deepagents-typescript-quickstart

$npx mdskill add langchain-ai/langchain-skills/deepagents-typescript-quickstart

Scaffold a minimal local Deep Agent in TypeScript using provider-native web search.

  • User wants to quickly build or try a Deep Agent locally.
  • Depends on Node 22+, LangChain docs, and chosen provider's built-in web search.
  • Asks user for provider:model string, defaults to anthropic:claude-sonnet-5.
  • Creates a new directory, implements research agent, and runs with a sample question.

SKILL.md

.github/skills/deepagents-typescript-quickstartView on GitHub ↗
---
name: deepagents-typescript-quickstart
description: "Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally."
---

# Deep Agents TypeScript quickstart

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

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

Fetch that page (Docs MCP or HTTP) and implement the research-agent shape it shows (`createDeepAgent`, research system prompt, invoke with a research question like “What is LangGraph?”). 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 Deep Agents are 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-3.5-flash`. Default if you're unsure: **`anthropic:claude-sonnet-5`**.  
   > We'll use that provider's built-in web search (no separate search API key).

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

3. **Do not use Tavily** (or `@langchain/tavily`). Replace the quickstart's search tool with the chosen provider's built-in web search. Look up the current export/tool shape on that provider's LangChain docs (examples as of writing — re-check if needed):

   | Provider | Built-in search tool |
   |----------|----------------------|
   | Anthropic | `@langchain/anthropic` `tools.webSearch_*()` (or equivalent dict) |
   | OpenAI | `{ type: "web_search" }` |
   | Google | `{ google_search: {} }` |

   Prefer Anthropic / OpenAI / Google so provider search is available. Only secret: that provider's API key in `.env` (gitignored). Skip LangSmith tracing unless they ask.

4. Install packages from the quickstart **minus** Tavily; add the provider package for their model.

5. Run the research example, show output, then stop. Point to `deep-agents-core` / customization / Managed Deep Agents for next steps.

More from langchain-ai/langchain-skills

SkillDescription
deep-agents-coreINVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
deep-agents-memoryINVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
deep-agents-orchestrationINVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
deepagents-python-quickstartScaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.
ecosystem-primerINVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and which skill to load next.
eval-engineeringInspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals, benchmark design, Task generation, controlled Environments, synthetic data, Verifiers, Harbor runs, calibration, or continuous benchmark maintenance.
langchain-dependenciesINVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.
langchain-fundamentalsCreate LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
langchain-middlewareINVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
langchain-python-quickstartScaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally.