Laminar

Laminar is an open-source, OpenTelemetry-native observability and debugging platform built for AI agents and LLM applications. It traces every LLM call, tool call, and sub-agent a run produces, renders each trace as a readable transcript rather than a raw span tree, and turns that data into answers: a record-and-replay Debugger that serves everything before your change from cache so each iteration takes seconds, and Signals that let you describe outcomes and failures in plain language and extract structured events across all traces for clustering and alerting. The platform adds evaluations, datasets and labeling queues, a playground, full-text search, custom dashboards, and read-only ClickHouse SQL over trace data from the UI, the lmnr-cli, or a hosted MCP server. Laminar ships TypeScript and Python SDKs with auto-instrumentation for the Vercel AI SDK, Claude Agent SDK, OpenAI Agents SDK, LangChain/LangGraph, Pydantic AI, Browser Use, Playwright and more, and can run as managed Laminar Cloud or fully self-hosted via Docker Compose or Kubernetes/Helm.

Laminar publishes 3 APIs on the APIs.io network. Tagged areas include Observability, LLM, AI Agents, Tracing, and OpenTelemetry.

Laminar’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, pricing, signup flow, and 26 more developer resources.

🌐 Visit website 📡 Source on GitHub

45.3/100 developing ▬ flat Agent 15/100 agent aware open core · Apache-2.0 Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0

AccessFreemiumSelf serve⚡ Free to try

3 APIs 1 MCP Servers

Observability LLM AI Agents Tracing OpenTelemetry Evaluations Monitoring Developer Tools Open-Source

Kin Score

Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0

Composite quality — 45.3/100 · developing

Contract Quality 0.0 / 23

Developer Ergonomics 14.1 / 18

Access Clarity 13.7 / 18

Operational Transparency 3.1 / 12

Contract Governance 2.0 / 11

Discoverability 7.3 / 9

Open Source Surface 5.0 / 10

Agent readiness — 15/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Open Source Surface applies to this provider. This product is open source and we read its repository directly, so Open Source Surface carries 10 points of the composite. It is scored from what the repository actually publishes — a security policy, a contribution guide, a release history, a code of conduct — read live from the provider rather than inferred from our own catalog pointers. This facet adds; nothing was taken away to make room for it. An open-source project is not excused from the commercial facets, because exemption would strip it of the points it does earn. If we have the wrong repository, or this product is not open source, say so on your provider repo and we will drop the facet rather than have you publish against it.

Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 90 points between them, because the conditional facet above carries the other 10. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 90% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/laminar: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 3

Individual APIs this provider publishes, each with its own machine-readable definition.

Laminar SQL Query API

Run SELECT-only ClickHouse SQL over a project's observability data via POST /v1/sql/query. Authenticates with a project API key as a bearer token, accepts a query plus typed {na...

Laminar OpenTelemetry Trace Ingest API

The standard OpenTelemetry trace ingest endpoint at /v1/traces. Laminar accepts OTLP over gRPC, HTTP+protobuf, and (since May 2026) HTTP+JSON, so any OpenTelemetry-capable runti...

Laminar Evaluations API

The lower-level LaminarClient.evals surface for wiring evaluations into an existing pipeline: create an evaluation, pre-register each datapoint so a row is visible in the UI bef...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

Laminar MCP Server

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Laminar Plans

4 plans

PLANS

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Laminar Authentication

http/oauth2 · 2 schemes

SECURITY

Laminar Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Documentation 3

Reference material describing how the API behaves

ContributionGuide

ContributionGuide

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer

AgentSkill

LLMsTxt

WellKnown

Design & Contract 3

Pagination, idempotency, versioning, errors, and events

Conventions

Conventions

Lifecycle

Lifecycle

Conformance

Conformance

Build 5

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

SourceCode

Packages

SDKs

CLI

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 5

Status, limits, changes, and where to get help

IssueTracker

Releases

Support

StatusPage

ChangeLog

Commercial 5

Pricing, plans, and the legal terms of use

License

Pricing

TermsOfService

PrivacyPolicy

Plans

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 1

Properties that don't map to a standard resource type

SelfHosted

SelfHosted

Source (apis.yml)

aid: laminar
name: Laminar
description: 'Laminar is an open-source, OpenTelemetry-native observability and debugging platform built for AI agents and
  LLM applications. It traces every LLM call, tool call, and sub-agent a run produces, renders each trace as a readable transcript
  rather than a raw span tree, and turns that data into answers: a record-and-replay Debugger that serves everything before
  your change from cache so each iteration takes seconds, and Signals that let you describe outcomes and failures in plain
  language and extract structured events across all traces for clustering and alerting. The platform adds evaluations, datasets
  and labeling queues, a playground, full-text search, custom dashboards, and read-only ClickHouse SQL over trace data from
  the UI, the lmnr-cli, or a hosted MCP server. Laminar ships TypeScript and Python SDKs with auto-instrumentation for the
  Vercel AI SDK, Claude Agent SDK, OpenAI Agents SDK, LangChain/LangGraph, Pydantic AI, Browser Use, Playwright and more,
  and can run as managed Laminar Cloud or fully self-hosted via Docker Compose or Kubernetes/Helm.'
deliveryModel:
  model: open-core
  license: Apache-2.0
  open_source: true
  commercial: true
  callable_host: false
  label: Open core · an OSS project plus a commercial hosted product
  confidence: high
  source:
  - license
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Freemium · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://laminar.sh/favicon.ico
url: https://raw.githubusercontent.com/api-evangelist/laminar/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- insight-partners
- techstars
x-backed-by-note: Inherited from the originating VC-portfolio stub and NOT verified against this company during enrichment.
  Laminar (lmnr / laminar.sh) is the open-source AI-agent observability company; the name collides with other companies called
  Laminar. Treat x-backed-by as unverified.
x-tier: enriched
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Observability
- LLM
- AI Agents
- Tracing
- OpenTelemetry
- Evaluations
- Monitoring
- Developer Tools
- Open-Source
tags_raw:
- Observability
- LLM
- AI Agents
- Tracing
- OpenTelemetry
- Evaluations
- Monitoring
- Developer Tools
- Open Source
apis:
- aid: laminar:laminar-sql-query-api
  name: Laminar SQL Query API
  humanURL: https://laminar.sh/docs/platform/sql-editor
  baseURL: https://api.lmnr.ai
  tags:
  - SQL
  - Traces
  - Spans
  - Analytics
  description: Run SELECT-only ClickHouse SQL over a project's observability data via POST /v1/sql/query. Authenticates with
    a project API key as a bearer token, accepts a query plus typed {name:Type} parameters, and returns rows as a JSON data
    array. Queryable tables are spans, traces, events, tags, dataset_datapoints, dataset_datapoint_versions and evaluation_datapoints;
    queries are automatically scoped to the calling project so no tenant filter is required.
  properties:
  - url: https://laminar.sh/docs/platform/sql-editor
    type: Documentation
  - url: https://github.com/lmnr-ai/lmnr-skills/blob/main/skills/laminar/references/sql-query-api.md
    type: APIReference
- aid: laminar:laminar-otlp-trace-ingest-api
  name: Laminar OpenTelemetry Trace Ingest API
  humanURL: https://laminar.sh/docs/tracing/otel
  baseURL: https://api.lmnr.ai
  tags:
  - OpenTelemetry
  - OTLP
  - Tracing
  - Ingest
  description: The standard OpenTelemetry trace ingest endpoint at /v1/traces. Laminar accepts OTLP over gRPC, HTTP+protobuf,
    and (since May 2026) HTTP+JSON, so any OpenTelemetry-capable runtime — including browser SDKs without a protobuf encoder
    — can send spans without the Laminar SDK. Authenticated with a project API key; gRPC ingest is served on port 8443 for
    Laminar Cloud.
  properties:
  - url: https://laminar.sh/docs/tracing/otel
    type: Documentation
  - url: https://laminar.sh/docs/tracing/introduction
    type: Tracing
- aid: laminar:laminar-evaluations-api
  name: Laminar Evaluations API
  humanURL: https://laminar.sh/docs/evaluations/manual-evaluation
  baseURL: https://api.lmnr.ai
  tags:
  - Evaluations
  - Datasets
  - Scoring
  description: 'The lower-level LaminarClient.evals surface for wiring evaluations into an existing pipeline: create an evaluation,
    pre-register each datapoint so a row is visible in the UI before the executor runs, then update that datapoint with a
    trace id, executor output, and scores. Because update can be called any time after create, the executor and the scorer
    can run in different processes, which supports async LLM-judge scoring and pure backfills of scored rows.'
  properties:
  - url: https://laminar.sh/docs/evaluations/manual-evaluation
    type: Documentation
  - url: https://laminar.sh/docs/sdk/client
    type: APIReference
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: IssueTracker
  url: https://github.com/lmnr-ai/lmnr/issues
- type: Releases
  url: https://github.com/lmnr-ai/lmnr/releases
- type: ContributionGuide
  url: https://github.com/lmnr-ai/lmnr/blob/main/CONTRIBUTING.md
- type: License
  name: Apache-2.0
  url: https://github.com/lmnr-ai/lmnr/blob/main/LICENSE
- type: DomainSecurity
  url: security/laminar-domain-security.yml
- type: Website
  url: https://laminar.sh/
- type: DeveloperPortal
  url: https://laminar.sh/docs
- type: Documentation
  url: https://laminar.sh/docs
- type: APIReference
  url: https://laminar.sh/docs/sdk/client
- type: GettingStarted
  url: https://laminar.sh/docs/getting-started
- type: Support
  url: https://discord.gg/nNFUUDAKub
- type: Blog
  url: https://laminar.sh/blog
- type: GitHubOrganization
  url: https://github.com/lmnr-ai
- type: SourceCode
  url: https://github.com/lmnr-ai/lmnr
- type: Pricing
  url: https://laminar.sh/pricing
- type: SignUp
  url: https://laminar.sh/sign-in
- type: TermsOfService
  url: https://laminar.sh/policies/terms
- type: PrivacyPolicy
  url: https://laminar.sh/policies/privacy
- type: StatusPage
  url: https://status.laminar.sh
- type: SelfHosted
  url: https://laminar.sh/docs/self-hosting/overview
- type: Packages
  url: packages/laminar-packages.yml
- type: SDKs
  url: packages/laminar-packages.yml
- type: CLI
  url: cli/laminar-cli.yml
- type: MCPServer
  url: mcp/laminar-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/laminar-llms.txt
- type: Authentication
  url: authentication/laminar-authentication.yml
- type: Conventions
  url: conventions/laminar-conventions.yml
- type: ChangeLog
  url: changelog/laminar-changelog.yml
- type: Lifecycle
  url: lifecycle/laminar-lifecycle.yml
- type: Conformance
  url: conformance/laminar-conformance.yml
- type: WellKnown
  url: well-known/laminar-well-known.yml
- type: Plans
  url: plans/laminar-plans.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/laminar"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/laminar/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/laminar/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.