each chapter at its own .md URL.

Publication

Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.

Local setup constraints

Apply these on top of the quickstart (they keep setup minimal and model-agnostic):

Ask which provider/model to use. Showcase that LangGraph works with any LangChain chat model. Suggested prompt:

Which model should this agent use? Pass a provider:model string — e.g. openai:gpt-5.5, anthropic:claude-sonnet-5, google_genai:gemini-2.5-flash-lite. Default if you’re unsure: anthropic:claude-sonnet-5.

The docs often hardcode Anthropic — replace with init_chat_model("<MODEL>") (or equivalent) using their choice. If using Claude Sonnet 5+, omit temperature / top_p / top_k (unsupported).

Create a new directory (e.g. langgraph-agent/) and do all work there — do not pollute the open project.

Only secret: the provider API key in .env (gitignored). No LangSmith / Tavily unless they ask. Prefer they edit .env themselves — don’t paste keys into chat.

Install packages from the quickstart plus the provider package for their model.

Run the example (e.g. “Add 3 and 4.”), show output, then stop. Point to langgraph-fundamentals for next steps. For a higher-level agent API, use LangChain create_agent instead.