Back to Tool
L

Laminar

Tool Oct 19, 2026

An open-source AI-agent observability platform with tracing, evaluations and Signals for investigating behavior across agent runs.

Visit primary link 2 sources attached
Laminar trace dashboard with a run timeline and a Signals failure-detector event linked to a trace.
Author-published screenshot of Laminar's existing trace and Signals interface. It illustrates the platform, not an AITrending test of flow-1 or evidence of its benchmark results. Source: Laminar / lmnr contributors
ai-agentsagent-ecosystemself-hosted

What happened lately

Laminar timeline

Laminar combines agent tracing, evaluations, dashboards and structured analysis of agent behavior. Its Signals harness investigates traces from a plain-English instruction and produces events linked to the relevant spans. The company’s flow-1 model is trained for this investigation workflow.

The platform repository uses Apache 2.0 and documents Docker Compose self-hosting, alongside Laminar’s managed service. TypeScript and Python SDK setup requires a project API key. Self-hosted AI features require a configured model provider and its credentials, with provider and infrastructure costs remaining the operator’s responsibility. The platform’s license does not establish that flow-1’s trained weights are publicly available.