Laminar
laminar.shOpen-source platform to trace, evaluate, and improve AI agents.
AI Toolsobservabilityai-agentsllm-tracingevaluationsopen-sourcedeveloper-toolsdebugging
About
Laminar is an open-source observability platform built specifically for AI agents, enabling developers to trace LLM calls, tool use, and custom functions. It provides agent debugging, browser session replay, signal extraction from traces, SQL-based data querying, and evaluation pipelines. Teams can use it both during development and in production to understand agent behavior and iterate quickly.
Problem
Developers struggle to understand why their AI agents fail and lack the tooling to debug, trace, and evaluate agent behavior at scale.
For
AI/ML engineers and developers building AI agents and LLM-powered applications
How it works
Developers integrate Laminar with two lines of code alongside their existing AI frameworks, which then captures traces of every LLM call, tool execution, and function, enabling replay, signal extraction, and evaluation.
Business model
open-source
Status
launched