# Laminar

**Canonical:** https://apis.io/providers/laminar/  
**Website:** https://laminar.sh/  
**APIs profiled:** 3

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.

## Kin Score — 43.7 / 100 (developing)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 43.7).

| Facet | Score |
|---|---|
| Discoverability | 81.5 |
| Contract Quality | 0.0 |
| Governance | 18.2 |
| Contract Governance | 18.2 |
| Operational Transparency | 18.4 |
| Developer Ergonomics | 78.6 |
| Commercial Clarity | 76.3 |
| Access Clarity | 76.3 |

## Agent readiness — 23.1 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | verified |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | yes |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Freemium · Self-serve signup — onboarding: self-serve, pricing: freemium, trial: no (confidence: high).

## APIs (3)

- **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)

- **Laminar MCP Server**

## Security (2)

- **Laminar Authentication** — http/oauth2 · 2 schemes
- **Laminar Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Laminar Plans**

## Tags

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

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/laminar/). Scores are computed from the provider's own public artifacts under a published rubric.