OpenLLMetry logo

OpenLLMetry

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.

6 APIs 0 Features
AILLMObservabilityOpen SourceOpenTelemetryTracingGenAI

OpenLLMetry publishes 6 APIs on the APIs.io network. Tagged areas include AI, LLM, Observability, Open Source, and OpenTelemetry.

OpenLLMetry’s developer surface includes documentation, engineering blog, getting-started guide, and 7 more developer resources.

APIs

OpenLLMetry Traceloop SDK

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...

OpenLLMetry Semantic Conventions for AI

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...

OpenLLMetry LLM Provider Instrumentations

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 Vector Database Instrumentations

Instrumentations for vector databases used in retrieval-augmented generation pipelines — Chroma, Pinecone, Qdrant, Weaviate, LanceDB, Milvus, and Marqo. Captures query, upsert, ...

OpenLLMetry Framework and Agent Instrumentations

Instrumentations for higher-level LLM frameworks and agent runtimes — LangChain, LlamaIndex, Haystack, CrewAI, Agno, OpenAI Agents, and Model Context Protocol (MCP). Captures ch...

OpenLLMetry OTLP Exporters

OpenLLMetry emits standard OpenTelemetry traces and metrics over OTLP (gRPC or HTTP), so any OpenTelemetry-compatible backend can receive its telemetry. Supported destinations i...

Resources

🔗
Website
Website
🔗
Documentation
Documentation
👥
GitHubRepository
GitHubRepository
👥
GitHubRepository
GitHubRepository
🔗
License
License
🔗
Maintainer
Maintainer
🔗
Discord
Discord
📰
Blog
Blog
🚀
GettingStarted
GettingStarted
🔗
SemanticConventions
SemanticConventions

Sources

apis.yml Raw ↑ 
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.
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
- AI
- LLM
- Observability
- Open Source
- OpenTelemetry
- Tracing
- GenAI
created: '2026-05-25'
modified: '2026-05-25'
specificationVersion: '0.19'
apis:
- aid: openllmetry:openllmetry-traceloop-sdk
  name: OpenLLMetry Traceloop SDK
  tags:
  - SDK
  - Instrumentation
  - Tracing
  image: https://kinlane-productions.s3.amazonaws.com/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: SDK
  - url: https://www.npmjs.com/package/@traceloop/node-server-sdk
    type: SDK
  - 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
  - GenAI
  image: https://kinlane-productions.s3.amazonaws.com/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: SDK
  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-productions.s3.amazonaws.com/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: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-anthropic/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-bedrock/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-google-generativeai/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-cohere/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-mistralai/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-ollama/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-groq/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-together/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-replicate/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-vertexai/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-sagemaker/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-watsonx/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-alephalpha/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-transformers/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-voyageai/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-writer/
    type: SDK
  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 Databases
  - RAG
  image: https://kinlane-productions.s3.amazonaws.com/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: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-pinecone/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-qdrant/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-weaviate/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-lancedb/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-milvus/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-marqo/
    type: SDK
  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
  - Frameworks
  - Agents
  image: https://kinlane-productions.s3.amazonaws.com/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: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-llamaindex/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-haystack/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-crewai/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-agno/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-openai-agents/
    type: SDK
  - url: https://pypi.org/project/opentelemetry-instrumentation-mcp/
    type: SDK
  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-productions.s3.amazonaws.com/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: 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/
maintainers:
- FN: Kin Lane
  email: [email protected]
include: []