Features

Detailed explanation of each feature you can include when scaffolding a new agent. Learn the setup patterns, APIs, and practical examples needed to build...

Detailed explanation of each feature you can include when scaffolding a new agent.

Memory

Enable persistent memory for your agent. The agent remembers conversations across sessions using vector search for efficient retrieval.

const agent = await Agent.create({
  name: 'my-agent',
  model: 'gpt-4o',
  memory: true,
});

await agent.ask("My name is John");
// Later, even in a new session:
await agent.ask("What's my name?"); // "Your name is John"

Use cases:

Personal assistants that remember user preferences
Customer support bots with conversation history
Long-running agents that need context persistence

Knowledge (RAG)

Add document retrieval capabilities. Ingest PDFs, text files, and other documents into a searchable knowledge base.

const agent = await Agent.create({
  name: 'my-agent',
  model: 'gpt-4o',
  knowledge: true,
});

// Add documents to knowledge base
await agent.addKnowledgeFromFile('./docs/guide.pdf', { category: 'docs' });
await agent.addKnowledgeFromFile('./docs/api.md', { category: 'api' });

// Agent answers from documents
await agent.ask("What does the guide say about authentication?");

Use cases:

Documentation Q&A bots
Research assistants
Knowledge management systems

Requirements: PostgreSQL with pgvector extension

Graph Workflows

Create complex multi-step workflows with DAG-based task orchestration. Define dependencies between tasks and run them in parallel where possible.

import { Agent, Graph } from '@astreus-ai/astreus';

const agent = await Agent.create({ name: 'my-agent', model: 'gpt-4o' });
const graph = new Graph({ name: 'research-workflow' }, agent);

// Define workflow nodes
const researchNode = graph.addTaskNode({
  prompt: 'Research the topic thoroughly'
});

const analyzeNode = graph.addTaskNode({
  prompt: 'Analyze the research findings',
  dependsOn: [researchNode]
});

const writeNode = graph.addTaskNode({
  prompt: 'Write a comprehensive report',
  dependsOn: [analyzeNode]
});

// Execute the workflow
const result = await graph.run();
console.log(result.results);

Use cases:

Multi-step content generation
Data processing pipelines
Complex decision workflows

Sub-Agents

Coordinate multiple specialized agents for complex tasks. Each sub-agent can have its own configuration and expertise.

// Create specialized agents
const researcher = await Agent.create({
  name: 'researcher',
  model: 'gpt-4o',
  systemPrompt: 'You are a research specialist.'
});

const writer = await Agent.create({
  name: 'writer',
  model: 'gpt-4o',
  systemPrompt: 'You are a professional writer.'
});

// Main agent coordinates sub-agents
const agent = await Agent.create({ name: 'coordinator', model: 'gpt-4o' });

const result = await agent.executeWithSubAgents(
  'Research and write an article about quantum computing',
  [researcher, writer]
);

Use cases:

Content creation pipelines
Expert systems with multiple domains
Parallel task execution

Custom Plugins

Extend your agent with custom tools. Define parameters, descriptions, and handlers for each tool.

const weatherPlugin = {
  name: 'weather-plugin',
  version: '1.0.0',
  description: 'Get weather information',
  tools: [{
    name: 'get_weather',
    description: 'Get current weather for a location',
    parameters: {
      location: {
        type: 'string',
        description: 'City name',
        required: true
      }
    },
    handler: async ({ location }) => {
      const response = await fetch(`https://api.weather.com/${location}`);
      const data = await response.json();
      return { success: true, data };
    }
  }]
};

const agent = await Agent.create({ name: 'my-agent', model: 'gpt-4o' });
await agent.registerPlugin(weatherPlugin);

// Agent can now use the weather tool
await agent.ask("What's the weather in Tokyo?");

Use cases:

API integrations
Database operations
Custom business logic

MCP Integration

Model Context Protocol support for standardized tool integration. Connect to MCP-compatible services and tools.

const agent = await Agent.create({
  name: 'my-agent',
  model: 'gpt-4o',
  mcp: {
    servers: [
      { name: 'filesystem', command: 'mcp-server-filesystem' },
      { name: 'github', command: 'mcp-server-github' }
    ]
  }
});

Use cases:

File system operations
GitHub integration
Standardized tool ecosystem

Feature Combinations

Features work together seamlessly:

const agent = await Agent.create({
  name: 'advanced-agent',
  model: 'gpt-4o',
  memory: true,           // Remember conversations
  knowledge: true,        // Access documents
  mcp: {                  // Use MCP tools
    servers: [
      { name: 'filesystem', command: 'mcp-server-filesystem' }
    ]
  }
});

// Register custom plugins
await agent.registerPlugin(myCustomPlugin);

// Use with graph workflows
const graph = new Graph({ name: 'workflow' }, agent);

Last updated: July 6, 2026

In this section

Introduction

Scaffold new Astreus AI agent projects with best practices and sensible defaults. Interactively configure your agent with the features you need.

Configuration

Environment variables and configuration options for your Astreus agent project. Learn the setup patterns, APIs, and practical examples needed to build...

Quick Start

Templates