Home

Welcome to the Agent Framework Wiki

This wiki is your central resource for understanding, using, and extending the Agent Framework — a modular, Pythonic toolkit for building intelligent, task-oriented agents powered by LLMs like GPT or Ollama.

---

🚀 Overview

The Agent Framework enables you to compose LLM-based agents with:

• ✅ Composable agent pipelines
• 🧠 Built-in memory management
• 🌐 Web augmentation tools
• ✨ Prompt-driven summarization
• 🛠️ Tool/function calling via LLMs

Whether you're building a simple chatbot or a multi-agent orchestration pipeline, this framework gives you the flexibility to do it cleanly and efficiently.

---

🧩 Core Concepts

Component	Description
Agent	A single callable unit that communicates with an LLM (OpenAI, Ollama, etc.), handles prompts, memory, and optional tools.
BaseMemory	A lightweight memory store for chat history and message objects. Useful for maintaining conversation context.
SmartMemory	An enhanced memory that summarizes long histories automatically using a dedicated summarizer agent.
AgentFactory	A factory for quickly instantiating pre-configured agents with consistent settings.
AgentManager	A router or controller that orchestrates multiple agents (e.g., AutoAgentManager, SequentialAgent).
InternetAgent	An agent that can search the web and summarize live data using LLMs.

---

📦 Features at a Glance

• 🔁 Composable and chainable agents
• 🧠 Context-preserving memory (with summarization)
• 🔌 Tool/function calling using LLM function schemas
• 🌍 Web-augmented agents
• ⚡ Parallel document summarization
• 🧼 Clean and simple Python interface (no magic, no metaclasses)

See the full Feature Table in the README.

---

🧪 Getting Started

# Clone the repository
git clone https://github.com/your-username/agent-framework.git
cd agent-framework

# Install dependencies
pip install -r requirements.txt

Basic example

from agent import AgentFactory, SmartMemory

# Setup factory
factory = AgentFactory(
    base_url="http://localhost:8000/v1",
    api_key="your-key",
    model="gpt-4",
    provider="openai"
)

# Setup memory with summarization
memory = SmartMemory(agent_factory=factory)

# Create agent with memory
agent = factory.create_agent(
    name="assistant",
    system_prompt="You're a helpful assistant.",
    memory=lambda: memory
)

🛠️ This wiki is a work in progress. We will continue to expand and improve it with detailed documentation, examples, and advanced usage guides as the project evolves.