Updated

OpenLLMetry

Traceloop's open-source OpenTelemetry instrumentation for LLM apps, which sends traces of model, vector store and framework calls to any OpenTelemetry backend or to the Traceloop platform.

6 open-source projects declare OpenLLMetry in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostableFree tier

Acquired: Traceloop announced it is joining ServiceNow; it says OpenLLMetry stays open source and existing customers' obligations will be honoured. Source ↗

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use OpenLLMetry

What OpenLLMetry is used for

LLM Observability & Evals · Open-source platform →Open-source OpenTelemetry instrumentation that traces model, vector store and framework calls and sends them to any OpenTelemetry backend.Trade-off: Instrumentation only — you still need a backend to store and view traces; Traceloop, its maker, is joining ServiceNow.
Datadog50Langfuse35Helicone13LangSmith11Braintrust6OpenLLMetry0Makers' products on each, for LLM observability & evals

OpenLLMetry vs the alternatives makers chose

OptionMakers' productsFree forAt 10,000 usersOpen source
Datadog50 43%——No
Langfuse35 30%~5,000 users$29/mo · CoreYes
Helicone13 11%~1,000 users$116/mo · ProYes
LangSmith11 9%~520 users$475/mo · DeveloperNo
Braintrust6 5%——No
Weights & Biases3 3%——No
OpenLLMetry0 0%——Yes

For LLM observability & evals: how many of the 117 makers' products we know the LLM observability & evals of chose each option, and what each costs at 10,000 users.

Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.

When to use OpenLLMetry, and when not

Something else fits better if

  • You want tracing, prompts and evals in one tool you can self-host for free: Langfuse.
  • You already use OpenTelemetry or want vendor-neutral instrumentation: Arize Phoenix.
  • You want request logs and costs today by changing one base URL: Helicone.
  • Your app is built on LangChain or LangGraph: LangSmith.
  • Your main question is whether a prompt or model change made outputs better or worse: Braintrust.
From each decision's guide, written from what makers' products chose and why.

How OpenLLMetry itself is built

31 tools, from its own code, website and Product Hunt page.

Who uses it

No maker's live product on record yet, and 6 open-source projects that declare it in their code.

We haven't found a maker's live product that uses OpenLLMetry yet — only the open-source projects below, which declare it in their code.

Open source: a project that declares OpenLLMetry as a dependency in its public code — verifiable, but not necessarily a live product.

Alternatives to OpenLLMetry

All alternatives by situation →

Questions makers ask about OpenLLMetry

What are the alternatives to OpenLLMetry?

For LLM observability & evals, the other options makers' products we track chose most are Datadog (50), Langfuse (35), Helicone (13), LangSmith (11), Braintrust (6), Weights & Biases (3). Open source or self-hostable among them: Langfuse, Helicone, Weights & Biases. Each alternative, with the situation it fits, is on the OpenLLMetry alternatives page.

Is OpenLLMetry free?

Yes — it is free, open-source software. source ↗

Is OpenLLMetry open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with OpenLLMetry?

No llms.txt, official MCP server or CLI found yet.

Who uses OpenLLMetry?

No maker's live product we track yet; 6 open-source projects declare it in their code. source ↗