For detailed visual representations of the system architecture, see System Architecture Diagrams.

Express-Inspired Flow

Liz uses an Express-style middleware architecture where each request flows through a series of middleware functions. This approach provides a clear, predictable processing pipeline that's easy to understand and extend.

Standard Middleware Pipeline

1. validateInput: Ensures required fields are present

2. loadMemories: Retrieves relevant conversation history

3. wrapContext: Builds the context for LLM interactions

4. createMemoryFromInput: Stores the user's input

5. router: Determines and executes the appropriate route handler

Agent Framework

The AgentFramework class in src/framework orchestrates the middleware pipeline and handles request processing:

import { AgentFramework } from "./framework";
import { standardMiddleware } from "./middleware";

const framework = new AgentFramework();

// Add middleware
standardMiddleware.forEach((middleware) => framework.use(middleware));

// Process requests
framework.process(input, agent, res);

Agents vs. Middleware

Agent

• Defines personality and capabilities

• Holds system prompt and style context

• Manages route definitions

• Provides agent-specific context

Middleware

• Handles request processing

• Manages memory operations

• Builds context for LLM

• Routes requests to handlers

Route Handling

Routes define how an agent handles different types of interactions. The router middleware uses LLM to select the most appropriate handler:

// Adding a route to an agent
agent.addRoute({
	name: "conversation",
	description: "Handle natural conversation",
	handler: async (context, req, res) => {
		const response = await llmUtils.getTextFromLLM(
			context,
			"anthropic/claude-3-sonnet"
		);
		await res.send(response);
	},
});

Request Flow Example

1. Client sends request to /agent/input
   ↓
2. validateInput checks required fields
   ↓
3. loadMemories fetches conversation history
   ↓
4. wrapContext builds prompt with memories
   ↓
5. createMemoryFromInput stores request
   ↓
6. router selects appropriate handler
   ↓
7. handler processes request with LLM
   ↓
8. Response sent back to client

Next: Agents →

Overall System Architecture

Middleware Flow

Memory System

Agent Interaction Flow