Laminar
Laminar is an open-source observability and debugging platform for AI agents, designed around OpenTelemetry.
What Laminar is
Laminar is an open-source observability and debugging platform for AI agents, designed around OpenTelemetry. It traces LLM calls, tool use, custom functions and sub-agents, then presents those runs as readable transcripts. Signals turn plain-language descriptions of outcomes or failures into structured events across traces. For debugging, it can replay a run from cache up to the point under examination, using cached results for earlier calls. Teams can run evaluations against datasets locally or in CI to look for regressions. The platform also provides realtime traces, full-text search, raw SQL access through its UI, CLI or MCP, and custom dashboards. Integrations include OpenAI, Anthropic, Gemini, Cohere, LangChain, Pydantic AI, Claude Code and Playwright. Laminar is available as managed cloud or self-hosted software; self-hosted deployments can run on AWS or GCP with Helm charts. A free plan includes 1 GB of data and seven-day retention. Starter costs $30/mo, with higher plans also listed.
Good
- Traces LLM calls, tools, functions and sub-agents.
- Replays runs from cached prior calls.
- Runs evaluations locally or in CI.
- Offers managed cloud and self-hosting.
Watch out
- Free plan includes one project and one seat.
- Free plan retention is seven days.
- Starter costs $30/mo.
- PII redaction is best-effort and not a sole safeguard.
Who it suits
Laminar suits teams building AI agents that need trace inspection, run replay, evaluations or cost tracking. Its free plan may suit a small project, while self-hosting is an option for teams deploying on AWS or GCP.
Verdict
Laminar combines agent tracing, cached replay, evaluations and data tools in one platform. Check the plan limits and privacy safeguards against your needs before choosing a deployment.
Plans and prices
From Laminar's own pricing page, checked 3 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Free | Free | 1 GB data · no overage · $5 one-time Signals credit · 7 day retention · 1 project · 1 seat · Community support · $0/ month |
| Starter | $30 a month | 3 GB data included · then $2 / GB · $5 one-time Signals credit · 30 day retention · Unlimited projects · Unlimited seats · Email support · $30/ month |
| Pro | $150 a month | 10 GB data included · then $1.50 / GB · $5 one-time Signals credit · 6 month retention · Unlimited projects · Unlimited seats · Slack support · $150/ month |
| Enterprise | Priced on request | Custom limits · On-premise · Unlimited projects · Unlimited seats · Dedicated support · Custom |
The facts
Each one read from Laminar's own pages, with the date it was checked.
The company
- Company
- Y Combinator lists Laminar as founded in 2024 and located in London, United Kingdom.checked 3 Oct 2026
What it does
- Data tools
- The platform offers realtime traces, full-text search, raw SQL access through the UI, CLI or MCP, and custom dashboards.checked 3 Oct 2026
- Debugger
- The debugger can replay a run from cache up to the point being tested, with prior calls served from cache.checked 3 Oct 2026
- Deployment
- Laminar offers managed cloud and self-hosting; its site says self-hosted deployments can run on AWS or GCP with Helm charts.checked 3 Oct 2026
- Evaluations
- Users can run evaluations against datasets locally or in CI to catch regressions.checked 3 Oct 2026
- Integrations
- Documented integrations include OpenAI, Anthropic, Gemini, Cohere, LiteLLM, Vercel AI SDK, LangChain, Pydantic AI, Claude Code, Codex, Browser Use, Stagehand, Playwright, and others.checked 3 Oct 2026
- Privacy
- Privacy Mode defaults to off on Free and Starter, on for Pro and higher, and on and unchangeable for accounts covered by a signed DPA; when enabled, Customer Data is not used to train or improve its machine-learning models.checked 3 Oct 2026
- Privacy limits
- The privacy notice says PII redaction is best-effort and applies to model input/output content, so customers should not rely on it as their only safeguard.checked 3 Oct 2026
- Product
- Laminar is an open-source, OpenTelemetry-native observability and debugging platform built for AI agents.checked 3 Oct 2026
- Security
- Laminar states it is HIPAA and SOC 2 Type II compliant and offers server-side PII redaction on eligible plans.checked 3 Oct 2026
- Signals
- Signals let users describe outcomes and failures in plain language and extract structured events across traces.checked 3 Oct 2026
- Support
- The listed support options are community support on Free, email on Starter, Slack on Pro, and dedicated support for Enterprise.checked 3 Oct 2026
- Tracing
- It traces LLM calls, tool use, custom functions, and sub-agents, and presents traces as readable transcripts.checked 3 Oct 2026
Alternatives to Laminar
- 1
Vellum
Free planOpen sourceAndroidiOSWebAPI8.7From $30 a month - 2
W&B Weave
Free planOpen sourceiOSWebAPILinux8.7From $60 a month - 3
DeepEval
Free planOpen sourceWebAPILinuxmacOS8.3From $200 a month - 4
Langfuse
Free planOpen sourceWebAPILinuxSelf-hosted8.2From $29 a month - 5
Agenta
Free planOpen sourceWebAPISelf-hosted8.0From $29 a month - 6
LangSmith
Free planWebAPILinuxmacOS8.0$39 usage-based