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: May 26, 2026

Quick Start

Templates