Overview - Inworld AI Documentation

Inworld’s Node.js Runtime SDK is a comprehensive toolkit for building AI-powered applications.

Graphs

At the core of the SDK is the Graph system, an interface to construct complete AI pipelines, from input to final output.

Core Classes

Import core graph classes from @inworld/runtime/graph:

import { 
  Graph, 
  GraphBuilder, 
  SubgraphBuilder, 
  SequentialGraphBuilder, 
  GraphOutputStream, 
  GraphExecutionManager 
} from '@inworld/runtime/graph';

Graph - Main graph execution engine
GraphBuilder - Builder for creating graph configurations
SubgraphBuilder - Builder for creating reusable subgraphs
SequentialGraphBuilder - Builder for creating sequential graphs
GraphOutputStream - Handler for graph execution output
GraphExecutionManager - Registry for managing graph executions

Nodes

Import nodes from @inworld/runtime/graph or @inworld/runtime/graph/nodes:

import { 
  RemoteLLMChatNode,
  RemoteTTSNode,
  RemoteSTTNode,
  SubgraphNode
  // ... and other nodes ...
} from '@inworld/runtime/graph';

Built-in Nodes

Nodes with an asterisk (*) are experimental and subject to change.

Node	Description	Input Type(s)	Output Type(s)
KeywordMatcherNode	Matches keywords in text input	String	GraphTypes.MatchedKeywords
KnowledgeNode*	Retrieves relevant knowledge based on input text	String	GraphTypes.KnowledgeRecords
LLMChatRequestBuilderNode	Generates formatted chat requests using prompt templates populated with JSON input	Object	GraphTypes.LLMChatRequest
LLMPromptBuilderNode	Generates formatted prompts using prompt templates populated with JSON input	Object	String
MCPCallToolNode	Calls multiple tools on an MCP server in parallel	GraphTypes.ToolCallRequest	GraphTypes.ToolCallResponse
MCPListToolsNode	Lists available tools from an MCP server	any	GraphTypes.ListToolsResponse
ProxyNode	Simple data passing node for forwarding input to output	any	any
RandomCannedTextNode	Selects a random text from a list of predefined phrases	any	String
RemoteLLMChatNode	Generates a response using a large language model	GraphTypes.LLMChatRequest	GraphTypes.LLMChatResponse
RemoteLLMCompletionNode	Generates text completion using a large language model	String	String
RemoteSTTNode	Converts speech audio to text using a speech-to-text (STT) model	GraphTypes.Audio	String
RemoteTTSNode	Converts text-to-speech audio using a text-to-speech (TTS) model	String GraphTypes.TextStream GraphTypes.TTSRequest	GraphTypes.TTSOutputStream
SafetyCheckerNode	Analyzes text for potentially harmful content and returns safety assessment results	String	GraphTypes.SafetyResult
SubgraphNode	Executes a compiled subgraph as a node	any	any
TextAggregatorNode	Combines text streams (chunks) into a single string	String GraphTypes.TextStream GraphTypes.LLMChatResponse	String
TextChunkingNode	Splits text into smaller chunks	GraphTypes.TextStream GraphTypes.ContentStream	GraphTypes.TextStream
TextClassifierNode	Analyzes text and classifies it into predefined categories using ML models	String	GraphTypes.ClassificationResult

Built-in Subgraphs

Subgraphs with an asterisk (*) are experimental and subject to change.

Subgraph	Description	Input Type(s)	Output Type(s)
Intent Subgraph*	Detects the intent of the text input using a built-in subgraph	String	GraphTypes.MatchedIntents

Custom Nodes

You can create your own nodes by extending the CustomNode base class.

Graph Types

Import graph data types from @inworld/runtime/graph:

import { GraphTypes } from '@inworld/runtime/graph';

GraphTypes are graph data types used for input and output between nodes in the graph:

Components

Import components from @inworld/runtime/graph or @inworld/runtime/graph/components:

import { 
  RemoteLLMComponent,
  RemoteKnowledgeComponent,
  RemoteEmbedderComponent,
  RemoteSTTComponent,
  RemoteTTSComponent,
  MCPClientComponent
} from '@inworld/runtime/graph';

Components are reusable configurations that can be shared across multiple nodes:

RemoteLLMComponent - LLM provider configuration
RemoteKnowledgeComponent - Knowledge base configuration
RemoteEmbedderComponent - Text embedding configuration
RemoteSTTComponent - Speech-to-text configuration
RemoteTTSComponent - Text-to-speech configuration
MCPClientComponent - MCP server configuration

Telemetry

Import telemetry functionality from @inworld/runtime:

import { telemetry } from '@inworld/runtime';

Capture metrics, trace, and logs to help with understanding and optimizing your AI pipeline:

Telemetry

​Graphs

​Core Classes

​Nodes

​Built-in Nodes

​Built-in Subgraphs

​Custom Nodes

​Graph Types

​Components

​Telemetry

Graphs

Core Classes

Nodes

Built-in Nodes

Built-in Subgraphs

Custom Nodes

Graph Types

Components

Telemetry