Super Agent Stack
DocsHome

Examples

Ready-to-use code examples for common use cases with Super Agent Stack.

Getting Started

Basic Chat

Simple chat application with conversation history. Perfect starting point.

Streaming Responses

Real-time streaming for better UX. See responses as they're generated.

RAG Enhanced

Chat with your documents using RAG. Upload files and get grounded answers.

Memory Examples

Examples showcasing the memory system features for building AI applications with context.

Chatbot with MemoryNew

Build a chatbot that remembers conversation context across messages.

User PreferencesNew

Store and retrieve user preferences using the Memory Facts API.

Knowledge Q&ANew

Build a Q&A system combining RAG with memory for document querying.

Advanced Features

Examples showcasing the new OpenRouter features available through Super Agent Stack.

Structured OutputsNew

Get type-safe JSON responses with schema validation. Perfect for data extraction.

Web SearchNew

Real-time web search with citations. Get current information with sources.

Model RoutingNew

Fallback models for high availability. Never miss a request.

Tool Calling

Enable AI to call functions and interact with external systems.

Quick Code Snippets

Basic Request

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }]
});

With Session Memory

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Remember my name is John' }],
  sessionId: crypto.randomUUID(),  // UUID for session tracking
  saveToMemory: true,              // Save to memory
  autoMemory: true                 // Enable "remember" commands
});

With User Memory

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'What do you know about me?' }],
  sessionId: crypto.randomUUID(),
  useUserMemory: true,      // Include cross-session memory
  userMemoryTokens: 500     // Max tokens for user memory
});

With Hybrid Search

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Find docs about authentication' }],
  useRAG: true,
  searchMode: 'hybrid',     // 'vector' | 'keyword' | 'hybrid'
  keywordWeight: 0.3        // 30% keyword, 70% semantic
});

With Web Search

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o:online',  // Add :online suffix
  messages: [{ role: 'user', content: 'Latest AI news' }]
});

With Structured Output

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Extract: John, 25, NYC' }],
  response_format: {
    type: 'json_schema',
    json_schema: {
      name: 'person',
      schema: {
        type: 'object',
        properties: {
          name: { type: 'string' },
          age: { type: 'number' },
          city: { type: 'string' }
        }
      }
    }
  }
});

With Model Fallbacks

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
  models: ['anthropic/claude-3.5-sonnet', 'google/gemini-2.0-flash']
});

Need More Help?