### CLI Commands for LangChain Build System

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/internal/build/README.md

Provides examples of common CLI commands for the LangChain build system, including getting help, building all packages, using watch mode, building specific packages, and excluding packages.

```bash
# Get help
pnpm build:new --help
```

```bash
# Build all packages in the workspace
pnpm build:new
```

```bash
# Build with watch mode for development
pnpm build:new --watch
```

```bash
# Build specific packages
pnpm build:new @langchain/core
pnpm build:new @langchain/core langchain @langchain/openai
```

```bash
# Exclude packages from build
pnpm build:new --exclude @langchain/community
pnpm build:new -e @langchain/aws -e @langchain/openai
```

```bash
# Skip various build steps
pnpm build:new --no-emit          # Skip type declarations
pnpm build:new --skip-unused      # Skip unused dependency check
pnpm build:new --skip-clean       # Skip cleaning build directory
pnpm build:new --skip-sourcemap   # Skip sourcemap generation
```

--------------------------------

### Install LangGraph Swarm

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/multi-agent.md

Install the `langgraph-swarm` library using npm.

```bash
npm install @langchain/langgraph-swarm
```

--------------------------------

### Install dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/CONTRIBUTING.md

Install project dependencies using pnpm.

```bash
pnpm install
```

--------------------------------

### Install PDE package

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/libs/prompt-decomposition-engine/README.md

Install the core package using npm or yarn.

```bash
npm install ava-langgraph-prompt-decomposition-engine
# or
yarn add ava-langgraph-prompt-decomposition-engine
```

--------------------------------

### Install LangGraph Supervisor

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/multi-agent.md

Install the `langgraph-supervisor` library using npm.

```bash
npm install @langchain/langgraph-supervisor
```

--------------------------------

### Install optional dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/libs/narrative-intelligence/README.md

Install additional packages for LangGraph integration or Redis persistence.

```bash
# For LangGraph integration
npm install @langchain/langgraph

# For Redis persistence
npm install ioredis
```

--------------------------------

### Install MCP Adapters

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/mcp.md

Install the required library to enable MCP tool support in LangGraph.

```bash
npm install @langchain/mcp-adapters
```

--------------------------------

### Install LangGraph.js CLI with npx

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/langgraph_cli.md

Install the LangGraph.js CLI using npx. This is a quick way to run the CLI without a global installation.

```bash
npx @langchain/langgraph-cli
```

--------------------------------

### Install AvaLangGraph Libraries

Source: https://context7.com/avadisabelle/ava-langgraphjs/llms.txt

Install the core AvaLangGraph libraries using npm or pnpm.

```bash
# Using npm
npm install ava-langgraph-prompt-decomposition-engine
npm install ava-langgraph-inquiry-routing-engine
npm install ava-langgraph-narrative-intelligence

# Using pnpm
pnpm add ava-langgraph-prompt-decomposition-engine
pnpm add ava-langgraph-inquiry-routing-engine
pnpm add ava-langgraph-narrative-intelligence
```

--------------------------------

### Install Dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/langgraph-platform/local-server.md

Install project dependencies using yarn.

```bash
$ yarn
```

--------------------------------

### Install LangGraph SDKs

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/langgraph-platform/local-server.md

Commands to install the necessary SDKs for Python and JavaScript environments.

```shell
$ pip install langgraph-sdk
```

```shell
$ yarn add @langchain/langgraph-sdk
```

--------------------------------

### Launch LangGraph Server

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/langgraph-platform/local-server.md

Start the LangGraph API server in development mode.

```bash
$ npx @langchain/langgraph-cli@latest dev
```

--------------------------------

### Install Python MCP Library

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/mcp.md

Install the Python MCP SDK to build custom tool servers.

```bash
pip install mcp
```

--------------------------------

### Install package dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/libs/narrative-intelligence/README.md

Install the core package using npm or yarn.

```bash
npm install ava-langgraph-narrative-intelligence
# or
yarn add ava-langgraph-narrative-intelligence
```

--------------------------------

### Install package dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/libs/inquiry-routing-engine/README.md

Install the core engine and its required peer dependencies.

```bash
npm install ava-langgraph-inquiry-routing-engine
```

```bash
npm install ava-langchain-prompt-decomposition ava-langchain-inquiry-routing
```

--------------------------------

### Run Next.js Development Server

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/internal/environment_tests/test-exports-vercel/README.md

Commands to start the local development server using different package managers.

```bash
npm run dev
# or
yarn dev
# or
pnpm dev
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/langgraph-platform/local-server.md

Example content for the .env file required for API authentication.

```bash
LANGSMITH_API_KEY=lsv2...
TAVILY_API_KEY=tvly-...
ANTHROPIC_API_KEY=sk-
OPENAI_API_KEY=sk-...
```

--------------------------------

### Connect to Authenticated Deployments

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/how-tos/auth/custom_auth.md

Examples of how to include authorization headers when connecting to the platform from various clients.

```python
from langgraph_sdk import get_client

my_token = "your-token" # In practice, you would generate a signed token with your auth provider
client = get_client(
    url="http://localhost:2024",
    headers={"Authorization": f"Bearer {my_token}"}
)
threads = await client.threads.search()
```

```python
from langgraph.pregel.remote import RemoteGraph

my_token = "your-token" # In practice, you would generate a signed token with your auth provider
remote_graph = RemoteGraph(
    "agent",
    url="http://localhost:2024",
    headers={"Authorization": f"Bearer {my_token}"}
)
threads = await remote_graph.ainvoke(...)
```

```javascript
import { Client } from "@langchain/langgraph-sdk";

const my_token = "your-token"; // In practice, you would generate a signed token with your auth provider
const client = new Client({
  apiUrl: "http://localhost:2024",
  headers: { Authorization: `Bearer ${my_token}` },
});
const threads = await client.threads.search();
```

```javascript
import { RemoteGraph } from "@langchain/langgraph/remote";

const my_token = "your-token"; // In practice, you would generate a signed token with your auth provider
const remoteGraph = new RemoteGraph({
  graphId: "agent",
  url: "http://localhost:2024",
  headers: { Authorization: `Bearer ${my_token}` },
});
const threads = await remoteGraph.invoke(...);
```

```bash
curl -H "Authorization: Bearer ${your-token}" http://localhost:2024/threads
```

--------------------------------

### Launch local development server

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/deployment.md

Start the LangGraph API server for local development and debugging.

```bash
npx @langchain/langgraph-cli dev
```

--------------------------------

### Install LangGraph.js CLI with bun

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/langgraph_cli.md

Install the LangGraph.js CLI as a project dependency using bun.

```bash
bun add @langchain/langgraph-cli
```

--------------------------------

### Install LangGraph CLI

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/langgraph-platform/local-server.md

Install the LangGraph CLI tool via npx or globally via npm.

```bash
$ npx @langchain/langgraph-cli@latest

# Or install globally, will be available as `langgraphjs`
$ npm install -g @langchain/langgraph-cli
```

--------------------------------

### Install AgentEvals and LangChain Core

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/evals.md

Install the necessary packages for using prebuilt evaluators. This includes agentevals and @langchain/core.

```bash
npm install agentevals @langchain/core
```

--------------------------------

### Install LangGraph.js CLI with pnpm

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/langgraph_cli.md

Install the LangGraph.js CLI as a project dependency using pnpm.

```bash
pnpm add @langchain/langgraph-cli
```

--------------------------------

### Install LangGraph.js CLI with npm

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/langgraph_cli.md

Install the LangGraph.js CLI as a project dependency using npm.

```bash
npm install @langchain/langgraph-cli
```

--------------------------------

### Run AvaLangGraph Example

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/README.md

Conceptual example demonstrating how an AvaLangGraph component, specifically the InquiryRoutingGraph, might be invoked with a sample decomposition result. Full LangGraph integration requires defining StateGraph nodes and edges.

```typescript
import { InquiryRoutingGraph } from "inquiry-routing-engine";
import { DecompositionResult } from "ava-langchain-prompt-decomposition"; // Assuming this comes from ChainStack

async function runAvaLangGraphExample() {
  const sampleDecomposition: DecompositionResult = {
    primary: { action: "build", target: "knowledge graph", urgency: "high", confidence: 0.9 },
    secondary: [],
    directions: { east: [], south: [], west: [], north: [] }, // Simplified for example
    actionStack: [],
    balance: 0.8,
    leadDirection: "north",
    neglectedDirections: [],
    ambiguities: []
  };

  const inquiryGraph = new InquiryRoutingGraph({ enforceCeremony: true });
  const finalState = await inquiryGraph.invoke(sampleDecomposition);

  console.log("Inquiry Routing Final State:", finalState.status);
  if (finalState.ceremonyRequired) {
    console.log("Ceremony required. Human review initiated.");
  } else {
    console.log("Dispatched inquiries:", finalState.dispatchedInquiries);
  }
}

runAvaLangGraphExample();
```

--------------------------------

### Run AvaLangGraph Conceptual Example

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/getting-started.md

Demonstrates initializing the InquiryRoutingGraph and invoking it with a decomposition result.

```typescript
// This is a conceptual example for AvaLangGraph, showing how its engines work.
// Full LangGraph integration would involve defining StateGraph nodes and edges.

import { InquiryRoutingGraph } from "inquiry-routing-engine";
import { DecompositionResult } from "ava-langchain-prompt-decomposition"; // Assuming this comes from ChainStack

async function runAvaLangGraphExample() {
  const sampleDecomposition: DecompositionResult = {
    primary: { action: "build", target: "knowledge graph", urgency: "high", confidence: 0.9 },
    secondary: [],
    directions: { east: [], south: [], west: [], north: [] }, // Simplified for example
    actionStack: [],
    balance: 0.8,
    leadDirection: "north",
    neglectedDirections: [],
    ambiguities: []
  };

  const inquiryGraph = new InquiryRoutingGraph({ enforceCeremony: true });
  const finalState = await inquiryGraph.invoke(sampleDecomposition);

  console.log("Inquiry Routing Final State:", finalState.status);
  if (finalState.ceremonyRequired) {
    console.log("Ceremony required. Human review initiated.");
  } else {
    console.log("Dispatched inquiries:", finalState.dispatchedInquiries);
  }
}

runAvaLangGraphExample();
```

--------------------------------

### Import entrypoint

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/CONTRIBUTING.md

Example of importing a module from a LangGraph subpath.

```typescript
import { Pregel } from "@langchain/langgraph/pregel";
```

--------------------------------

### Install LangGraph.js CLI with yarn

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/langgraph_cli.md

Install the LangGraph.js CLI as a project dependency using yarn.

```bash
yarn add @langchain/langgraph-cli
```

--------------------------------

### Install AvaLangGraph Packages

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/README.md

Commands for installing AvaLangGraph packages using npm, pnpm, or yarn.

```bash
# Using npm
npm install inquiry-routing-engine
npm install prompt-decomposition-engine
npm install narrative-intelligence

# Using pnpm
pnpm add inquiry-routing-engine
pnpm add prompt-decomposition-engine
pnpm add narrative-intelligence

# Using yarn
yarn add inquiry-routing-engine
yarn add prompt-decomposition-engine
yarn add narrative-intelligence
```

--------------------------------

### Install project dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/deployment.md

Install required packages for the LangGraph application and chat model support.

```shell
yarn
# install these to use initChatModel with Anthropic
yarn add langchain
yarn add @langchain/anthropic
```

--------------------------------

### Full interrupt workflow example

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/human_in_the_loop.md

A complete example showing graph construction, interrupt usage, and resuming with Command.

```typescript
import { MemorySaver, Annotation, interrupt, Command, StateGraph } from "@langchain/langgraph";

// Define the graph state
const StateAnnotation = Annotation.Root({
  some_text: Annotation<string>()
});

function humanNode(state: typeof StateAnnotation.State) {
   const value = interrupt(
      // Any JSON serializable value to surface to the human.
      // For example, a question or a piece of text or a set of keys in the state
      {
         text_to_revise: state.some_text
      }
   );
   return {
      // Update the state with the human's input
      some_text: value
   };
}

// Build the graph
const workflow = new StateGraph(StateAnnotation)
// Add the human-node to the graph
  .addNode("human_node", humanNode)
  .addEdge("__start__", "human_node")

// A checkpointer is required for `interrupt` to work.
const checkpointer = new MemorySaver();
const graph = workflow.compile({
   checkpointer
});

// Using stream() to directly surface the `__interrupt__` information.
for await (const chunk of await graph.stream(
   { some_text: "Original text" },
   threadConfig
)) {
   console.log(chunk);
}

// Resume using Command
for await (const chunk of await graph.stream(
   new Command({ resume: "Edited text" }),
   threadConfig
)) {
   console.log(chunk);
}
```

```typescript
{
   __interrupt__: [
      {
         value: { question: 'Please revise the text', some_text: 'Original text' },
         resumable: true,
         ns: ['human_node:10fe492f-3688-c8c6-0d0a-ec61a43fecd6'],
         when: 'during'
      }
   ]
}
{ human_node: { some_text: 'Edited text' } }
```

--------------------------------

### Start LangGraph Development Server

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/langgraph_cli.md

The `langgraph dev` command starts a lightweight development server without Docker. It supports hot reloading and in-memory state with local persistence, ideal for rapid local development and testing.

```bash
langgraph dev
```

--------------------------------

### Install LangGraph and LangChain Dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/agents.md

Install the necessary LangGraph and LangChain packages using npm.

```bash
npm install langchain @langchain/langgraph @langchain/anthropic
```

--------------------------------

### Start LangGraph API Server with Docker

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/langgraph_cli.md

Run the `langgraph up` command to start a local instance of the LangGraph API server in a Docker container. This requires Docker to be running and a LangSmith or license key.

```bash
langgraph up
```

--------------------------------

### Run documentation locally

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/CONTRIBUTING.md

Commands to set up and serve the documentation site.

```bash
cd docs
```

```bash
pip install -r docs-requirements.txt
```

```bash
make serve-docs
```

--------------------------------

### Initialize LangGraph Project

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/how-tos/http/custom_middleware.md

Command to scaffold a new LangGraph project using the CLI.

```bash
npm create langgraph
```

--------------------------------

### Build project

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/CONTRIBUTING.md

Compile the project source code.

```bash
pnpm build
```

--------------------------------

### Install peer dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/libs/prompt-decomposition-engine/README.md

Install required peer dependencies for full functionality.

```bash
npm install ava-langchain-relational-intelligence ava-langgraph-narrative-intelligence
# or
yarn add ava-langchain-relational-intelligence ava-langgraph-narrative-intelligence
```

--------------------------------

### Connect Studio Web UI to Custom Port

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/langgraph-platform/local-server.md

Example URL format for connecting the Studio Web UI to a server running on a non-default port.

```text
https://smith.langchain.com/studio/baseUrl=http://localhost:8000
```

--------------------------------

### Navigate to project directory

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/CONTRIBUTING.md

Change the current working directory to the project root.

```bash
cd langgraph
```

--------------------------------

### Install Hono Dependency

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/how-tos/http/custom_routes.md

Install the `hono` package as a project dependency using npm.

```bash
npm install hono
```

--------------------------------

### Initialize a React Agent with Web Search Tool

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/tools.md

Configures a LangGraph agent using the OpenAI GPT-4o-mini model and the web_search_preview prebuilt tool.

```ts
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { initChatModel } from "langchain/chat_models/universal";

const llm = await initChatModel("openai:gpt-4o-mini");

const agent = createReactAgent({
  llm,
  tools: [{ type: "web_search_preview" }],
});

const response = await agent.invoke({
  messages: ["What was a positive news story from today?"],
});
```

--------------------------------

### Workflow stream output examples

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/functional_api.md

Example outputs from the workflow stream during execution and interruption.

```typescript
{ write_essay: 'An essay about topic: cat' }
```

```typescript
{ __interrupt__: [{
  value: { essay: 'An essay about topic: cat', action: 'Please approve/reject the essay' },
  resumable: true,
  ns: ['workflow:f7b8508b-21c0-8b4c-5958-4e8de74d2684'],
  when: 'during'
}] }
```

--------------------------------

### Build System Directory Structure

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/internal/build/README.md

Illustrates the directory structure of the LangChain build system, showing the location of core files and plugins.

```tree
infra/build/
├── index.ts              # Main build orchestrator
├── cli.ts                # Command-line interface
├── types.ts              # TypeScript type definitions
├── utils.ts              # Utility functions
├── plugins/
│   ├── README.md         # Plugin documentation
│   ├── lc-secrets.ts     # LangChain secrets scanning plugin
│   ├── import-map.ts     # Import map generation plugin
│   └── import-constants.ts # Import constants generation plugin
├── package.json          # Build system dependencies
└── README.md             # This documentation
```

--------------------------------

### Scaffold a new LangGraph project

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/agents/deployment.md

Use the CLI tool to initialize a new project directory structure.

```bash
npm install -g create-langgraph
create-langgraph path/to/your/app
```

--------------------------------

### Install LangGraph CLI

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/how-tos/deploy-self-hosted.md

Install the CLI tool required to build the Docker image for your LangGraph application.

```shell
pip install -U langgraph-cli
```

--------------------------------

### Install LangGraphJS Dependencies

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/workflows/index.md

Install the necessary LangGraphJS packages using yarn. Ensure you are using a compatible version of @langchain/langgraph.

```bash
yarn add @langchain/langgraph @langchain/anthropic @langchain/core
```

--------------------------------

### Initialize and run the decomposition pipeline

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/libs/prompt-decomposition-engine/README.md

Demonstrates initializing the graph, analyzer, and gate, then executing the pipeline and evaluating the results.

```typescript
import {
  DecompositionGraph,
  PerspectiveAnalyzer,
  CeremonyGate,
} from "ava-langgraph-prompt-decomposition-engine";

const graph = new DecompositionGraph();
const analyzer = new PerspectiveAnalyzer();
const gate = new CeremonyGate();

// Run the full pipeline
const state = await graph.invoke("Build a relational intelligence system...");

console.log("Decomposition Status:", state.status);

// Analyze through three perspectives
if (state.decomposition) {
  const perspectives = analyzer.analyze(state.decomposition);
  console.log("Lead Universe:", perspectives.leadUniverse);

  // Evaluate if ceremony is needed
  const verdict = gate.evaluate(state.decomposition, perspectives);

  if (verdict.decision === "hold") {
    console.log("Ceremony needed:", verdict.reasons);
  } else {
    console.log("Can proceed:", verdict.decision);
  }
}
```

--------------------------------

### Create LangGraph App

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/tutorials/langgraph-platform/local-server.md

Initialize a new LangGraph project using the interactive CLI.

```shell
$ npm create langgraph
```

--------------------------------

### Install LangGraph SDK for Python

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/sdk.md

Install the Python SDK using pip. This package is required to interact with the LangGraph Platform.

```bash
pip install langgraph-sdk
```

--------------------------------

### Install LangGraph SDK for JavaScript

Source: https://github.com/avadisabelle/ava-langgraphjs/blob/main/docs/content/concepts/sdk.md

Install the JavaScript SDK using yarn. This package is required for Node.js environments to interact with the LangGraph Platform.

```bash
yarn add @langchain/langgraph-sdk
```