peargent 0.1.2

A modern Python framework for building intelligent AI agents with advanced tracing, history management, and seamless LLM integration

Peargent

A modern Python framework for building intelligent AI agents with advanced tracing, history management, and seamless LLM integration.

Features

• Advanced Tracing - Track every action, decision, and API call with detailed telemetry and database persistence
• Smart History Management - Built-in conversation history with intelligent context windowing and buffer management
• Multi-LLM Support - Seamlessly switch between OpenAI, Anthropic, Groq, Gemini, and more
• Type-Safe Tools - Pydantic-powered tool system with automatic validation
• Agent Pools - Run multiple agents concurrently with shared context
• Streaming Support - Real-time streaming responses with event handling
• Cost Tracking - Monitor token usage and costs across all LLM providers

Installation

pip install peargent

Quick Start

from peargent import create_agent
from peargent.models import groq, anthropic, openai

# Use any model provider
agent = create_agent(
    name="assistant",
    persona="You are a helpful AI assistant.",
    model=anthropic("claude-3-5-sonnet-20241022")  # or groq("llama-3.3-70b-versatile"), openai("gpt-4o")
)

result = agent.run("What is the capital of France?")
print(result)

For more examples and detailed documentation, visit the Documentation.

License

MIT License - see LICENSE file for details

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Author

Created by Quanta-Naut