# Awesome Agent Observability

> A neutral list of resources for observing AI agents: standards, instrumentation, frameworks, platforms, gateways, evaluation, cost, safety signals, and on-chain agents and payments, with an OpenTelemetry focus.

Every entry is one YAML file in entries/. All fields, including OTel support with an evidence link, license and repository metadata, are in https://raw.githubusercontent.com/selimaytac/awesome-agent-observability/main/entries.json.

To choose a tool, filter entries.json by `category`, `tags`, `otlp`, `conventions`, `telemetry`, `license`, `hosting`, `languages` and `agent_types`, and skip entries with `historical_section: true`. A missing or `unknown` value means not confirmed, not no. Each OTel claim links its evidence in `otel_evidence` or `telemetry_docs`. Order is alphabetical and says nothing about quality.

## Standards and specifications

- [A2A distributed tracing proposal](https://github.com/a2aproject/A2A/issues/2103): Open proposal in the A2A repository for semantic conventions and W3C Trace Context propagation between delegating agents.
- [A2A Protocol](https://github.com/a2aproject/A2A): Specification of the Agent2Agent protocol for communication between agents, relevant to propagating context between them.
- [A2A protocol documentation](https://a2a-protocol.org/latest/): Documentation site of the Agent2Agent protocol.
- [GenAI semantic conventions for agentic systems (issue 35)](https://github.com/open-telemetry/semantic-conventions-genai/issues/35): Tracking issue for agentic system conventions in OpenTelemetry GenAI.
- [MCP specification release candidate 2026-07-28](https://blog.modelcontextprotocol.io/posts/2026-07-28-release-candidate/): Announcement of the MCP release candidate, which includes trace context propagation (SEP-414) and OpenTelemetry-compatible telemetry.
- [Model Context Protocol specification](https://modelcontextprotocol.io/specification/): Specification of the protocol that connects agents to tools and data sources.
- [OpenInference specification](https://arize-ai.github.io/openinference/spec/): Semantic conventions for tracing LLM, retriever, tool and agent steps on top of OpenTelemetry.
- [OpenTelemetry GenAI agent spans](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-agent-spans/): Semantic conventions for spans that describe agent creation and invocation.
- [OpenTelemetry GenAI Anthropic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/anthropic/): Provider-specific attributes for Anthropic calls within the GenAI conventions.
- [OpenTelemetry GenAI attribute registry](https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/): Reference list of the `gen_ai.*` attribute names and their types.
- [OpenTelemetry GenAI events](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-events/): Semantic conventions for events that carry prompts and completions.
- [OpenTelemetry GenAI MCP conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/mcp/): Semantic conventions for Model Context Protocol operations.
- [OpenTelemetry GenAI metrics](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-metrics/): Semantic conventions for token usage and operation duration metrics.
- [OpenTelemetry GenAI OpenAI conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/openai/): Provider-specific attributes for OpenAI calls within the GenAI conventions.
- [OpenTelemetry GenAI semantic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/): Entry page of the conventions for generative AI spans, metrics and events.
- [OpenTelemetry GenAI spans](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-spans/): Semantic conventions for spans that describe model calls.
- [OpenTelemetry JSON-RPC conventions](https://opentelemetry.io/docs/specs/semconv/rpc/json-rpc/): Semantic conventions for JSON-RPC calls, the transport of MCP and of blockchain nodes.
- [OpenTelemetry Protocol (OTLP)](https://opentelemetry.io/docs/specs/otlp/): Specification of the wire protocol for traces, metrics and logs.
- [OpenTelemetry semantic conventions repository](https://github.com/open-telemetry/semantic-conventions): Source repository of all semantic conventions, including the GenAI ones.
- [OpenTelemetry semantic-conventions-genai repository](https://github.com/open-telemetry/semantic-conventions-genai): Repository of the OpenTelemetry semantic conventions for generative AI: spans, metrics, events, MCP and provider conventions.
- [OpenTelemetry Weaver](https://github.com/open-telemetry/weaver): Tool for defining, validating and evolving telemetry schemas built on semantic conventions, with a live check of OTLP data.
- [SEP-414: OpenTelemetry trace context in MCP](https://modelcontextprotocol.io/seps/414-request-meta): MCP proposal that defines traceparent, tracestate and baggage keys in the request metadata for W3C Trace Context propagation.
- [W3C Baggage](https://www.w3.org/TR/baggage/): Specification for propagating application key-value pairs across service boundaries.
- [W3C Trace Context](https://www.w3.org/TR/trace-context/): Specification of the `traceparent` and `tracestate` headers used to correlate distributed traces.
- [W3C Trace Context Level 2](https://www.w3.org/TR/trace-context-2/): Newer level of the Trace Context specification.

## Instrumentation

- [Arize OTel Python helper](https://github.com/Arize-ai/arize-otel-python): Python helper that registers OpenTelemetry export to Arize with OpenInference.
- [AWS Distro for OpenTelemetry Python instrumentation](https://github.com/aws-observability/aws-otel-python-instrumentation): Python auto-instrumentation distribution from AWS with generative AI instrumentation.
- [Axiom AI SDK](https://github.com/axiomhq/ai): TypeScript SDK from Axiom for instrumenting and evaluating AI applications.
- [Elastic Distribution of OpenTelemetry Python](https://github.com/elastic/elastic-otel-python): Python distribution of OpenTelemetry maintained by Elastic.
- [Galileo Python SDK](https://github.com/rungalileo/galileo-python): Python package that sends traces of LLM applications and agents to a Galileo log stream.
- [HoneyHive Python SDK](https://github.com/honeyhiveai/python-sdk): Python SDK for HoneyHive tracing built on OpenTelemetry.
- [Langfuse JS/TS SDK](https://github.com/langfuse/langfuse-js): JavaScript client for sending traces to Langfuse, built on OpenTelemetry.
- [Langfuse Python SDK](https://github.com/langfuse/langfuse-python): Python client and decorators for sending traces to Langfuse, built on OpenTelemetry.
- [Logfire](https://github.com/pydantic/logfire): SDK that sends OpenTelemetry traces and metrics, with integrations for LLM clients and agent frameworks.
- [Maxim Python SDK](https://github.com/maximhq/maxim-py): Python SDK for Maxim tracing and evaluation.
- [Microsoft.Extensions.AI libraries](https://learn.microsoft.com/en-us/dotnet/ai/microsoft-extensions-ai): Documents .NET AI abstractions that include OpenTelemetry middleware for chat clients.
- [Monocle](https://github.com/monocle2ai/monocle): Python library that traces GenAI apps and agents with automatic instrumentation and exports spans over OTLP, with an optional GenAI semantic conventions mode.
- [New Relic OpenTelemetry examples](https://github.com/newrelic/newrelic-opentelemetry-examples): Examples for sending OpenTelemetry data to New Relic.
- [OpenInference](https://github.com/Arize-ai/openinference): Instrumentation packages for LLM clients and agent frameworks that follow the OpenInference conventions.
- [OpenLIT](https://github.com/openlit/openlit): SDK and tooling that instruments LLM calls and agents and exports OpenTelemetry data.
- [OpenLLMetry](https://github.com/traceloop/openllmetry): Python instrumentation for LLM clients, vector databases and frameworks on top of OpenTelemetry.
- [OpenLLMetry for Go](https://github.com/traceloop/go-openllmetry): Go counterpart of OpenLLMetry.
- [OpenLLMetry for JavaScript](https://github.com/traceloop/openllmetry-js): JavaScript and TypeScript counterpart of OpenLLMetry.
- [OpenLLMetry Ruby](https://github.com/traceloop/openllmetry-ruby): Ruby sibling of OpenLLMetry for tracing LLM applications.
- [OpenTelemetry .NET](https://github.com/open-telemetry/opentelemetry-dotnet): OpenTelemetry SDK and API for .NET.
- [OpenTelemetry contrib GenAI utilities for JavaScript](https://github.com/open-telemetry/opentelemetry-js-contrib/tree/main/packages/genai-util): Shared helpers for GenAI instrumentations in the JavaScript contrib repository.
- [OpenTelemetry contrib OpenAI instrumentation for JavaScript](https://github.com/open-telemetry/opentelemetry-js-contrib/tree/main/packages/instrumentation-openai): Instrumentation of the OpenAI client library for Node.js.
- [OpenTelemetry eBPF instrumentation](https://github.com/open-telemetry/opentelemetry-ebpf-instrumentation): Zero-code instrumentation of HTTP and gRPC services through eBPF.
- [OpenTelemetry GenAI OpenAI Agents instrumentation for Python](https://github.com/open-telemetry/opentelemetry-python-genai/tree/main/instrumentation/opentelemetry-instrumentation-genai-openai-agents): Instrumentation of the OpenAI Agents SDK following the GenAI conventions; replaces the deprecated contrib package openai-agents-v2.
- [OpenTelemetry GenAI OpenAI instrumentation for Python](https://github.com/open-telemetry/opentelemetry-python-genai/tree/main/instrumentation/opentelemetry-instrumentation-genai-openai): Instrumentation of the OpenAI client library following the GenAI conventions; replaces the deprecated contrib package openai-v2.
- [OpenTelemetry Go](https://github.com/open-telemetry/opentelemetry-go): OpenTelemetry SDK and API for Go.
- [OpenTelemetry Java](https://github.com/open-telemetry/opentelemetry-java): OpenTelemetry SDK and API for Java.
- [OpenTelemetry Java instrumentation](https://github.com/open-telemetry/opentelemetry-java-instrumentation): Java agent and libraries that instrument applications without code changes.
- [OpenTelemetry Java instrumentation: OpenAI](https://github.com/open-telemetry/opentelemetry-java-instrumentation/tree/main/instrumentation/openai): Java instrumentation folder for OpenAI client libraries.
- [OpenTelemetry JavaScript](https://github.com/open-telemetry/opentelemetry-js): OpenTelemetry SDK and API for JavaScript and TypeScript.
- [OpenTelemetry JavaScript contrib](https://github.com/open-telemetry/opentelemetry-js-contrib): Community instrumentations for the JavaScript SDK.
- [OpenTelemetry Python](https://github.com/open-telemetry/opentelemetry-python): OpenTelemetry SDK and API for Python.
- [OpenTelemetry Python contrib](https://github.com/open-telemetry/opentelemetry-python-contrib): Community instrumentations for the Python SDK, including a GenAI directory.
- [OpenTelemetry Python GenAI instrumentations](https://github.com/open-telemetry/opentelemetry-python-genai): Repository of the OpenTelemetry instrumentation packages for generative AI client libraries and agent frameworks in Python.
- [OpenTelemetry Python GenAI utilities](https://github.com/open-telemetry/opentelemetry-python-genai/tree/main/util/opentelemetry-util-genai): Shared utilities for Python GenAI instrumentations.
- [opentelemetry-hooks](https://github.com/o11y-dev/opentelemetry-hooks): Hooks that record activity of several coding agents as OpenTelemetry data.
- [Splunk OpenTelemetry Python distribution](https://github.com/signalfx/splunk-otel-python): Splunk distribution of OpenTelemetry Python, used to instrument agent applications for Splunk Observability Cloud.

## Agent frameworks

- [AG2](https://github.com/ag2ai/ag2): Multi-agent framework whose classic API derives from AutoGen, with OpenTelemetry tracing that follows the GenAI agent span conventions.
- [AgentScope](https://github.com/agentscope-ai/agentscope): Multi-agent framework in Python with OpenTelemetry-based tracing sent to a collector or compatible backend.
- [Agno](https://github.com/agno-agi/agno): Python framework for agents and multi-agent teams that traces runs with OpenTelemetry through the OpenInference instrumentation.
- [AutoGen](https://github.com/microsoft/autogen): Microsoft multi-agent framework whose tracing is built on OpenTelemetry and follows its semantic conventions for agents and tools.
- [BeeAI Framework](https://github.com/i-am-bee/beeai-framework): Framework for building agents in Python and TypeScript, traced in Python through an OpenInference instrumentor.
- [Claude Code monitoring](https://code.claude.com/docs/en/monitoring-usage): Documentation of the OpenTelemetry metrics and events that the Claude Code terminal agent exports.
- [Cline](https://github.com/cline/cline): Open source coding agent for the editor, with telemetry and OpenTelemetry export documented for enterprise setups.
- [CrewAI](https://github.com/crewAIInc/crewAI): Multi-agent framework in Python whose built-in tracing exports OpenTelemetry spans, with integrations for other tracing tools.
- [Dify](https://github.com/langgenius/dify): Platform for agentic workflows with integrations to tracing backends such as Opik, Langfuse and Arize Phoenix.
- [DSPy](https://github.com/stanfordnlp/dspy): Python framework for programming language model pipelines, with a callback interface for custom logging and tracing through MLflow autolog.
- [Embabel](https://github.com/embabel/embabel-agent): JVM agent framework whose user guide documents observation of its services through Micrometer.
- [Gemini CLI telemetry](https://geminicli.com/docs/cli/telemetry/): Documentation of the OpenTelemetry traces, metrics and logs of the Gemini CLI terminal agent, with GenAI conventions.
- [Genkit](https://github.com/genkit-ai/genkit): Framework for AI-powered applications that collects traces and metrics through OpenTelemetry instrumentation.
- [GitHub Copilot OpenTelemetry monitoring](https://docs.github.com/en/copilot/concepts/enterprise/opentelemetry): GitHub documentation on sending OpenTelemetry data from Copilot clients to an OTLP-compatible backend.
- [Google Agent Development Kit for JavaScript](https://github.com/google/adk-js): Agent framework for JavaScript and TypeScript with an OpenTelemetry telemetry setup in its core package.
- [Google Agent Development Kit for Python](https://github.com/google/adk-python): Agent framework in Python whose traces implement the OpenTelemetry semantic conventions for GenAI.
- [GPT Researcher](https://github.com/assafelovic/gpt-researcher): Autonomous research agent whose README documents tracing of its workflows with LangSmith.
- [Haystack](https://github.com/deepset-ai/haystack): Framework for pipelines and agents with tracing through OpenTelemetry, Datadog, Langfuse and other backends.
- [Inngest AgentKit](https://github.com/inngest/agent-kit): TypeScript toolkit for agent networks with durable execution.
- [kagent](https://github.com/kagent-dev/kagent): Kubernetes-native framework for running agents, with OpenTelemetry tracing of agent, model and tool execution.
- [LangChain](https://github.com/langchain-ai/langchain): Framework for LLM applications whose callbacks send traces to LangSmith and other tools.
- [LangChain.js](https://github.com/langchain-ai/langchainjs): JavaScript and TypeScript version of LangChain.
- [LangChain4j](https://github.com/langchain4j/langchain4j): Java library for LLM applications with observability listeners that follow the GenAI conventions, and Micrometer metrics.
- [LangGraph](https://github.com/langchain-ai/langgraph): Library for stateful agent graphs; traces go to LangSmith.
- [LiveKit Agents](https://docs.livekit.io/testing/observability/tracing/): Framework for voice agents whose documentation describes OpenTelemetry traces per session, exportable to any OTLP backend.
- [LlamaIndex](https://github.com/run-llama/llama_index): Data and agent framework with its own instrumentation module and integrations that include OpenTelemetry.
- [Mastra](https://github.com/mastra-ai/mastra): TypeScript agent framework with its own tracing and exporters for Langfuse, Datadog and OpenTelemetry-compatible platforms.
- [Microsoft Agent Framework](https://github.com/microsoft/agent-framework): Microsoft framework for building agents in .NET and Python that emits traces, logs and metrics per the OpenTelemetry GenAI conventions.
- [NVIDIA NeMo Agent Toolkit](https://github.com/NVIDIA/NeMo-Agent-Toolkit): Open source library for connecting and profiling teams of agents, with OpenTelemetry-based observability.
- [Open WebUI](https://github.com/open-webui/open-webui): Self-hosted chat interface for language models with documented OpenTelemetry trace and metric export over OTLP.
- [OpenAI Agents SDK for JavaScript](https://github.com/openai/openai-agents-js): OpenAI agent SDK for TypeScript with built-in tracing in its own trace format and processors for other destinations.
- [OpenAI Agents SDK for Python](https://github.com/openai/openai-agents-python): OpenAI agent SDK; tracing uses its own trace format, with processors that can export elsewhere.
- [OpenAI Codex telemetry](https://developers.openai.com/codex/config-advanced): Documentation of the opt-in OpenTelemetry log export of the Codex terminal coding agent.
- [OpenClaw](https://github.com/openclaw/openclaw): Personal AI assistant whose Gateway exports metrics, traces and logs over OTLP/HTTP through a diagnostics plugin.
- [Pipecat](https://github.com/pipecat-ai/pipecat): Framework for voice and multimodal agents with OpenTelemetry tracing of conversational pipelines.
- [Pydantic AI](https://github.com/pydantic/pydantic-ai): Python agent framework that emits OpenTelemetry data per the GenAI conventions and documents Logfire as one backend.
- [Quarkus LangChain4j](https://github.com/quarkiverse/quarkus-langchain4j): Quarkus extension for LangChain4j, with an observability guide that covers tracing and metrics.
- [Rasa](https://github.com/RasaHQ/rasa): Framework for text and voice assistants whose documentation covers OpenTelemetry tracing of messages, actions and LLM calls.
- [Rig](https://github.com/0xPlaygrounds/rig): Rust library for LLM applications with tracing that is compatible with OpenTelemetry.
- [Semantic Kernel](https://github.com/microsoft/semantic-kernel): Microsoft SDK for agents that emits logs, metrics and traces following the OpenTelemetry semantic conventions.
- [smolagents](https://github.com/huggingface/smolagents): Hugging Face library for code-writing agents, traced with OpenTelemetry through the OpenInference instrumentation.
- [Spring AI](https://github.com/spring-projects/spring-ai): Spring framework for AI applications, with Micrometer observations that follow the GenAI conventions.
- [Strands Agents SDK](https://github.com/strands-agents/harness-sdk): Agent SDK from AWS for Python and TypeScript whose traces use OpenTelemetry and the GenAI attribute names.
- [Temporal Python SDK](https://github.com/temporalio/sdk-python): Python SDK for durable workflows, with OpenTelemetry tracing for workflows that often run long-lived agents.
- [Temporal TypeScript SDK](https://github.com/temporalio/sdk-typescript): TypeScript SDK for durable workflows, with OpenTelemetry interceptors for tracing.
- [Vercel AI SDK](https://github.com/vercel/ai): TypeScript toolkit whose telemetry option emits OpenTelemetry spans with GenAI attributes.
- [VoltAgent](https://github.com/VoltAgent/voltagent): TypeScript agent framework with tracing in its own VoltOps observability platform.

## Agent protocols and tool servers

- [A2A enterprise features](https://a2a-protocol.org/latest/topics/enterprise-ready/): Page of the A2A documentation that covers tracing, monitoring and auditing for agents that use the protocol.
- [A2A Java SDK](https://github.com/a2aproject/a2a-java): Official Java SDK for the A2A protocol, with an OpenTelemetry module for tracing and context propagation in servers and clients.
- [A2A Python SDK](https://github.com/a2aproject/a2a-python): Python library for building A2A clients and servers, with optional OpenTelemetry tracing.
- [AG-UI](https://github.com/ag-ui-protocol/ag-ui): Agent-user interaction protocol with Python, TypeScript and .NET SDKs, where the .NET SDK emits OpenTelemetry spans for each run.
- [Datadog MCP server](https://docs.datadoghq.com/mcp_server/): Managed MCP server that lets agents query logs, metrics, traces and incidents in Datadog.
- [FastMCP](https://github.com/PrefectHQ/fastmcp): Python framework for MCP servers and clients with documented OpenTelemetry tracing.
- [Last9 MCP server](https://github.com/last9/last9-mcp-server): MCP server that lets agents query Last9 telemetry such as logs, traces and metrics.
- [mcp-grafana](https://github.com/grafana/mcp-grafana): MCP server that gives agents access to Grafana dashboards, data sources and alerts.
- [mcp-otel](https://github.com/studiomeyer-io/mcp-otel): Library that reads W3C Trace Context from the MCP request metadata and emits OpenTelemetry spans for MCP servers.
- [Model Context Protocol C# SDK](https://github.com/modelcontextprotocol/csharp-sdk): Official C# SDK for MCP clients and servers, with a sample that configures OpenTelemetry for MCP operations.
- [Model Context Protocol Python SDK](https://github.com/modelcontextprotocol/python-sdk): Python SDK for MCP servers and clients.
- [Model Context Protocol TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk): TypeScript SDK for MCP servers and clients.
- [OpenTelemetry MCP server (Traceloop)](https://github.com/traceloop/opentelemetry-mcp-server): MCP server that lets agents search and read traces stored in Jaeger, Tempo or Traceloop.
- [SigNoz MCP server](https://github.com/SigNoz/signoz-mcp-server): MCP server that lets agents query SigNoz telemetry.

## Collectors and pipelines

- [Bindplane OpenTelemetry Collector](https://github.com/observIQ/bindplane-otel-collector): Bindplane build of the OpenTelemetry Collector that can be managed remotely through the OpAMP protocol.
- [Dynatrace OpenTelemetry Collector](https://github.com/Dynatrace/dynatrace-otel-collector): Collector distribution for sending OpenTelemetry data to Dynatrace.
- [Fluent Bit](https://github.com/fluent/fluent-bit): Telemetry agent that collects and routes logs, metrics and traces, with plugins that read and write OpenTelemetry data.
- [Grafana Alloy](https://github.com/grafana/alloy): Grafana distribution of the OpenTelemetry Collector that also runs Prometheus-style pipelines for metrics, logs, traces and profiles.
- [OpenTelemetry Collector](https://github.com/open-telemetry/opentelemetry-collector): Vendor-neutral agent for receiving, processing and exporting telemetry.
- [OpenTelemetry Collector Contrib](https://github.com/open-telemetry/opentelemetry-collector-contrib): Community receivers, processors and exporters for the Collector.
- [OpenTelemetry Operations for Python (Google Cloud exporters)](https://github.com/GoogleCloudPlatform/opentelemetry-operations-python): OpenTelemetry Python exporters for Cloud Monitoring and Cloud Trace.
- [OpenTelemetry redaction processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/redactionprocessor): Collector processor that removes attributes not on an allowed list and masks values that match a blocked list.
- [OpenTelemetry span metrics connector](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/connector/spanmetricsconnector): Collector connector that aggregates spans into request, error and duration metrics.
- [OpenTelemetry tail sampling processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/tailsamplingprocessor): Collector processor that decides which traces to keep after seeing whole traces, by policies such as errors or latency.
- [OpenTelemetry transform processor](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/processor/transformprocessor): Collector processor that modifies telemetry with OpenTelemetry Transformation Language statements.
- [Refinery](https://github.com/honeycombio/refinery): Sampling proxy that buffers all spans of a trace and then keeps or drops the trace as a whole.
- [Vector](https://github.com/vectordotdev/vector): Observability data pipeline for logs, metrics and traces, with an OpenTelemetry source and sink.

## Platforms

- [Agenta](https://github.com/Agenta-AI/agenta): Workspace for building, evaluating and observing LLM applications.
- [AgentOps](https://github.com/AgentOps-AI/agentops): Python SDK and platform for session replay, cost and tracing of agents.
- [Arize AX](https://docs.arize.com/ax): Hosted platform from Arize for tracing and evaluating LLM applications.
- [Arize Phoenix](https://github.com/Arize-ai/phoenix): Self-hostable tracing and evaluation tool that ingests OpenInference traces over OTLP.
- [Braintrust](https://www.braintrust.dev/docs/guides/traces): Hosted platform for logging traces, evaluating and monitoring LLM applications, with an open source JavaScript SDK.
- [Databricks: MLflow tracing overview](https://docs.databricks.com/aws/en/mlflow3/genai/tracing/): Documents MLflow tracing on Databricks for generative AI applications and agents.
- [Evidently](https://github.com/evidentlyai/evidently): Framework to evaluate and monitor LLM apps and ML systems, with a trace store and viewer that receives OpenTelemetry traces over OTLP.
- [Fiddler documentation](https://docs.fiddler.ai/): Documentation of Fiddler, a platform for monitoring and governing agents and models.
- [Galileo documentation](https://docs.galileo.ai/): Documentation of Galileo, a platform for evaluating and monitoring agents, with OpenTelemetry ingest.
- [Helicone](https://github.com/Helicone/helicone): Platform for logging requests, cost and sessions of LLM applications.
- [HoneyHive documentation](https://docs.honeyhive.ai/): Documentation of HoneyHive, a platform for tracing and evaluating agents with OpenTelemetry support.
- [Laminar](https://github.com/lmnr-ai/lmnr): Self-hostable agent observability platform with an OpenTelemetry-native SDK that instruments common LLM frameworks.
- [Langfuse](https://github.com/langfuse/langfuse): Self-hostable platform for traces, prompts and evaluations, with an OpenTelemetry endpoint.
- [LangSmith](https://docs.langchain.com/langsmith/home): Hosted platform from LangChain for tracing and evaluating LLM applications, with OpenTelemetry trace ingestion.
- [Langtrace](https://github.com/Scale3-Labs/langtrace): Tool that records OpenTelemetry traces of LLM calls, vector database queries and framework operations in LLM applications.
- [LangWatch](https://github.com/langwatch/langwatch): Platform for tracing, evaluating and simulating agents.
- [Latitude](https://github.com/latitude-dev/latitude-llm): Agent observability platform that groups failing traces into tracked signals and replays fixes against them.
- [Lunary](https://lunary.ai/docs): Hosted platform documentation for monitoring LLM applications, with a JavaScript SDK.
- [Maxim documentation](https://www.getmaxim.ai/docs): Documentation of Maxim, a platform for evaluating and observing agents.
- [MLflow Tracing](https://mlflow.org/docs/latest/genai/tracing/): Tracing feature of MLflow for LLM applications and agents, compatible with OpenTelemetry and the GenAI conventions.
- [Opik](https://github.com/comet-ml/opik): Platform for tracing, evaluating and monitoring LLM applications and agents.
- [Snowflake AI Observability with Cortex](https://docs.snowflake.com/en/user-guide/snowflake-cortex/ai-observability): Documents Snowflake tracing and evaluation of generative AI applications.
- [Traceloop](https://www.traceloop.com/docs): Hosted platform from the OpenLLMetry maintainers for monitoring LLM applications.
- [Weights & Biases Weave](https://github.com/wandb/weave): Toolkit for tracing and evaluating LLM applications.
- [Axiom LLM observability](https://axiom.co/docs/use-cases/llm-observability): Documents Axiom tracing of LLM and agent applications with OpenTelemetry.
- [Coralogix AI observability](https://coralogix.com/platform/ai-observability/): Product page for Coralogix monitoring of AI applications and agents.
- [Datadog LLM Observability](https://docs.datadoghq.com/llm_observability/): Hosted product for tracing and monitoring LLM applications and agents, which also accepts OpenTelemetry GenAI instrumentation.
- [Dynatrace AI observability](https://docs.dynatrace.com/docs/observe/dynatrace-for-ai-observability): Hosted product documentation for observing AI workloads, with OpenTelemetry ingestion through OpenInference or GenAI conventions.
- [Elastic LLM observability](https://www.elastic.co/observability/llm-monitoring): Elastic Observability features for monitoring LLM applications, with OpenTelemetry support through the Elastic distributions (EDOT).
- [GenAI Observability for Splunk](https://splunkbase.splunk.com/app/8308): Splunkbase app with dashboards for tokens, latency, cost and errors of generative AI workloads.
- [Grafana Cloud AI Observability](https://grafana.com/docs/grafana-cloud/monitor-applications/ai-observability/): Documents Grafana Cloud AI observability dashboards built on OpenLIT instrumentation and OpenTelemetry data.
- [Grafana Cloud Claude Code integration](https://grafana.com/docs/grafana-cloud/monitor-infrastructure/integrations/integration-reference/integration-claude-code): Documents the prebuilt Grafana Cloud integration that receives coding agent telemetry over OTLP.
- [Honeycomb](https://docs.honeycomb.io/send-data/opentelemetry/): Hosted observability product that ingests OpenTelemetry data.
- [Honeycomb AI and LLM observability](https://www.honeycomb.io/use-cases/ai-llm-observability): Product page for Honeycomb tracing of LLM applications and agents.
- [IBM Instana Observability](https://www.ibm.com/products/instana): Product page of IBM Instana, an APM platform with OpenTelemetry ingest and generative AI monitoring.
- [Last9 documentation](https://last9.io/docs/): Documentation of Last9, an observability platform that ingests OpenTelemetry data.
- [New Relic AI monitoring](https://docs.newrelic.com/docs/ai-monitoring/intro-to-ai-monitoring/): Hosted product documentation for monitoring AI applications.
- [Salesforce Agentforce Observability](https://www.salesforce.com/agentforce/observability/): Product page for observability of Agentforce agents.
- [Sentry AI agent monitoring](https://docs.sentry.io/product/insights/ai/agents/): Hosted product documentation for monitoring agent runs and tool calls.
- [SigNoz](https://github.com/SigNoz/signoz): OpenTelemetry-native observability platform with guides for monitoring LLM applications.
- [Splunk AI Agent Monitoring](https://help.splunk.com/en/splunk-observability-cloud/observability-for-ai/splunk-ai-agent-monitoring): Documents Splunk Observability Cloud views for AI agents, built on OpenTelemetry GenAI data.
- [Claude Code Grafana dashboard (Application Insights)](https://grafana.com/grafana/dashboards/25052-claude-code/): Community Grafana dashboard that reads coding agent telemetry from Azure Application Insights.
- [Claude Code Metrics (Prometheus) Grafana dashboard](https://grafana.com/grafana/dashboards/25255-claude-code-metrics-prometheus/): Community Grafana dashboard for coding agent usage metrics on Prometheus-compatible backends.
- [claude-code-metrics-prometheus](https://github.com/rockdarko/claude-code-metrics-prometheus): Grafana dashboard that reads OpenTelemetry metrics of a coding agent from Prometheus-compatible stores.
- [claude-otel](https://github.com/li0nel/claude-otel): Configuration for sending a coding agent's OpenTelemetry metrics to Grafana Cloud, with a dashboard of cost and tokens per session.
- [Grafana](https://github.com/grafana/grafana): Dashboard and query front end used with Tempo, Prometheus and Loki.
- [Grafana Tempo](https://grafana.com/docs/tempo/latest/): Distributed tracing backend that accepts OTLP.
- [Jaeger](https://github.com/jaegertracing/jaeger): Open source distributed tracing backend that accepts OTLP.
- [OpenObserve](https://github.com/openobserve/openobserve): Self-hostable backend that stores and queries logs, metrics and traces, with native OTLP ingestion.
- [Prometheus](https://github.com/prometheus/prometheus): Metrics database commonly used for GenAI metrics.
- [Uptrace](https://github.com/uptrace/uptrace): Self-hostable APM that collects data with OpenTelemetry and keeps traces, metrics and logs in ClickHouse.
- [Amazon Bedrock AgentCore observability](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/observability.html): Observability of agents run on Amazon Bedrock AgentCore, with telemetry in an OpenTelemetry-compatible format.
- [Amazon Bedrock AgentCore Observability, configure](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/observability-configure.html): Describes how to configure observability for AgentCore runtimes and for agents hosted outside AgentCore.
- [Amazon Bedrock AgentCore Observability, get started](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/observability-get-started.html): Explains how to enable AgentCore observability for agents and send their telemetry to CloudWatch.
- [Amazon CloudWatch generative AI observability](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/GenAI-observability.html): Documents CloudWatch views for latency, usage and errors, and prompt tracing across models and agents.
- [AWS Distro for OpenTelemetry](https://aws-otel.github.io/docs/introduction/): AWS-supported distribution of OpenTelemetry components that sends traces and metrics to AWS services and other backends.
- [Azure Monitor: enable OpenTelemetry in Application Insights](https://learn.microsoft.com/en-us/azure/azure-monitor/app/opentelemetry-enable): Explains the Azure Monitor OpenTelemetry distro that sends application telemetry to Application Insights.
- [Azure Monitor: monitor AI agents with Application Insights](https://learn.microsoft.com/en-us/azure/azure-monitor/app/agents-view): Describes the Application Insights agents view for performance, token usage and errors of agents.
- [Google Cloud Observability for AI agent developers](https://docs.cloud.google.com/stackdriver/docs/instrumentation/ai-agent-overview): Overview of instrumenting agents built with frameworks such as ADK and LangGraph and viewing them in Cloud Observability.
- [Google Cloud Trace overview](https://docs.cloud.google.com/trace/docs/overview): Describes Cloud Trace, the distributed tracing backend that accepts OpenTelemetry data from agents on Google Cloud.
- [Google Cloud: trace an agent (Agent Engine runtime)](https://docs.cloud.google.com/agent-builder/agent-engine/manage/tracing): Explains how to enable Cloud Trace on deployed agents and read traces of tool calls and model requests.
- [Microsoft Copilot Studio analytics overview](https://learn.microsoft.com/en-us/microsoft-copilot-studio/analytics-overview): Documents analytics and monitoring views for agents built in Copilot Studio.
- [Microsoft Foundry tracing](https://learn.microsoft.com/en-us/azure/foundry/observability/concepts/trace-agent-concept): Tracing of agents and applications in Microsoft Foundry (formerly Azure AI Foundry), built on OpenTelemetry.
- [BentoML](https://github.com/bentoml/BentoML): Python framework for serving models and AI services, with documented OpenTelemetry tracing and OTLP export.
- [KServe](https://github.com/kserve/kserve): Kubernetes inference platform with a Prometheus monitoring guide and an OpenTelemetry-based JSON log profile.
- [llama.cpp server](https://github.com/ggml-org/llama.cpp/tree/master/tools/server): HTTP server of llama.cpp with an optional Prometheus-compatible metrics endpoint enabled by a command-line flag.
- [llm-d](https://github.com/llm-d/llm-d): Kubernetes inference stack whose operations guide covers Prometheus metrics, Grafana dashboards and OpenTelemetry distributed tracing.
- [LMDeploy](https://github.com/InternLM/lmdeploy): Toolkit for deploying and serving language models that exposes Prometheus metrics, with a bundled Grafana setup.
- [NVIDIA Dynamo](https://github.com/ai-dynamo/dynamo): Distributed inference serving framework whose Kubernetes guide covers Prometheus metrics and an OTLP collector endpoint for traces.
- [SGLang](https://github.com/sgl-project/sglang): Serving framework for language models, with Prometheus production metrics documented.
- [Triton Inference Server](https://github.com/triton-inference-server/server): Inference server that exposes Prometheus metrics and can emit request traces through OpenTelemetry.
- [vLLM](https://github.com/vllm-project/vllm): Inference and serving engine for language models, with Prometheus production metrics documented.

## Gateways and proxies

- [Agent Router](https://github.com/theagentrouter/agent-router): Control plane for AI and agent traffic built on Envoy Gateway, formerly named Envoy AI Gateway.
- [agentgateway](https://github.com/agentgateway/agentgateway): Proxy for agent, MCP and LLM traffic, with tracing and metrics documented.
- [Azure API Management AI gateway capabilities](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities): Lists API Management features for LLM endpoints, including token metrics, logging and monitoring.
- [Bifrost](https://github.com/maximhq/bifrost): AI gateway that also works as an MCP gateway, with Prometheus metrics, distributed tracing and logging.
- [Cloudflare AI Gateway](https://developers.cloudflare.com/ai-gateway/observability/): Hosted gateway whose documentation covers request logging, analytics, costs and an OpenTelemetry integration.
- [Databricks AI Gateway](https://docs.databricks.com/aws/en/ai-gateway/): Documents the Databricks gateway for governing model, MCP and coding agent traffic.
- [Envoy Gateway](https://github.com/envoyproxy/gateway): Gateway project that the Envoy AI Gateway builds on.
- [Helicone AI Gateway](https://github.com/Helicone/ai-gateway): Open source gateway for routing LLM requests, with OpenTelemetry support for logs, metrics and traces.
- [IBM ContextForge](https://github.com/IBM/mcp-context-forge): Gateway that fronts MCP, A2A and REST tools, with documented tracing and metrics.
- [Kong AI Gateway](https://docs.konghq.com/gateway/latest/ai-gateway/): AI traffic features of Kong Gateway, with the AI Proxy plugin documented separately.
- [LiteLLM](https://docs.litellm.ai/docs/observability/opentelemetry_integration): Python SDK and proxy server with one API for many model providers, including an OpenTelemetry callback for traces.
- [OpenRouter broadcast](https://openrouter.ai/docs/guides/features/broadcast): Hosted router that can forward traces of requests to observability tools, including an OpenTelemetry Collector.
- [Portkey AI Gateway](https://github.com/Portkey-AI/gateway): Gateway that routes requests to many providers, with request logging in the hosted product.
- [Traceloop Hub](https://github.com/traceloop/hub): Rust gateway in front of LLM providers that emits OpenTelemetry traces and Prometheus metrics for each request.
- [Vercel AI Gateway](https://vercel.com/docs/ai-gateway): Hosted gateway for model access with usage and cost reporting.

## Evaluation and testing

- [Braintrust autoevals](https://github.com/braintrustdata/autoevals): Library of evaluation scorers that works with Braintrust logging.
- [DeepEval](https://github.com/confident-ai/deepeval): Evaluation framework with tracing of LLM applications and an OpenTelemetry integration.
- [Inspect AI](https://github.com/UKGovernmentBEIS/inspect_ai): Evaluation framework for models and agents, with trace logging for debugging evaluation runs.
- [Opik evaluation](https://www.comet.com/docs/opik/): Documentation of the evaluation features that run on traced data in Opik.
- [promptfoo](https://github.com/promptfoo/promptfoo): Test and red-team tool for prompts and agents that reads OpenTelemetry (OTLP) traces of the application under test.
- [Ragas](https://github.com/vibrantlabsai/ragas): Python library of evaluation metrics for LLM applications that can score traces collected in tools such as Langfuse and Opik.
- [TruLens](https://github.com/truera/trulens): Library for evaluating and tracking LLM applications with instrumented traces, described as OpenTelemetry-native.

## Cost and usage

- [Azure API Management llm-emit-token-metric policy](https://learn.microsoft.com/en-us/azure/api-management/llm-emit-token-metric-policy): Policy reference for emitting token usage metrics of LLM calls passing through API Management.
- [ccusage](https://github.com/ccusage/ccusage): Command-line tool that reports token usage and cost of coding agents from local data.
- [FinOps for AI overview](https://www.finops.org/wg/finops-for-ai-overview/): FinOps Foundation guide to managing token costs and resource usage of language models and generative AI.
- [genai-prices](https://github.com/pydantic/genai-prices): Library and price data to calculate the price of calls to LLM inference APIs.
- [Helicone cost tracking](https://docs.helicone.ai/guides/cookbooks/cost-tracking): Guide to monitoring LLM spend and unit economics with Helicone.
- [Langfuse token and cost tracking](https://langfuse.com/docs/observability/features/token-and-cost-tracking): Documentation of how Langfuse records usage and cost of generations, with model prices that can be overridden.
- [LangSmith cost tracking](https://docs.langchain.com/langsmith/cost-tracking): Documentation of token and cost tracking on LangSmith traces.
- [LiteLLM budgets and rate limits](https://docs.litellm.ai/docs/proxy/users): Documentation of budgets and rate limits per user, key and team in the LiteLLM proxy.
- [LiteLLM Prometheus metrics](https://docs.litellm.ai/docs/proxy/prometheus): Documents Prometheus metrics for spend, tokens and latency exposed by the LiteLLM proxy.
- [LiteLLM spend tracking](https://docs.litellm.ai/docs/proxy/cost_tracking): Documentation of spend tracking by key, user and team in the LiteLLM proxy.
- [OpenClaw Monitor](https://github.com/flik2002/openclaw-monitor): Dashboard that monitors OpenClaw AI agents, tracking token usage, sessions and 7-day trends across models.
- [OpenLIT LLM cost tracking](https://docs.openlit.io/latest/openlit/costs/overview): Documentation of spend per model, user and agent run in OpenLIT, with managed model pricing and backfill of missing costs.
- [OpenMeter](https://github.com/openmeterio/openmeter): Metering and usage-based billing infrastructure that aggregates usage events for AI, API and DevOps products.
- [Phoenix cost tracking](https://arize.com/docs/phoenix/tracing/how-to-tracing/cost-tracking): Documentation of cost tracking on traces in Arize Phoenix.
- [Tokscale](https://github.com/junhoyeo/tokscale): Command-line tool and dashboard that track token usage and cost across several coding agents.

## Safety signals

- [Agent Governance Toolkit](https://github.com/microsoft/agent-governance-toolkit): Policy enforcement and trust scoring for agents that emits spans and metrics for policy evaluations and violations.
- [Amazon Bedrock Guardrails CloudWatch metrics](https://docs.aws.amazon.com/bedrock/latest/userguide/monitoring-guardrails-cw-metrics.html): Documentation of CloudWatch metrics for guardrail invocations, interventions, latency and errors.
- [Arthur Engine](https://github.com/arthur-ai/arthur-engine): Monitoring and governance engine that ingests OpenInference traces, runs evaluations on live traces and enforces guardrails.
- [Google Cloud Model Armor](https://docs.cloud.google.com/model-armor/overview): Google Cloud service that screens prompts and responses of AI applications, with a monitoring dashboard.
- [Guardrails AI](https://github.com/guardrails-ai/guardrails): Python framework for validating inputs and outputs of language models, with guard invocations traced through an OpenInference instrumentor.
- [IBM watsonx.governance](https://www.ibm.com/products/watsonx-governance): Product page for continuous monitoring and governance of AI systems for compliance and operational risk.
- [Langfuse security and guardrails](https://langfuse.com/docs/security-and-guardrails): Guide to monitoring and evaluating prompt injection, PII leakage and harmful content with Langfuse and guardrail libraries.
- [NeMo Guardrails](https://github.com/NVIDIA-NeMo/Guardrails): Toolkit for adding guardrails to LLM applications, with OpenTelemetry tracing of guardrail execution.
- [OpenGuardrails](https://github.com/openguardrails/openguardrails): Specification and reference integrations for portable agent safety verdicts, with a mapping to OpenTelemetry concepts.
- [OpenLIT guardrails](https://docs.openlit.io/latest/sdk/features/guardrails.md): Documentation of OpenLIT guardrails for prompt injection, sensitive topics and topic restriction, traced with OpenTelemetry.
- [Pydantic Logfire agent governance](https://pydantic.dev/logfire/agent-governance): Product page on spend policies, data loss prevention and audit of agent actions based on traces.

## On-chain agents and payments

- [cast run (Foundry)](https://www.getfoundry.sh/cast/reference/run): Foundry command that re-executes a mined transaction against forked chain state and shows the resulting call trace, with an optional debugger.
- [Geth EVM tracing](https://geth.ethereum.org/docs/developers/evm-tracing): Documentation of the go-ethereum tracers that replay a transaction on the node and report each step the EVM ran.
- [hashspan](https://github.com/selimaytac/hashspan): OpenTelemetry tracing for on-chain transactions sent by AI agents and other services, with adapters for viem, the CDP SDK, x402 and MPP.
- [Tenderly Debugger](https://docs.tenderly.co/debugger/overview): Hosted tool for inspecting a failed or past EVM transaction: its call trace, contract state at each step and the matching source code.
- [a2a-x402](https://github.com/google-agentic-commerce/a2a-x402): Extension that combines the A2A protocol with x402 payments.
- [Agent Payments Protocol (AP2) documentation](https://ap2-protocol.org/): Documentation site of AP2, an open protocol for agent-initiated payments.
- [Agentic Commerce Protocol](https://github.com/agentic-commerce-protocol/agentic-commerce-protocol): Specification of how a buyer, the buyer's agent and a merchant exchange checkout requests to complete a purchase.
- [AP2](https://github.com/google-agentic-commerce/AP2): Agent Payments Protocol specification for payments initiated by agents.
- [Mastercard agentic commerce guide](https://developer.mastercard.com/merchant-cloud/documentation/tutorials-and-guides/agentic-commerce-guide/22/): Mastercard developer guide on agentic commerce flows and recommended practices.
- [MPP](https://mpp.dev/): Machine Payments Protocol for payments between machines and agents.
- [mppx](https://github.com/wevm/mppx): TypeScript SDK for the Machine Payments Protocol.
- [OpenAI commerce developer documentation](https://developers.openai.com/commerce): Developer documentation for commerce integrations with conversational agents.
- [Stripe agentic commerce documentation](https://docs.stripe.com/agentic-commerce): Stripe documentation of agentic commerce flows and protocol support.
- [Universal Commerce Protocol](https://ucp.dev/): Specification for interoperable commerce between agents and merchants.
- [Visa Trusted Agent Protocol](https://developer.visa.com/capabilities/trusted-agent-protocol): Visa developer documentation for establishing trust between agents and merchants.
- [x402](https://github.com/x402-foundation/x402): Open protocol for payments over HTTP 402 responses.
- [Erigon dashboard setup](https://docs.erigon.tech/fundamentals/creating-a-dashboard): Documentation of Prometheus metrics export and a Grafana dashboard for monitoring an Erigon node.
- [eRPC](https://github.com/erpc/erpc): Fault-tolerant RPC proxy for EVM chains with caching, a monitoring setup and tracing exported over OTLP.
- [Ethereum execution APIs](https://github.com/ethereum/execution-apis): Specification of the JSON-RPC interface of Ethereum execution clients.
- [Geth metrics](https://geth.ethereum.org/docs/monitoring/metrics): Documentation of the metrics of the go-ethereum client, including a Prometheus-formatted endpoint.
- [Reth](https://github.com/paradigmxyz/reth): Ethereum execution client with Prometheus metrics and OTLP trace export through a command-line flag.
- [Alto](https://github.com/pimlicolabs/alto): ERC-4337 bundler that relays user operations sent by smart accounts.
- [Coinbase AgentKit](https://github.com/coinbase/agentkit): Toolkit that gives AI agents wallets and on-chain actions.
- [Coinbase CDP SDK](https://github.com/coinbase/cdp-sdk): SDK for Coinbase Developer Platform wallets and APIs.
- [Privy agent wallets](https://docs.privy.io/wallets/overview/solutions/agent-wallets): Documentation of wallets for agents with a policy engine that limits tokens, chains, transfer values and recipients.
- [Turnkey agentic wallets](https://docs.turnkey.com/solutions/company-wallets/agentic-wallets): Documentation of scoped signing authority for agents with policies, spending caps and multi-party approval.
- [viem](https://github.com/wevm/viem): TypeScript library for Ethereum clients and transactions.
- [Anvil](https://book.getfoundry.sh/anvil/): Local Ethereum node of Foundry for testing transactions without a public network.
- [ethereum-package (Kurtosis)](https://github.com/ethpandaops/ethereum-package): Kurtosis package that starts a private multi-client Ethereum testnet on Docker or Kubernetes for testing and development.
- [Foundry](https://github.com/foundry-rs/foundry): Toolkit for Ethereum development that includes Anvil and Cast.
- [Hardhat simulated networks](https://hardhat.org/docs/explanations/edr-simulated-networks): Documentation of the in-process blockchains that Hardhat starts on the local machine when tests or scripts run.

## Findings

- [Anvil gave concurrent transactions from one account the same nonce](https://github.com/foundry-rs/foundry/issues/17354): Concurrent eth_sendTransaction calls from one unlocked Anvil account got the same nonce, which breaks parallel agent tests.
- [EDR OP chain type reports an L1 data fee of 0](https://github.com/NomicFoundation/edr/issues/1829): The OP chain type of EDR set the L1Block fee scalars at the wrong storage offsets, so simulated receipts reported an L1 data fee of 0.
- [eRPC OTLP/HTTP tracing exports nothing when the endpoint has a scheme](https://github.com/erpc/erpc/issues/1276): With tracing over OTLP/HTTP, eRPC exports no spans when the endpoint includes a scheme, the form its documentation asks for.
- [MLflow OTLP trace ingest drops the span kind](https://github.com/mlflow/mlflow/issues/26841): Spans sent to the OTLP endpoint of MLflow lose their kind, so CLIENT and SERVER spans read back as INTERNAL.
- [viem concurrent receipt waits shared the first call options](https://github.com/wevm/viem/issues/5137): Concurrent viem receipt waits for one hash on one client all ran with the timeout and confirmations of the first call.
- [viem receipt wait missed replacements of already dropped transactions](https://github.com/wevm/viem/issues/5242): The viem receipt wait never detects a replacement when the original transaction left the pool before its first lookup, and times out.
- [viem receipt wait took a transaction for its own replacement](https://github.com/wevm/viem/issues/5161): The viem receipt wait treated the awaited transaction as its own replacement when the node returned it before its receipt, and failed.

## Benchmarks and datasets

- [AgentErrorBench (AgentDebug)](https://github.com/ulab-uiuc/AgentDebug): Annotated failure trajectories from ALFWorld, GAIA and WebShop with an error taxonomy and a debugging pipeline.
- [AgentRx dataset (Hugging Face)](https://huggingface.co/datasets/microsoft/AgentRx): Annotated failed agent trajectories used to evaluate step localization and failure attribution.
- [AIOpsLab](https://github.com/microsoft/AIOpsLab): Framework to design, run and evaluate autonomous AIOps agents on microservice faults with telemetry as input.
- [CatchBench](https://github.com/yzhao062/catchbench): Benchmark for auditing agent failures from the declared configuration, a growing prefix of a run and the finished trace.
- [MAST-Data (Hugging Face)](https://huggingface.co/datasets/mcemri/MAD): Annotated traces of multi-agent systems used for failure taxonomy research.
- [OpenRCA](https://github.com/microsoft/OpenRCA): Benchmark of root cause localization for software failures from logs, metrics and traces.
- [SWE-smith trajectories (Hugging Face)](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories): Dataset of recorded trajectories of a coding agent solving software engineering tasks.
- [TRAIL dataset (Hugging Face)](https://huggingface.co/datasets/PatronusAI/TRAIL): Annotated agent execution traces with error labels, stored as OpenTelemetry spans.
- [Who_and_When (Hugging Face)](https://huggingface.co/datasets/Kevin355/Who_and_When): Dataset of multi-agent logs with annotated failure agents and steps.

## Learning

- [Agenta guide to LLM observability with OpenTelemetry](https://agenta.ai/blog/the-ai-engineer-s-guide-to-llm-observability-with-opentelemetry): Vendor guide on instrumenting LLM applications with OpenTelemetry.
- [Agno tracing](https://docs.agno.com/tracing/overview): Documentation of OpenTelemetry tracing of Agno agents and teams.
- [AI Agent Observability - Evolving Standards and Best Practices](https://opentelemetry.io/blog/2025/ai-agent-observability/): OpenTelemetry blog post on observing agents and the standards in progress.
- [Amazon Bedrock AgentCore samples](https://github.com/awslabs/agentcore-samples): Sample agents and notebooks for Amazon Bedrock AgentCore, including observability examples.
- [AutoGen core OpenTelemetry](https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/framework/telemetry.html): Documentation of the OpenTelemetry support of the AutoGen core runtime.
- [AutoGen tracing and observability](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tracing.html): Documentation of OpenTelemetry tracing for AutoGen AgentChat applications.
- [AWS blog: build trustworthy agents with AgentCore Observability](https://aws.amazon.com/blogs/machine-learning/build-trustworthy-ai-agents-with-amazon-bedrock-agentcore-observability/): AWS Machine Learning blog post on using AgentCore Observability to monitor and debug agents.
- [CrewAI observability](https://docs.crewai.com/en/observability/overview): Official documentation listing tracing integrations for CrewAI.
- [Dify: integrate with Alibaba Cloud Monitor](https://docs.dify.ai/en/use-dify/monitor/integrations/integrate-aliyun): Documents the Dify setting that exports application traces to Alibaba Cloud Monitor through OpenTelemetry.
- [Dynatrace expands AI coding agent monitoring](https://www.dynatrace.com/news/blog/dynatrace-expands-ai-coding-agent-monitoring/): Dynatrace announcement of monitoring for several coding agents.
- [Google ADK observability](https://google.github.io/adk-docs/observability/): Official documentation on observability for ADK agents.
- [Google Cloud blog: Google Cloud and OpenTelemetry GenAI conventions](https://cloud.google.com/blog/products/devops-sre/google-cloud-and-otel-genai): Google Cloud blog post on its work with the OpenTelemetry GenAI conventions.
- [Govern and redact traces in Unity Catalog](https://docs.databricks.com/aws/en/mlflow3/genai/tracing/govern-redact): Databricks documentation on governing access to MLflow traces and redacting them in Unity Catalog.
- [Greptime: how OpenTelemetry traces LLM calls, agent reasoning and MCP tools](https://www.greptime.com/blogs/2026-05-09-opentelemetry-genai-semantic-conventions): Blog post summarizing the GenAI semantic conventions for LLM, agent and MCP spans.
- [Hamel Husain: a field guide to rapidly improving AI products](https://hamel.dev/blog/posts/field-guide/): Practitioner guide on error analysis of logged traces for AI products.
- [How to redact PII from LLM telemetry](https://openobserve.ai/blog/redact-pii-llm-telemetry/): Guide to redacting PII from LLM traces with pipelines and an OpenTelemetry Collector while keeping traces debuggable.
- [How to redact sensitive prompts in GenAI OpenTelemetry traces](https://oneuptime.com/blog/post/2026-02-06-redact-sensitive-prompts-genai-opentelemetry-traces/view): Guide to removing PII and credentials from GenAI traces before they reach the observability backend.
- [IONOS: monitor a coding agent with the Monitoring Service](https://docs.ionos.com/cloud/tutorials/observability/monitoring-service/monitor-claude-code-with-monitoring-service.md): IONOS tutorial for exporting coding agent token and cost metrics to its monitoring service.
- [LangGraph observability](https://docs.langchain.com/oss/python/langgraph/observability): Documentation of the tracing options for LangGraph applications, mostly through LangSmith.
- [LangSmith: trace voice agents](https://langchain.com/blog/trace-voice-agents-in-langsmith): Vendor blog on tracing voice agent frameworks in LangSmith.
- [LangWatch OpenClaw integration docs](https://langwatch.ai/docs/integration/openclaw): Documents sending traces of a personal assistant agent to LangWatch over OpenTelemetry.
- [LangWatch: instrumenting an OpenClaw assistant with OpenTelemetry](https://langwatch.ai/blog/instrumenting-your-openclaw-agent-with-opentelemetry): Vendor guide to exporting OpenTelemetry GenAI traces from a self-hosted personal assistant agent.
- [LlamaIndex observability](https://developers.llamaindex.ai/python/framework/module_guides/observability/): Documentation of the tracing options of LlamaIndex, including OpenTelemetry-based integrations.
- [Mastra observability](https://mastra.ai/docs/observability/overview): Official documentation on tracing Mastra agents and workflows.
- [Maxim: agent observability guide](https://www.getmaxim.ai/articles/agent-observability-the-definitive-guide-to-monitoring-evaluating-and-perfecting-production-grade-ai-agents): Vendor guide on monitoring and evaluating production agents.
- [Microsoft Agent Framework observability](https://learn.microsoft.com/en-us/agent-framework/agents/observability): Documentation of how Microsoft Agent Framework emits traces, logs and metrics with the OpenTelemetry GenAI conventions.
- [Microsoft Tech Community: Observability for the Age of Generative AI](https://techcommunity.microsoft.com/blog/azureobservabilityblog/observability-for-the-age-of-generative-ai/4473307): Azure observability blog post on agent dashboards, AI-aware traces and attribute-based trace search.
- [Mintive: OpenTelemetry standards for agent monitoring](https://www.mintmcp.com/blog/opentelemetry-standards-agent-monitoring): Vendor blog on OpenTelemetry standards for agent monitoring.
- [MLflow tracing integrations](https://mlflow.org/docs/latest/genai/tracing/integrations/): Official list of libraries that MLflow can trace automatically.
- [MLflow: tracing OpenClaw](https://mlflow.org/blog/openclaw-tracing): MLflow blog on tracing a personal assistant agent with a self-hosted MLflow server.
- [Monitor agent usage with OpenTelemetry (VS Code)](https://code.visualstudio.com/docs/agents/guides/monitoring-agents): Documentation of the OpenTelemetry traces, metrics and events of agent mode in VS Code, following the GenAI conventions.
- [Monitoring AI commerce agents (LogicMonitor)](https://www.logicmonitor.com/blog/how-to-monitor-ai-agents-in-commerce-systems): Vendor guide on monitoring shopping agents, with attention to infrastructure and agent decision paths.
- [Nango: OpenTelemetry for AI agent observability](https://nango.dev/blog/opentelemetry-ai-agent-observability): Blog post on tracing agent tool calls and API integrations with OpenTelemetry.
- [Observability and audit trails for Agent Builder in Elastic](https://www.elastic.co/observability-labs/blog/ai-agent-observability-audit-trail): Article on reading Agent Builder traces in Elastic and writing an approval record for agent actions.
- [OpenAI Agents SDK tracing](https://openai.github.io/openai-agents-python/tracing/): Official documentation on the trace and span model of the SDK.
- [OpenTelemetry blog: generative AI](https://opentelemetry.io/blog/2024/otel-generative-ai/): OpenTelemetry blog post introducing the generative AI work.
- [OpenTelemetry blog: LLM observability](https://opentelemetry.io/blog/2024/llm-observability/): OpenTelemetry blog post on observing LLM applications.
- [OpenTelemetry context propagation](https://opentelemetry.io/docs/concepts/context-propagation/): Explains how trace context moves between services and processes, which applies to multi-agent and tool calls.
- [OpenTelemetry demo](https://github.com/open-telemetry/opentelemetry-demo): Multi-service demo application that shows traces, metrics and logs end to end.
- [OpenTelemetry GenAI conventions are not stable yet (DEV Community)](https://dev.to/azena-ai/opentelemetrys-genai-semantic-conventions-are-not-stable-yet-heres-what-actually-shipped-in-2026-3mke): Community post on the stability status of the GenAI conventions in 2026.
- [OpenTelemetry traces concept](https://opentelemetry.io/docs/concepts/signals/traces/): Official introduction to spans and traces.
- [Opik: observability and alerts for OpenClaw](https://www.comet.com/site/blog/openclaw-observability/): Vendor post on tracing LLM calls, tool runs and memory recall of a personal assistant agent with an Opik plugin.
- [Opik: Pipecat integration](https://www.comet.com/docs/opik/v1/integrations/pipecat): Documents conversation and turn level tracing of Pipecat voice agents in Opik.
- [Pydantic AI with Logfire](https://ai.pydantic.dev/logfire/): Official documentation on debugging and monitoring Pydantic AI agents.
- [Semantic Kernel observability](https://learn.microsoft.com/en-us/semantic-kernel/concepts/enterprise-readiness/observability/): Official documentation on logs, metrics and traces for Semantic Kernel applications.
- [smolagents: inspecting runs with OpenTelemetry](https://huggingface.co/docs/smolagents/tutorials/inspect_runs): Tutorial on instrumenting smolagents runs with OpenTelemetry and viewing them.
- [Splunk blog: what is agentic observability](https://www.splunk.com/en_us/blog/learn/agentic-observability.html): Vendor explainer on agentic observability and AI-assisted operations.
- [Traceloop OpenLLMetry blog introduction](https://traceloop.com/blog/openllmetry): Original announcement of OpenLLMetry, extending OpenTelemetry to LLM applications.
- [Uptrace: AI agent observability explained](https://uptrace.dev/blog/ai-agent-observability): Vendor explainer of agent observability concepts and standards.
- [Uptrace: OpenTelemetry for AI systems](https://uptrace.dev/blog/opentelemetry-ai-systems): Vendor implementation guide for OpenTelemetry instrumentation of LLM and agent systems.
- [Vellum: AI observability for agents](https://www.vellum.ai/blog/understanding-your-agents-behavior-in-production): Vendor practical guide to observing agents in production.
- [Vercel AI SDK telemetry](https://ai-sdk.dev/docs/ai-sdk-core/telemetry): Official documentation of the telemetry settings of the AI SDK.
- [Weights and Biases: AI agent observability guide](https://wandb.ai/site/articles/ai-agent-observability/): Vendor guide to tracing AI agents.
- [AI Engineering (book)](https://www.oreilly.com/library/view/ai-engineering/9781098166298/): Book by Chip Huyen on building applications with foundation models, with chapters on evaluation and on monitoring and observability.
- [Building Applications with AI Agents (book)](https://www.oreilly.com/library/view/building-applications-with/9781098176495/): Book by Michael Albada on designing agent systems, with chapters on validation, measurement and monitoring in production.
- [Learning OpenTelemetry (book)](https://www.oreilly.com/library/view/learning-opentelemetry/9781098147174/): Book by Ted Young and Austin Parker on adopting OpenTelemetry, the telemetry layer most agent tracing builds on.
- [Observability Engineering (book)](https://www.oreilly.com/library/view/observability-engineering/9781492076438/): Book by Charity Majors, Liz Fong-Jones and George Miranda on observability practice for production systems.
- [Observability for Large Language Models (report)](https://www.oreilly.com/library/view/observability-for-large/9781098159757/): Short report by Phillip Carter on observability for LLM applications with OpenTelemetry.
- [KubeCon EU 2025: deep dive to AI agent observability](https://kccnceu2025.sched.com/event/1txEC/deep-dive-to-ai-agent-observability-guangya-liu-ibm-karthik-kalyanaraman-langtrace-ai): Session on tracing and monitoring AI agents with OpenTelemetry, by IBM and Langtrace speakers.
- [KubeCon India 2026: what did my agent do?](https://kccncind2026.sched.com/event/2IW20/what-did-my-agent-do-observability-and-accountability-for-ai-agents-ishan-jain-grafana-labs): Session on observability and accountability for AI agents with OpenTelemetry and GenAI conventions.
- [KubeCon talk: AI/ML observability with OpenTelemetry and Fluent Bit](https://www.youtube.com/watch?v=DVFQ20OrEFk): KubeCon session recording by Celalettin Calis on AI and ML observability with OpenTelemetry and Fluent Bit.
- [KubeCon talk: End-to-end observability for LLM inference: from token to GPU](https://www.youtube.com/watch?v=K6doiHgBabk): KubeCon session recording by speakers from DaoCloud on observability of LLM inference.
- [KubeCon talk: Exploring observability with MCP servers](https://www.youtube.com/watch?v=SIg81hkHZXQ): KubeCon session recording by Tiffany Jernigan of Grafana Labs on observability with MCP servers.
- [KubeCon talk: GenAI observability: keeping GenAI honest without oversharing](https://www.youtube.com/watch?v=Q4E9GDAslIk): KubeCon session recording by Liudmila Molkova of Grafana Labs on GenAI observability and sensitive content.
- [KubeCon talk: LLM observability with Open Data Hub and vLLM](https://www.youtube.com/watch?v=pZRJ783BCDY): KubeCon lightning talk recording by Twinkll Sisodia on LLM observability with Open Data Hub and vLLM.
- [KubeCon talk: OpenTelemetry for autonomous AI agents](https://www.youtube.com/watch?v=1GaoQcGk57M): KubeCon session recording by Abdel Fane on applying OpenTelemetry to autonomous AI agents.
- [KubeCon talk: Optimizing LLM performance in Kubernetes with OpenTelemetry](https://www.youtube.com/watch?v=6rdeFACyyYg): KubeCon session recording by Ashok Chandrasekar and Liudmila Molkova on OpenTelemetry for LLM serving on Kubernetes.
- [KubeCon talk: Sponsored keynote: OpenSearch, open observability for agentic AI](https://www.youtube.com/watch?v=LuKaV3WeNlk): KubeCon sponsored keynote recording by Anirudha Jadhav on open observability for agentic AI with OpenSearch.
- [KubeCon talk: Why are your AI's decisions hard to explain: trace every decision](https://www.youtube.com/watch?v=e_u-YMUK-NE): KubeCon session recording by Dhiraj Kumar Jain and Vikash Agrawal on tracing the decisions of AI systems.
- [OpenClaw observability and monitoring with OpenTelemetry and SigNoz](https://www.youtube.com/watch?v=2DS1Y-h6GdE): Video on collecting traces, metrics and logs from OpenClaw with OpenTelemetry and viewing them in SigNoz.
- [OpenLLMetry is all you need (AI Engineer talk)](https://ai.engineer/talks/KVgbERRPU4M-openllmetry-is-all-you-need): Conference talk on instrumenting LLM applications with OpenLLMetry.
- [Watching AI workers: OpenSearch observability for OpenClaw and Hermes-agent](https://www.youtube.com/watch?v=T8dRtBpu2Xg): Conference talk by Stefano Pampaloni on observing OpenClaw and Hermes-agent runs with OpenSearch.
- [A multi-dataset benchmark for LLM agents in microservice failure diagnosis](https://arxiv.org/abs/2606.29193): Benchmark of agents diagnosing failures in microservice systems.
- [A survey on AgentOps](https://arxiv.org/abs/2508.02121): Survey of categories, challenges and directions of AgentOps.
- [AEGIS: a pre-execution firewall and audit layer for AI agents](https://arxiv.org/abs/2603.12621): Proposes a layer that checks tool calls before execution and keeps an audit log.
- [Agent Flight Recorder: tamper-evident audit trails for tool-using agents](https://arxiv.org/abs/2609.01931): Proposes tamper-evident audit trails for agents, with on-chain anchoring.
- [AgentDebugX: toolkit for failure observability, attribution and recovery](https://arxiv.org/abs/2607.18754): Presents an open-source toolkit for failure observability and attribution in LLM agents.
- [AgentGuard: execution guardrails from anomalous coding-agent trajectories](https://arxiv.org/abs/2609.16287): Studies learning guardrails from anomalous trajectories of coding agents.
- [Agentic observability: automated alert triage for Adobe e-commerce](https://arxiv.org/abs/2602.02585): Industry paper on agent-based alert triage for an e-commerce platform.
- [AgentLens: production-assessed trajectory reviews for coding agent evaluation](https://arxiv.org/abs/2607.06624): Studies reviewing production trajectories of coding agents for evaluation.
- [AgentOps: enabling observability of LLM agents](https://arxiv.org/abs/2411.05285): Proposes a taxonomy of artifacts and data to trace across the lifecycle of LLM agents.
- [AgentTrace: a structured logging framework for agent observability](https://arxiv.org/abs/2602.10133): Proposes a structured logging framework for agent systems that can integrate with OpenTelemetry.
- [AIOpsLab: a framework to evaluate AI agents for autonomous clouds](https://arxiv.org/abs/2501.06706): Framework for evaluating agents that operate cloud systems.
- [Annotrace: a workbench for step-level annotation of agent traces](https://arxiv.org/abs/2610.23284): Presents a workbench for annotating individual steps in agent traces.
- [Beyond the mandate: a security analysis of the Agent Payments Protocol](https://arxiv.org/abs/2608.23858): Systematic security analysis of AP2.
- [Detecting safety violations across many agent traces](https://arxiv.org/abs/2604.11806): Studies detection of safety violations by analyzing many agent traces.
- [Failure as a process: an anatomy of CLI coding agent trajectories](https://arxiv.org/abs/2607.09510): Analyzes failure patterns in trajectories of command line coding agents.
- [Five attacks on the x402 agentic payment protocol](https://arxiv.org/abs/2605.11781): Describes attacks on the x402 payment protocol.
- [From agent traces to trust: evidence tracing and execution provenance](https://arxiv.org/abs/2606.04990): Survey of evidence tracing and execution provenance for LLM agents.
- [Functionality-grounded benchmark for web agents in e-commerce](https://arxiv.org/abs/2508.15832): Benchmark of web agents on e-commerce functionality.
- [Governance-aware agent telemetry for closed-loop enforcement](https://arxiv.org/abs/2604.05119): Proposes agent telemetry that supports governance enforcement in multi-agent systems.
- [Observability and fault injection for LLM multi-agent systems](https://arxiv.org/abs/2608.24271): Studies observability and fault injection for multi-agent systems used in software engineering.
- [Observability for delegated execution in agentic AI systems](https://arxiv.org/abs/2606.09692): Discusses observability needs when agents delegate execution to other agents or tools.
- [Observing, analyzing and optimizing agentic AI systems](https://arxiv.org/abs/2507.11277): Describes automation for observing, analyzing and optimizing agentic AI systems.
- [PrefixGuard: online failure warning and trace-grounded diagnosis for LLM agents](https://arxiv.org/abs/2605.06455): Studies online failure warning from partial agent traces.
- [ProbGuard: proactive runtime monitoring for LLM agent safety](https://arxiv.org/abs/2508.00500): Proposes probabilistic runtime monitoring to predict unsafe agent behavior.
- [ShopGym: simulation and benchmarking of e-commerce web agents](https://arxiv.org/abs/2605.16116): Framework for simulating and benchmarking e-commerce agents.
- [SoK: security of autonomous LLM agents in agentic commerce](https://arxiv.org/abs/2604.15367): Systematization of security issues of agents in commerce settings.
- [TelemetrySuffBench: is agent telemetry sufficient for failure-origin diagnosis?](https://arxiv.org/abs/2608.07899): Benchmark that tests whether agent telemetry suffices to find where failures originate.
- [Traccia: an OpenTelemetry-based governance platform for AI systems](https://arxiv.org/abs/2607.14309): Describes a governance platform built on OpenTelemetry data.
- [TRAIL: trace reasoning and agentic issue localization](https://arxiv.org/abs/2505.08638): Introduces an annotated benchmark of agent traces for locating errors.
- [WebMall: a multi-shop benchmark for web agents](https://arxiv.org/abs/2508.13024): Benchmark of web agents performing tasks across several online shops.
- [Which agent causes task failures and when?](https://arxiv.org/abs/2505.00212): Studies automated failure attribution in multi-agent systems and releases a dataset.
- [Whispers of wealth: red-teaming the Agent Payments Protocol via prompt injection](https://arxiv.org/abs/2601.22569): Security analysis of AP2 flows under prompt injection.
- [Why do multi-agent LLM systems fail?](https://arxiv.org/abs/2503.13657): Analyzes failure modes of multi-agent systems and releases annotated traces.
- [Willful disobedience: automatically detecting failures in agentic traces](https://arxiv.org/abs/2603.23806): Studies automatic detection of failures in agent traces.
- [Evaluating AI Agents (DeepLearning.AI)](https://www.deeplearning.ai/courses/evaluating-ai-agents): Short course on adding tracing to an agent and evaluating its components, taught with Arize.
- [Getting Started with OpenTelemetry (LFS148)](https://training.linuxfoundation.org/training/getting-started-with-opentelemetry-lfs148/): Free online Linux Foundation course covering manual and automatic OpenTelemetry instrumentation and Collector pipelines.
- [Hugging Face Agents Course](https://huggingface.co/learn/agents-course/unit0/introduction): Free course on building agents; has a bonus unit on agent observability and evaluation.
- [Anthropic engineering: how we built our multi-agent research system](https://www.anthropic.com/engineering/multi-agent-research-system): Engineering write-up of a multi-agent research system that describes production tracing for debugging.
- [Elastic: AI agent observability with OTel, OpenLIT and Elastic](https://www.elastic.co/observability-labs/blog/ai-observability-web-agents-openlit): Elastic blog on monitoring web-browsing agents with OpenTelemetry, OpenLIT and Elastic.
- [Elastic: GenAI observability for customer support](https://www.elastic.co/search-labs/blog/genai-customer-support-observability): Engineering account of monitoring a customer support assistant built on Elastic.
- [Honeycomb for financial services](https://www.honeycomb.io/industries/financial-services): Vendor page on observability requirements in financial services, including retention for audit.
- [Pydantic case study: Evergreen.ai](https://pydantic.dev/case-studies/evergreenai): Case study of a financial planning agent team using tracing and evaluations in production.
- [Code RED #31: beyond hype, the real impact of AI on observability](https://www.dash0.com/podcast/31-code-red-live-beyond-hype-the-real-impact-of-ai-on-observability): Live episode on agentic observability and OpenTelemetry support for AI.
- [Dash0 Code RED podcast](https://www.dash0.com/podcast): Podcast about observability and OpenTelemetry, with episodes on AI and observability.
- [Datadog OpenTelemetry news, May 2026](https://opensource.datadoghq.com/otel-news/2026/05/): Monthly roundup of OpenTelemetry developments, including GenAI conventions releases.
- [o11y.news](https://buttondown.com/o11y.news/archive/): Weekly newsletter linking to observability and OpenTelemetry reading.
- [O11ycast](https://www.heavybit.com/library/podcasts/o11ycast): Podcast on observability with episodes on AI systems and OpenTelemetry.
- [OpenObservability Talks podcast](https://creators.spotify.com/pod/profile/openobservability/): Podcast on open source observability with an episode on OpenTelemetry for GenAI.
- [OpenObservability Talks: OpenTelemetry for GenAI and the OpenLLMetry project](https://www.castfox.net/podcast/openobservability-talks-1013852/episode/opentelemetry-for-genai-and-the-openllmetry-project-openobservability-talks-s6e06-211572): Podcast episode (S6E06) with the creator of OpenLLMetry on GenAI conventions and tracing.

## Community

- [A2A protocol discussions](https://github.com/a2aproject/A2A/discussions): GitHub Discussions forum of the Agent2Agent protocol repository.
- [CNCF Slack channel otel-genai-instrumentation-wg](https://cloud-native.slack.com/archives/C06KR7ARS3X): Slack channel of the OpenTelemetry GenAI instrumentation working group in the CNCF workspace.
- [CNCF: Observability Day at KubeCon North America 2026](https://www.cncf.io/blog/2026/09/24/observability-day-where-the-community-comes-together-at-kubecon-cloudnativecon-north-america-2026/): CNCF blog post announcing Observability Day on 2026-11-09, with AI and agent observability on the program.
- [Model Context Protocol discussions](https://github.com/modelcontextprotocol/modelcontextprotocol/discussions): GitHub Discussions forum of the Model Context Protocol specification repository.
- [OpenTelemetry community](https://opentelemetry.io/community/): Page of the OpenTelemetry project on how to join its working groups, meetings and chat channels.
- [OpenTelemetry GenAI conventions issues](https://github.com/open-telemetry/semantic-conventions-genai/issues): Issue tracker of the repository that holds the OpenTelemetry GenAI semantic conventions.
- [OpenTelemetry GenAI project page (community repo)](https://github.com/open-telemetry/community/blob/main/projects/gen-ai.md): Describes the OpenTelemetry GenAI project, its scope, owners and meeting information.
- [OpenTelemetry GenAI SIG meeting notes](https://docs.google.com/document/d/1EKIeDgBGXQPGehUigIRLwAUpRGa7-1kXB736EaYuJ2M/edit): Shared meeting notes of the OpenTelemetry GenAI semantic conventions and instrumentation SIG.
- [OpenTelemetry YouTube channel](https://www.youtube.com/@otel-official): Official OpenTelemetry channel with recordings of project meetings and talks.

## Related lists

- [awesome-agent-observability (anhermon)](https://github.com/anhermon/awesome-agent-observability): Link list on agent observability, grouped into standards, platforms, trace backends, evaluation, guardrails, gateways, MCP and frameworks.
- [awesome-agent-observability (danielt69)](https://github.com/danielt69/awesome-agent-observability): Link list on agent observability with hands-on guides, platform comparisons, evaluation, guardrails, red teaming and benchmarks.
- [awesome-ai-sre](https://github.com/agamm/awesome-ai-sre): List of AI agents, production debugging, incident management, AIOps and chaos engineering tools for site reliability work.
- [awesome-harness-engineering](https://github.com/ai-boost/awesome-harness-engineering): Curated list on AI agent harness engineering with tools, patterns and evaluations.
- [awesome-llm-observability (ContextJet-ai)](https://github.com/ContextJet-ai/awesome-llm-observability): Curated list of resources for observability of LLM applications.
- [Awesome-LLMOps](https://github.com/tensorchord/Awesome-LLMOps): Curated list of LLMOps tools.
- [awesome-observability](https://github.com/adriannovegil/awesome-observability): Curated list of observability resources, covering tools, practices and standards.
- [awesome-opentelemetry](https://github.com/magsther/awesome-opentelemetry): List of OpenTelemetry learning material, books, videos, tracing backends and instrumentation by language.

## Optional

- [entries.json](https://raw.githubusercontent.com/selimaytac/awesome-agent-observability/main/entries.json): all entries with every field, for programs and agents.