AgentOps

Active

GitHub Python MIT

Description

Observability platform for AI agents, auto-traces tool calls.

💡 Trace dashboards for multi-agent systems.

💡 Monitor LLM cost in production.

💡 Replay problematic sessions in customer support.

# Install
pip install agentops
# One-line init
import agentops
agentops.init(api_key='sk-...')
# All LLM calls are automatically recorded

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

AdalFlow: The library to build & auto-optimize LLM applications.

A CNCF Sandbox SRE Agent that automatically analyzes infrastructure logs and metrics to assist with incident diagnosis and system operations.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?