Running in production · Independent · 19 Oct 2026

lmnr-ai/lmnr

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

← Running in production

In simple English

When you build software that uses language models or AI agents, things often fail in strange ways. This tool records every step your AI takes and puts it into a searchable dashboard. You can watch what your code sends and receives in real time. It helps you find out why your bot got stuck or gave a wrong answer. You can run it on your own server using Docker or pay for their cloud version.

What it is

Laminar is an open-source observability platform purpose-built for tracing, evaluating, and debugging AI agents and large language model applications. It collects telemetry data from your code and provides a web interface to inspect traces, manage evaluation datasets, and query logs with SQL.

What it is good for

Solo developers building AI agents who need a clear way to see where their prompts fail, track token costs, and test changes before pushing them to users.

Stars3.4k
LicenceApache-2.0
Latestv0.3.2 (2026-10-16)checked 19 Oct 2026
Last code change2026-10-19
Written inTypeScript
Setup effort
3 / 5
Payoff
4 / 5
Good
  • Records traces automatically for major AI libraries with a single line of code.
  • Includes a local evaluation tool to test prompt changes in your terminal or CI pipeline.
  • Fast search and storage built with Rust and ClickHouse to handle large trace logs.
Watch for
  • Requires running external databases like ClickHouse and Postgres alongside the main service if you self-host.
  • Needs an LLM provider key configured to power the built-in AI search and chat features.
  • Self-hosted deployments collect anonymous usage telemetry by default unless you opt out.
Replaces

Console.log debugging of prompt outputs and manual spreadsheet tracking of AI test cases.

Works well with

Docker (a way to run a program inside its own sealed box, so it cannot break anything else on your server) and OpenAI.

Similar repositories
  • langfuse/langfuse36k stars

    An open-source LLM engineering platform that offers similar tracing, analytics, and prompt management.

  • Arize-ai/phoenix12k stars

    An open-source AI observability tool focused on evaluation, tracing, and troubleshooting for LLM applications.

Also reviewed on Repo Radar
  • nicolargo/glances34k stars

    A live view of one computer's health, in a terminal, in a browser, or through an AI assistant.

  • dokku/dokku32k stars

    A small platform you install on one server, which builds and runs an app every time you push code to it.

  • netbox-community/netbox22k stars

    A database of what a network and its hardware are supposed to look like, which other programs can read.

Install
git clone https://github.com/lmnr-ai/lmnr
cd lmnr
docker compose up -d

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Development & Evaluation › AI Observability.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.