OpenLLMetry

Visit Website

Introduction

OpenLLMetry is open-source observability for GenAI and LLM applications based on OpenTelemetry, maintained by Traceloop. It provides instrumentations for LLM providers, vector databases and frameworks, so LLM calls appear as standard spans with prompts, completions, token counts and latency.

Because it emits OpenTelemetry, traces can go to any compatible backend, such as Datadog, Honeycomb, Grafana Tempo, New Relic, SigNoz or Traceloop’s own platform. The Traceloop SDK initialises everything in one call, and decorators mark workflows and tasks.

In the quality loop it makes LLM behaviour visible in the observability stack teams already run.

The source code is at traceloop/openllmetry on GitHub under the Apache-2.0 licence, with about 7,500 stars; the most recent commit was on 5 November 2026.

Features

1. OTel-native: Standard spans and attributes.
2. Provider instrumentations: Many LLM APIs.
3. Vector DB instrumentations: Popular vector stores.
4. Framework support: LangChain, LlamaIndex and others.
5. Any backend: Export to existing APM tools.
6. Workflow decorators: Group spans logically.

Pros

1. No lock-in: Uses open standards.
2. Free to use: Open source under the Apache-2.0 licence, so the core tool costs nothing to use.
3. Actively maintained: The repository had commits as recent as 5 November 2026.
4. Community: About 7,500 GitHub stars.

Cons

1. Backend needed: You still need somewhere to store traces.
2. Prompt data in traces: Sensitive content needs controls.
3. Evaluation is separate: Tracing only, unless using Traceloop’s platform.

Usage and Links (Example)

from traceloop.sdk import Traceloop
Traceloop.init(app_name="support-bot", api_endpoint="http://otel-collector:4318")

Resources:

• OpenLLMetry website
• GitHub repository

Pricing

OpenLLMetry is free and open source under the Apache-2.0 licence.

Recommended for?

1. Teams with existing OpenTelemetry pipelines.

Conclusion

OpenLLMetry is the standards-based way to trace LLM apps.

Configure content redaction before sending prompts to shared backends.

On CheckOps, OpenLLMetry is filed under the Production monitoring & observability stage. Related tools listed here include Langfuse, Laminar, Helicone, AgentOps, Arize Phoenix and Opik. Before standardising on one, compare recent maintenance activity, the pricing model as your usage grows, and the integrations you rely on today. Information on this page was verified against the official website, documentation and repository on 11 November 2026.