Skip to content

langchain-typescript-quickstart

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

4,900
installs
0 up / 0 down, score 0.00
votes
1,299
repo stars
Updated
less than a month ago
In the catalog since
1 Oct 2026
From
langchain-ai/langchain-skills
AI & Agents
Get it through your agent npx skills add langchain-ai/langchain-skills@langchain-typescript-quickstart

Skill instructions

Rendered from the published SKILL.md, 26 lines.

LangChain TypeScript quickstart

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

https://docs.langchain.com/oss/javascript/langchain/quickstart

Fetch that page (Docs MCP or HTTP) and implement what it shows (weather agent + createAgent). Requires Node 22+.

Local setup constraints

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

  1. Ask which provider/model to use. Showcase that LangChain is model-agnostic. 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.

    Swap the quickstart's model string for their choice (or the default).

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

  3. 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.

  4. Install the provider package needed for their model if the quickstart's base install isn't enough.

  5. Run the example, show output, then stop. Point to langchain-fundamentals for next steps.