OpenLLMetry is an open-source observability framework for LLM and generative AI applications, built on top of OpenTelemetry. Maintained by Traceloop under the Apache 2.0 license, it provides drop-in instrumentation for 30+ LLM providers, vector databases, and agent frameworks, and emits standardized GenAI traces over OTLP to any observability backend (Datadog, Grafana, Honeycomb, New Relic, Splunk, Langfuse, LangSmith, Braintrust, and the Traceloop platform). Its semantic conventions for LLMs have been upstreamed into the OpenTelemetry GenAI semantic conventions.
OpenLLMetry is listed with 6 APIs on the APIs.io network. Tagged areas include Artificial Intelligence, LLM, Observability, Open Source, and OpenTelemetry.
OpenLLMetry’s developer surface includes pricing, documentation, engineering blog, getting-started guide, and 16 more developer resources.
Regulatory Posture applies to this provider. Its tags matched the
AI & Biometrics regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
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 75 points between them,
because both conditional facets apply and carry
25 points together. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 75% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/openllmetry/"><img src="https://apis.io/badge/openllmetry/card.svg" alt="OpenLLMetry on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Machine-Readable Auth+10 pts — a served openid-configuration/oauth-authorization-server carrying `issuer` (served), else the securitySchemes class in the provider OpenAPIs — bound (mutualTLS, DPoP, Signature) > negotiable (oauth2 authorizationCode/clientCredentials, openIdConnect) > bearer (http bearer, apiKey) Ask about this →
Idempotency+9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented) Ask about this →
Stable Error Semantics+8 pts — OpenAPI $refs a shared error schema across 4xx/5xx responses (verified), else common[].type includes ErrorCatalog / ErrorCodes / DeclineCodes Ask about this →
13 more unmet checks in the Agent Readiness table above.
Kin Score — facets with the most composite points still available (weight × headroom):
Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.
Not sure how this applies to your stack? Ask about any one item. Kin Lane reads every question, looks at your profile and your situation, and replies with what a fix would take — scoped to that one area, priced up front, yours whether you ship it or not. Ask a question →
The Traceloop SDK is the developer-facing entry point for OpenLLMetry. A single Traceloop.init() call configures OpenTelemetry, registers all available LLM/vector-DB/framework i...
Drop-in OpenTelemetry instrumentations for the major LLM providers including OpenAI, Anthropic, AWS Bedrock, Google Generative AI / Vertex AI, Cohere, Mistral AI, Ollama, Groq, ...
OpenLLMetry emits standard OpenTelemetry traces and metrics over OTLP (gRPC or HTTP), so any OpenTelemetry-compatible backend can receive its telemetry. Supported destinations i...
aid: openllmetry
url: https://raw.githubusercontent.com/api-evangelist/openllmetry/refs/heads/main/apis.yml
name: OpenLLMetry
kind: opensource
description: OpenLLMetry is an open-source observability framework for LLM and generative AI applications, built on top of
OpenTelemetry. Maintained by Traceloop under the Apache 2.0 license, it provides drop-in instrumentation for 30+ LLM providers,
vector databases, and agent frameworks, and emits standardized GenAI traces over OTLP to any observability backend (Datadog,
Grafana, Honeycomb, New Relic, Splunk, Langfuse, LangSmith, Braintrust, and the Traceloop platform). Its semantic conventions
for LLMs have been upstreamed into the OpenTelemetry GenAI semantic conventions.
deliveryModel:
model: self-hosted
license: Apache-2.0
license_evidence:
repo: traceloop/openllmetry
spdx: Apache-2.0
stars: 7447
open_source: true
commercial: false
callable_host: false
label: Self-hosted open source · you run it yourself
confidence: medium
source:
- repository-license
generated: '2026-09-25'
method: derived
accessModel:
pricing: freemium
onboarding: unknown
trial: false
try_now: false
public: false
label: Freemium
confidence: low
source:
- plans
- security
generated: '2026-11-13'
method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/openllmetry.png
tags:
- Artificial Intelligence
- LLM
- Observability
- Open Source
- OpenTelemetry
- Tracing
- Generative AI
tags_raw:
- AI
- LLM
- Observability
- Open Source
- OpenTelemetry
- Tracing
- GenAI
- Open-Source
created: '2026-05-25'
modified: '2026-05-25'
specificationVersion: '0.23'
apis:
- aid: openllmetry:openllmetry-traceloop-sdk
name: OpenLLMetry Traceloop SDK
tags:
- SDK
- Instrumentation
- Tracing
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
humanURL: https://www.traceloop.com/docs/openllmetry/introduction
properties:
- url: https://www.traceloop.com/docs/openllmetry/introduction
type: Documentation
- url: https://github.com/traceloop/openllmetry
type: GitHubRepository
- url: https://pypi.org/project/traceloop-sdk/
type: SDKs
- url: https://www.npmjs.com/package/@traceloop/node-server-sdk
type: SDKs
- url: https://www.traceloop.com/docs/openllmetry/getting-started-python
type: GettingStarted
- url: https://www.traceloop.com/docs/openllmetry/getting-started-nextjs
type: GettingStarted
- url: https://www.traceloop.com/docs/openllmetry/getting-started-go
type: GettingStarted
- url: https://www.traceloop.com/docs/openllmetry/getting-started-ruby
type: GettingStarted
description: The Traceloop SDK is the developer-facing entry point for OpenLLMetry. A single Traceloop.init() call configures
OpenTelemetry, registers all available LLM/vector-DB/framework instrumentations, and starts exporting GenAI traces to
any OTLP endpoint. Provides @workflow, @task, @agent, and @tool decorators (and TypeScript equivalents) for higher-level
tracing primitives, plus controls for prompt redaction, multi-modality content, user feedback, sessions, and prompt versioning.
- aid: openllmetry:openllmetry-semantic-conventions-ai
name: OpenLLMetry Semantic Conventions for AI
tags:
- Semantic Conventions
- OpenTelemetry
- Generative AI
tags_raw:
- Semantic Conventions
- OpenTelemetry
- GenAI
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
humanURL: https://opentelemetry.io/docs/specs/semconv/gen-ai/
properties:
- url: https://opentelemetry.io/docs/specs/semconv/gen-ai/
type: Documentation
- url: https://github.com/traceloop/openllmetry/tree/main/packages/opentelemetry-semantic-conventions-ai
type: GitHubRepository
- url: https://pypi.org/project/opentelemetry-semantic-conventions-ai/
type: SDKs
description: A vocabulary of span attribute names for GenAI workloads — gen_ai.system, gen_ai.request.model, gen_ai.response.model,
gen_ai.usage.input_tokens, gen_ai.usage.output_tokens, llm.prompts, llm.completions, traceloop.workflow.name, traceloop.entity.name,
and others. Originated in OpenLLMetry and has been upstreamed into the OpenTelemetry GenAI semantic conventions, giving
cross-vendor observability backends a shared schema for LLM telemetry.
- aid: openllmetry:openllmetry-llm-instrumentations
name: OpenLLMetry LLM Provider Instrumentations
tags:
- Instrumentation
- LLM Providers
- Tracing
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
humanURL: https://www.traceloop.com/docs/openllmetry/integrations/exporters
properties:
- url: https://www.traceloop.com/docs/openllmetry/integrations/exporters
type: Documentation
- url: https://github.com/traceloop/openllmetry/tree/main/packages
type: GitHubRepository
- url: https://pypi.org/project/opentelemetry-instrumentation-openai/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-anthropic/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-bedrock/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-google-generativeai/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-cohere/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-mistralai/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-ollama/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-groq/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-together/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-replicate/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-vertexai/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-sagemaker/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-watsonx/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-alephalpha/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-transformers/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-voyageai/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-writer/
type: SDKs
description: Drop-in OpenTelemetry instrumentations for the major LLM providers including OpenAI, Anthropic, AWS Bedrock,
Google Generative AI / Vertex AI, Cohere, Mistral AI, Ollama, Groq, Together AI, Replicate, SageMaker, Watsonx, Aleph
Alpha, HuggingFace Transformers, Voyage AI, and Writer. Each package monkey-patches the provider SDK to emit standardized
gen_ai.* spans without code changes.
- aid: openllmetry:openllmetry-vector-db-instrumentations
name: OpenLLMetry Vector Database Instrumentations
tags:
- Instrumentation
- Vector Search
- RAG
tags_raw:
- Instrumentation
- Vector Databases
- RAG
- Vector Database
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
humanURL: https://www.traceloop.com/docs/openllmetry/tracing/decorators
properties:
- url: https://www.traceloop.com/docs/openllmetry/tracing/decorators
type: Documentation
- url: https://github.com/traceloop/openllmetry/tree/main/packages
type: GitHubRepository
- url: https://pypi.org/project/opentelemetry-instrumentation-chromadb/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-pinecone/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-qdrant/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-weaviate/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-lancedb/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-milvus/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-marqo/
type: SDKs
description: Instrumentations for vector databases used in retrieval-augmented generation pipelines — Chroma, Pinecone,
Qdrant, Weaviate, LanceDB, Milvus, and Marqo. Captures query, upsert, and similarity- search operations with vector-DB-specific
attributes so RAG retrievals can be correlated with the LLM calls that consumed them.
- aid: openllmetry:openllmetry-framework-instrumentations
name: OpenLLMetry Framework and Agent Instrumentations
tags:
- Instrumentation
- Framework
- Agents
tags_raw:
- Instrumentation
- Frameworks
- Agents
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
humanURL: https://www.traceloop.com/docs/openllmetry/integrations
properties:
- url: https://www.traceloop.com/docs/openllmetry/integrations
type: Documentation
- url: https://github.com/traceloop/openllmetry/tree/main/packages
type: GitHubRepository
- url: https://pypi.org/project/opentelemetry-instrumentation-langchain/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-llamaindex/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-haystack/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-crewai/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-agno/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-openai-agents/
type: SDKs
- url: https://pypi.org/project/opentelemetry-instrumentation-mcp/
type: SDKs
description: Instrumentations for higher-level LLM frameworks and agent runtimes — LangChain, LlamaIndex, Haystack, CrewAI,
Agno, OpenAI Agents, and Model Context Protocol (MCP). Captures chain, retriever, agent, and tool spans alongside the
underlying LLM and vector-DB calls so multi-step workflows can be debugged end-to-end.
- aid: openllmetry:openllmetry-otlp-exporters
name: OpenLLMetry OTLP Exporters
tags:
- Exporters
- OTLP
- OpenTelemetry
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
humanURL: https://www.traceloop.com/docs/openllmetry/integrations/exporters
properties:
- url: https://www.traceloop.com/docs/openllmetry/integrations/exporters
type: Documentation
- url: https://www.traceloop.com/docs/openllmetry/integrations/datadog
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/grafana
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/honeycomb
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/newrelic
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/splunk
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/azureappinsights
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/gcp
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/langfuse
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/langsmith
type: Integrations
- url: https://www.traceloop.com/docs/openllmetry/integrations/braintrust
type: Integrations
description: OpenLLMetry emits standard OpenTelemetry traces and metrics over OTLP (gRPC or HTTP), so any OpenTelemetry-compatible
backend can receive its telemetry. Supported destinations include Datadog, Grafana Tempo/Loki, Honeycomb, New Relic, Splunk,
Dynatrace, Instana, Azure Application Insights, Google Cloud Trace, OCI APM, Highlight, Traceloop, Langfuse, LangSmith,
and Braintrust, as well as self-hosted OpenTelemetry Collectors.
common:
- type: Pricing
url: https://www.traceloop.com/pricing
- type: Plans
url: plans/openllmetry-plans-pricing.yml
- type: IssueTracker
url: https://github.com/traceloop/openllmetry/issues
- type: Releases
url: https://github.com/traceloop/openllmetry/releases
- type: SecurityPolicy
url: https://github.com/traceloop/openllmetry/blob/main/SECURITY.md
- type: CodeOfConduct
url: https://github.com/traceloop/openllmetry/blob/main/CODE_OF_CONDUCT.md
- type: ContributionGuide
url: https://github.com/traceloop/openllmetry/blob/main/CONTRIBUTING.md
- type: DomainSecurity
url: security/openllmetry-domain-security.yml
- type: Website
url: https://www.traceloop.com/openllmetry
- type: Documentation
url: https://www.traceloop.com/docs/openllmetry/introduction
- type: GitHubRepository
url: https://github.com/traceloop/openllmetry
- type: GitHubRepository
url: https://github.com/traceloop/openllmetry-js
- type: License
url: https://github.com/traceloop/openllmetry/blob/main/LICENSE
- type: Maintainer
url: https://www.traceloop.com/
- type: Discord
url: https://traceloop.com/slack
- type: Blog
url: https://www.traceloop.com/blog
- type: GettingStarted
url: https://www.traceloop.com/docs/openllmetry/quick-start/python
- type: Integrations
url: https://www.traceloop.com/docs/openllmetry/integrations
- type: SemanticConventions
url: https://opentelemetry.io/docs/specs/semconv/gen-ai/
- type: UsageTerms
url: terms/openllmetry-terms-of-service.yml
- type: DataLicense
url: data-license/openllmetry-data-license.yml
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com
include: []
x-parent: traceloop
x-relationship: product
OpenLLMetry API — frequently asked questions
Does OpenLLMetry have an API?
Yes. APIs.io lists 6 APIs from OpenLLMetry, including OpenLLMetry Traceloop SDK, OpenLLMetry Semantic Conventions for AI and OpenLLMetry LLM Provider Instrumentations, and 3 more.
How much does the OpenLLMetry API cost?
OpenLLMetry publishes its prices; its Free Forever plan is $0/ mo as of 2026-10-07. APIs.io lists 2 pricing plans for OpenLLMetry, with each plan's price, limits and inclusions under Pricing on this page.
Is the OpenLLMetry API ready for AI agents?
OpenLLMetry has a Kin Score of 28.8 out of 100 (thin) and an Agent Readiness score of 0.0 (human-only), scored by API Evangelist on 2026-11-13.
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
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.
Kin Score
How this is scored →
It updates itself when the score changes. Paste this where you link to your API docs: