Laminar

What's Changed

• refactor(LAM-1789): sync signals OTEL tracing refactor to OSS by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1924
• remove slow tools check in default signal prompt by @Rainhunter13 in https://github.com/lmnr-ai/lmnr/pull/1932
• feat(clusters): Clusters UI Refresh by @kolbeyang in https://github.com/lmnr-ai/lmnr/pull/1903
• feat(landing): add debugger by @kolbeyang in https://github.com/lmnr-ai/lmnr/pull/1931
• LAM-1804: Copy signal settings sidebar + custom alert filters to OSS by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1934
• fix: alert sheet skeleton no longer traps on failed signals fetch by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1935
• chore: drop unused labeling_queue_items Postgres table (LAM-1808) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1937
• add a switch so sql API requests >N bytes do direct disk read by @dinmukhamedm in https://github.com/lmnr-ai/lmnr/pull/1940
• feat(onboarding): add CLI setup connect step as final wizard page (LAM-1802) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1933
• feat(api-keys): API key expiration + creator user_id (LAM-1666) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1941
• fix(auth): sign-in provider icon colors (LAM-1817) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1950
• fix(signals): allow free-tier users to access signal settings LAM-1818 by @kolbeyang in https://github.com/lmnr-ai/lmnr/pull/1951
• feat(frontend): serve under a configurable base path (LAM-1749) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1895
• refactor: update README by @kolbeyang in https://github.com/lmnr-ai/lmnr/pull/1908
• fix: scope main-agent output span lookup by trace_id (LAM-1821) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1952
• LAM-1807: denormalize cache-read & reasoning tokens onto trace row by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1942
• LAM-1830: port public agent/MCP changes from lmnr-private by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1959
• create rw keys for CLI setup by @dinmukhamedm in https://github.com/lmnr-ai/lmnr/pull/1960
• LAM-1811: drop unused events/tags ClickHouse tables and clean up usages by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1939
• per million tokens pricing for signals by @dinmukhamedm in https://github.com/lmnr-ai/lmnr/pull/1962
• remove signals feature on backend test action by @dinmukhamedm in https://github.com/lmnr-ai/lmnr/pull/1967
• fix: merge metadata on trace pre-agg as well, pg already does similar by @dinmukhamedm in https://github.com/lmnr-ai/lmnr/pull/1969
• LAM-1839: show project name in signal event email notifications by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1964
• feat(slack): port public Slack channel-agent scaffolding to OSS (LAM-1847) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1970
• feat: mirror private impl by @olzhik11 in https://github.com/lmnr-ai/lmnr/pull/1971
• Fix/integrations by @olzhik11 in https://github.com/lmnr-ai/lmnr/pull/1972
• LAM-1806: render all signal findings in trace-view panel by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1936
• cleanup signal steps notion (fully removed from) DB now by @dinmukhamedm in https://github.com/lmnr-ai/lmnr/pull/1973
• fix: opengraph images by @kolbeyang in https://github.com/lmnr-ai/lmnr/pull/1966
• fix(billing): pricing accuracy and usage-page UI fixes (LAM-1857) by @olzhik11 in https://github.com/lmnr-ai/lmnr/pull/1978
• fix(search): render filter tags for unregistered columns (LAM-1853) by @laminar-coding-agent[bot] in https://github.com/lmnr-ai/lmnr/pull/1976
• LAM-1854: query engine accepts INTERVAL with unit inside string literal by @laminar-coding-agent[b

<a href="https://www.ycombinator.com/companies/laminar-ai">Static Badge</a>

<a href="https://x.com/lmnrai">X (formerly Twitter) Follow</a>

<a href="https://www.linkedin.com/company/lmnr-ai">LinkedIn</a>

<a href="https://discord.gg/nNFUUDAKub"> Static Badge </a>

Laminar banner

Laminar

Laminar is an open-source observability platform purpose-built for AI agents.

• [x] Tracing. Docs
• [x] OpenTelemetry-native powerful tracing SDK - 1 line of code to automatically trace Vercel AI SDK, Browser Use, Stagehand, LangChain, OpenAI, Anthropic, Gemini, and more.
• [x] Signals. Docs
• [x] Describe any behavior of your agent that you want to track in plain English (e.g. "agent is stuck in a loop")
• [x] Laminar reads every agent run and pings you in Slack when it happens.
• [x] Evals. Docs
• [x] Unopinionated, extensible SDK and CLI for running evals locally or in CI/CD pipeline.
• [x] UI for visualizing evals and comparing results.
• [x] MCP / CLI access for your coding agent
• [x] Query traces, spans, metrics, and events with SQL
• [x] Let your coding agent investigate and debug issues based on your traces
• [x] Dashboards. Docs
• [x] Powerful dashboard builder for traces, metrics, and events with support of custom SQL queries.
• [x] Data annotation & Datasets. Docs
• [x] Custom data rendering UI for fast data annotation and dataset creation for evals.
• [x] Extremely high performance.
• [x] Written in Rust 🦀
• [x] 20x trace compression for efficient ingestion and storage. Read more about it here.
• [x] Custom realtime engine for viewing traces as they happen.
• [x] Ultra-fast full-text search over span data.
• [x] gRPC exporter for tracing data.

Traces

Documentation

Check out the full documentation here laminar.sh/docs.

Getting started

The fastest and easiest way to get started is with our managed platform -> laminar.sh

Self-hosting with Docker compose

Laminar is very easy to self-host locally. For a quick start, clone the repo and start the services with docker compose:

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

This will spin up a lightweight but full-featured version of the stack. This is good for a quickstart

or for lightweight usage. You can access the UI at http://localhost:5667 in your browser.

You will also need to properly configure the SDK, with baseUrl and correct ports. See guide on self-hosting.

For production environment, we recommend using our managed platform or docker compose -f docker-compose-full.yml up -d.

Configuring LLM provider (optional)

Frontend AI features (chat-with-trace, SQL-with-AI) and server-side AI workers require an LLM provider. Configure one in your .env file at the repo root.

Pick one of the following provider setups. LLM_MODEL_SMALL|MEDIUM|LARGE are optional — per-provider defaults apply when unset. LLM_DEFAULT_HEADERS_JSON is optional for any provider or gateway that requires static headers.

# Optional for any provider/gateway that requires static headers
# LLM_DEFAULT_HEADERS_JSON='{"X-Gateway-Tenant":"tenant"}'

# Option A: Gemini
LLM_PROVIDER=gemini
LLM_API_KEY=your_gemini_key

# Option B: OpenAI (or any OpenAI-compatible gateway such as LiteLLM, OpenRouter, vLLM)
LLM_PROVIDER=openai
# LLM_BASE_URL=http://localhost:4000   # optional, for OpenAI-compatible gateways
LLM_API_KEY=your_openai_key

# Option C: AWS Bedrock (Anthropic Claude). Uses AWS credentials instead of LLM_API_KEY.
LLM_PROVIDER=bedrock
AWS_ACCESS_KEY_ID=...
AWS_SECRET_ACCESS_KEY=...
AWS_REGION=us-east-1

Custom Postgres schema (optional)

By default Laminar uses the public schema. To target a different schema (e.g.

when deploying alongside other services in a shared Postgres instance), set the

same value for both the frontend and the app-server:

POSTGRES_SCHEMA=laminar
# Set to false if the schema is pre-provisioned or the DB role lacks CREATE.
# POSTGRES_CREATE_SCHEMA=true

The schema is applied as the connection search_path, so all tables, foreign

keys, and migrations target it. When a non-public schema is set, the frontend

also tracks migrations inside that schema (<schema>.__drizzle_migrations)

rather than the shared drizzle schema. Note that running Laminar alongside

another Drizzle-managed service in the same database may still require manual

intervention, since Drizzle's migration journal is versioned per-schema.

Anonymous usage telemetry

Self-hosted deployments collect anonymized usage telemetry. To opt out, set LAMINAR_TELEMETRY_DISABLED=true in your .env.

Contributing

For running and building Laminar locally, or to learn more about docker compose files,

follow the guide in Contributing.

TS quickstart

First, create a project and generate a project API key. Then,

npm add @lmnr-ai/lmnr

It will install Laminar TS SDK and all instrumentation packages (OpenAI, Anthropic, LangChain ...)

To start tracing LLM calls just add

import { Laminar } from '@lmnr-ai/lmnr';
Laminar.initialize({ projectApiKey: process.env.LMNR_PROJECT_API_KEY });

To trace inputs / outputs of functions use observe wrapper.

import { OpenAI } from 'openai';
import { observe } from '@lmnr-ai/lmnr';

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const poemWriter = observe({name: 'poemWriter'}, async (topic) => {
  const response = await client.chat.completions.create({
    model: "gpt-4o-mini",
    messages: [{ role: "user", content: `write a poem about ${topic}` }],
  });
  return response.choices[0].message.content;
});

await poemWriter();

Python quickstart

First, create a project and generate a project API key. Then,

pip install --upgrade 'lmnr[all]'

It will install Laminar Python SDK and all instrumentation packages. See list of all instruments here

To start tracing LLM calls just add

from lmnr import Laminar
Laminar.initialize(project_api_key="<LMNR_PROJECT_API_KEY>")

To trace inputs / outputs of functions use @observe() decorator.

import os
from openai import OpenAI

from lmnr import observe, Laminar
Laminar.initialize(project_api_key="<LMNR_PROJECT_API_KEY>")

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

@observe()  # annotate all functions you want to trace
def poem_writer(topic):
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "user", "content": f"write a poem about {topic}"},
        ],
    )
    poem = response.choices[0].message.content
    return poem

if __name__ == "__main__":
    print(poem_writer(topic="laminar flow"))

Client libraries

To learn more about instrumenting your code, check out our client libraries:

<a href="https://www.npmjs.com/package/@lmnr-ai/lmnr"> NPM Version </a>

<a href="https://pypi.org/project/lmnr/"> PyPI - Version </a>