OpenLIT

OpenTelemetry-native observability for LLM apps and agents: one-line instrumentation for traces, metrics, cost tracking, plus prompt management and a playground - GenAI observability on open standards.

View source on GitHub

Key takeaways

• 01

  OpenTelemetry-native means agent traces join your existing stack

• 02

  Token/cost metrics belong in the same traces as latency

Flows built on this research

Harness Engineering

Observability for Agent Runs

Instrument your agent like production software: traces, session replay, cost tracking, and failure analysis on open standards.

4 steps · 90-120 minutes

Agent QA & Security

Secrets Hygiene in Agent Logs

Keep credentials out of prompts, tool outputs, logs, and traces: detection, redaction, and safe handling across the whole agent pipeline.

4 steps · 60-90 minutes