Laminar

Open source

Open-source observability platform for AI agents with OpenTelemetry-based tracing, evaluations, dashboards, and plain-English alerts on agent behavior.

laminar.sh
Laminar homepage screenshot
GitHub stars
3.5k
Last 30 days
+109(+3%)
Last commit
yesterday
Repository age
2 years
Version
v0.3.4
Licence
Apache-2.0
Self-hosted
Yes

About Laminar

Laminar is an open-source observability platform built for AI agents. It records what agents do during each run so that teams can debug failures, track behavior, and measure quality. The project is released under the Apache-2.0 license and the backend is written largely in Rust, with a TypeScript front end.

Tracing is based on OpenTelemetry, and a single line of SDK setup can automatically trace libraries such as the Vercel AI SDK, Browser Use, Stagehand, LangChain, OpenAI, Anthropic, and Gemini. Signals let you describe a behavior, such as an agent getting stuck in a loop, in plain English and be notified in Slack when it occurs. Evals run through an SDK and CLI locally or in CI, with a UI for comparing results, and SQL queries and dashboards cover traces, metrics, and events.

Coding agents can reach the data through MCP and CLI access to investigate issues themselves. Laminar can be self-hosted locally with Docker Compose, or used as the managed platform at laminar.sh. It suits teams building production agents who need tracing, evaluation datasets, and annotation in one place.

Key features

  • OpenTelemetry-native tracing SDK
  • Plain-English signals with Slack alerts
  • Evals via SDK and CLI with comparison UI
  • SQL queries over traces, spans, and metrics
  • Custom dashboards for traces and events
  • MCP and CLI access for coding agents
  • Datasets and data annotation tools

Good fit for

  • Debugging failing AI agent runs
  • Running agent evaluations in CI
Tags
observability
ai-agents
llm-tracing
evals
opentelemetry
llmops
self-hosted
monitoring

Laminar: questions and answers

What is Laminar used for?
Laminar is an open-source observability platform for AI agents with OpenTelemetry-based tracing, evaluations, dashboards, and plain-English alerts on agent behavior. It is a good fit for debugging failing AI agent runs and running agent evaluations in CI.
Is Laminar open source?
Yes. Laminar is open source under the Apache-2.0 licence. Its source code is on GitHub at lmnr-ai/lmnr and is written mainly in TypeScript.
Is Laminar free?
Yes. Laminar is open source, so the software itself is free to use. A managed cloud version is also available, with paid plans from $30 per month.
Can I self-host Laminar?
Yes. Laminar can be self-hosted on your own server or infrastructure.
What is Laminar an alternative to?
Laminar is an open-source alternative to Weights & Biases, LangSmith, Arize AI and Braintrust. Other open-source alternatives to Weights & Biases include Langfuse, Opik and Arize Phoenix.
Is Laminar actively maintained?
Yes. The most recent commit to Laminar was on 12 November 2026, and the latest release is v0.3.4, published on 10 November 2026. The project has 3.5k stars on GitHub, with 109 added in the last 30 days.

Open-source alternatives to Laminar

See all

SaaS alternatives to Laminar

See all