OpenLITTrace, evaluate, and monitor AI agents with OpenTelemetry.Apache-2.0
Trace, evaluate, and monitor AI agents with OpenTelemetry.
OpenLIT collects OpenTelemetry traces and metrics from AI applications and coding agents so teams can inspect model calls, tool activity, latency and costs. Its self-hosted dashboard works with Python and TypeScript instrumentation. Additional tools evaluate outputs, manage versioned prompts, compare model responses and monitor GPU utilization, giving developers several views of agent behavior during investigation and iteration.
OpenLIT README · Reviewed 2026-10-31
- 01 / Feature noteAgent tracing
Inspect model calls, tool calls, retrieval operations, errors and token usage through OpenTelemetry traces.
Feature source ↗ - 02 / Feature noteVersioned prompts
Create and version prompts centrally, compare versions and retrieve them from application code.
Feature source ↗
GitHub stars
2,902
Detected license
Apache-2.0
Repository created
2024-01-23
Repository push
2026-11-03
2024-01-23GitHub release
2026-10-26 · openlit-2.1.1Repository push
2026-11-03
GitHub stars
Unknown
i
Cached history uses a different month window; chart withheld until aligned.
Latest attempt: ok · Checked 2026-10-16T00:57:19.371756+00:00 · Last successful fetch 2026-10-16T00:57:19.371756+00:00 · Provider source
Hacker News stories
Unknown
i
OpenSSF Scorecard
Unknown
i
No result returned.
Checked 2026-10-27T00:21:53Z · Latest attempt: not found · Provider source
GitHub release
Published 2026-10-26
i
Checked 2026-11-04T04:04:05Z · Last successful fetch 2026-11-04T04:04:05Z · Value fetched 2026-11-04T04:04:05Z · Provider source
Unknown
