npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@aerostack/sdk-langchain

v0.11.27

Published

Use Aerostack workspace tools as LangChain.js tools

Readme

@aerostack/sdk-langchain

Use Aerostack workspace tools as LangChain.js tools.

Aerostack is the full-stack platform for AI agents — compose MCP servers, skills, and functions into a single workspace URL that any AI agent can call. This SDK lets you drop 250+ pre-built tools into your LangChain agent in 3 lines of code.

npm version License: MIT

Why?

Building LangChain agents means writing custom tool wrappers for every external service. With Aerostack, you compose a workspace of tools (GitHub, Slack, Notion, Stripe, 250+ more) and this SDK converts them into DynamicStructuredTool instances that work with any LangChain agent or model.

Your Agent → LangChain → @aerostack/sdk-langchain → Aerostack Workspace → GitHub, Slack, Notion, ...

Install

npm install @aerostack/sdk-langchain @langchain/core

Quick Start — ReAct Agent

import { ChatOpenAI } from '@langchain/openai';
import { createReactAgent } from '@langchain/langgraph/prebuilt';
import { getTools } from '@aerostack/sdk-langchain';

const { tools } = await getTools({ workspace: 'my-workspace', token: 'mwt_...' });

const agent = createReactAgent({
    llm: new ChatOpenAI({ model: 'gpt-4o' }),
    tools,
});

const result = await agent.invoke({
    messages: [{ role: 'user', content: 'Create a GitHub issue for the login bug' }],
});

Direct Tool Binding

Bind tools directly to any LangChain chat model:

import { ChatAnthropic } from '@langchain/anthropic';
import { getTools } from '@aerostack/sdk-langchain';

const { tools } = await getTools({ workspace: 'my-workspace', token: 'mwt_...' });
const model = new ChatAnthropic({ model: 'claude-sonnet-4-20250514' }).bindTools(tools);

const response = await model.invoke('Check open PRs on GitHub');

Works With Any LLM

import { ChatGoogleGenerativeAI } from '@langchain/google-genai';
import { ChatGroq } from '@langchain/groq';

// Gemini
const agent = createReactAgent({
    llm: new ChatGoogleGenerativeAI({ model: 'gemini-2.0-flash' }),
    tools,
});

// Groq
const agent = createReactAgent({
    llm: new ChatGroq({ model: 'llama-3.3-70b-versatile' }),
    tools,
});

LangGraph Workflows

Use the tools inside LangGraph state machines for complex multi-step workflows:

import { StateGraph } from '@langchain/langgraph';
import { ToolNode } from '@langchain/langgraph/prebuilt';

const { tools } = await getTools({ workspace: 'my-workspace', token: 'mwt_...' });
const toolNode = new ToolNode(tools);

// Use toolNode in your LangGraph workflow

Factory Pattern

For reusable clients that share a single connection:

import { createAerostackLangChain } from '@aerostack/sdk-langchain';

const aero = createAerostackLangChain({ workspace: 'my-workspace', token: 'mwt_...' });
const { tools } = await aero.tools();

API Reference

getTools(config)Promise<ToolSetResult>

Fetches tools from the workspace and converts to LangChain DynamicStructuredTool[]. Each tool auto-executes via the workspace gateway. Returns { tools, raw }.

createAerostackLangChain(config)AerostackLangChainClient

Creates a reusable client that shares a single WorkspaceClient instance.

formatToolResult(result)

Lower-level utility to flatten MCP tool results into strings.

How It Works

  1. Tool DiscoverygetTools() calls your Aerostack workspace gateway to fetch all connected MCP server tools
  2. Format Conversion — MCP tool schemas (JSON Schema) are wrapped as DynamicStructuredTool instances with name, description, and schema
  3. Auto-Execution — Each tool's func proxies calls through the workspace gateway to actual MCP servers
  4. Error Handling — Errors are caught and returned as string results, keeping the agent conversation flow intact

Requirements

  • Node.js 18+
  • @langchain/core >= 0.2.0
  • An Aerostack workspace with a token (mwt_...)

Getting Your Workspace Token

  1. Sign up at app.aerostack.dev
  2. Create a workspace and add MCP servers (GitHub, Slack, Notion, etc.)
  3. Copy the workspace token (mwt_...) from the workspace settings

Related Packages

| Package | Framework | |---------|-----------| | @aerostack/sdk-openai | OpenAI SDK | | @aerostack/sdk-vercel-ai | Vercel AI SDK | | @aerostack/core | Core types + WorkspaceClient |

Links

License

MIT