Evaluate your AI agents

KATE is an open-source platform for tracing, evaluating, and improving AI agents. Auto-instrument your code, run quality evals, and visualize every decision your agent makes.

Everything you need to ship reliable agents

Auto-Instrumentation

Drop-in SDK captures every LLM call, tool use, and chain step automatically. Zero config tracing.

Eval Metrics

Run faithfulness, relevance, and hallucination checks on every agent response. Powered by DeepEval.

Trace Visualization

Waterfall timelines show exactly how your agent thinks. Drill into any span to see inputs, outputs, and latency.

Get started in minutes

1

Install the SDK

pip install kate-sdk

2

Instrument your agent

One-line init wraps your LLM calls automatically

3

View results

Traces and eval scores appear in your dashboard instantly

Ready to improve your agents?

Sign in with Google to get your API key and start sending traces in under 5 minutes.

Get Started Free