Laminar

Open-source observability for long-running AI agents that captures LLM calls, tool use and browser actions for step-level debugging and replay.

Category	Agent Debugging & Replay
OpenTelemetry-native	Yes — no proprietary-SDK lock-in
Open source	Yes
Self-hostable	Yes
Pricing model	freemium
Pricing notes	OSS self-host (Docker) free; cloud free tier + paid plans
Framework integrations	openai-sdk, anthropic, langchain, browser-use, playwright
Funding / ownership	YC S24; $3M seed (Mar 2026)
GitHub stars	3,001
Maintenance	active (commit 2026-06-13)
License (GitHub)	Apache-2.0
Open issues	108
Maturity signal	93/100 (Mature) — computed from public GitHub signals, see methodology

Pricing/feature source: https://laminar.sh

Maturity signal is computed from public GitHub data only. How it is calculated.

Frequently asked questions

Is Laminar open source?

Yes. Licensed under Apache-2.0.

Can I self-host Laminar?

Yes — Laminar can run in your own infrastructure.

Is Laminar OpenTelemetry-native?

Yes — Laminar speaks OpenTelemetry (OTLP) natively, so there is no proprietary-SDK lock-in.

How much does Laminar cost?

Freemium. OSS self-host (Docker) free; cloud free tier + paid plans