Laminar
Open-source platform to trace, evaluate, and improve AI agents.
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.
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.
AI/ML engineers and developers building AI agents and LLM-powered applications
Background.
- Status
- launched
- Business model
- open-source
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.