agensight 0.6.3

A Python SDK for logging and visualizing OpenAI agent interactions

Agensight SDK

A simple SDK for tracing and evaluating AI agent workflows.

Installation

pip install --upgrade agensight

Quick Start

from agensight import init, trace, span

# Initialize Agensight
init(name="my-agent")

# Add tracing to your functions
@trace("my_workflow")
def my_function():
    @span()
    def my_subtask():
        # Your code here
        pass
    return my_subtask()

Key Features

1. Tracing

• Auto-instrumented tracing of LLM calls
• Function execution tracking
• Agent interaction monitoring
• Performance metrics and token usage analytics

2. Evaluation

from agensight.eval.metrics import GEvalEvaluator

# Create custom evaluator
accuracy = GEvalEvaluator(
    name="Accuracy",
    criteria="Evaluate response accuracy",
    threshold=0.7
)

# Use in your code
@span(metrics=[accuracy])
def my_function():
    # Your code here
    pass

3. Local Storage

• All data stored locally in .agensight
• No external data uploads
• Complete privacy and control

Dashboard

Start the dashboard to view traces and metrics:

agensight view

Visit http://localhost:5001 in your browser

Documentation

For detailed documentation, visit our docs.

Support

Join our GitHub Discussions for support and feature requests.

License

MIT License • © 2025 agensight contributors