Skip to main content
AgentMark ingests traces over OpenTelemetry. Anything that exports OTLP — the AgentMark SDK, a framework instrumentor, or a raw OpenTelemetry setup — can send spans to AgentMark by pointing its exporter at one endpoint. There is no AgentMark-specific exporter to install. This page covers the endpoint and authentication. If you’re using a framework, start with the ecosystem that instruments it:

OpenInference

LangChain, LlamaIndex, OpenAI Agents SDK, CrewAI, DSPy, Haystack, and more

OpenLLMetry

Traceloop and OpenLIT instrumentors — AutoGen, Semantic Kernel, Agno, and more

​
Endpoint

AgentMark accepts OTLP over HTTP at: 
https://api.agentmark.co/v1/traces
Every request needs two headers:
HeaderValueRequired
AuthorizationYour AgentMark API key, sent as the raw value (no Bearer prefix)Yes — missing returns 401
X-Agentmark-App-IdThe app the traces belong toYes — missing returns 400
Find both in your project settings. The API key authenticates the request; the app id routes the spans to the right app.

​
Point an exporter at AgentMark

Most OpenTelemetry SDKs and instrumentors read the standard OTLP environment variables, so no code change is needed: 
OTEL_EXPORTER_OTLP_TRACES_ENDPOINT="https://api.agentmark.co/v1/traces"
OTEL_EXPORTER_OTLP_TRACES_HEADERS="Authorization=<YOUR_API_KEY>,X-Agentmark-App-Id=<YOUR_APP_ID>"
To configure the exporter in code instead: 
import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-http";

const exporter = new OTLPTraceExporter({
  url: "https://api.agentmark.co/v1/traces",
  headers: {
    Authorization: process.env.AGENTMARK_API_KEY!, // raw key, no "Bearer" prefix
    "X-Agentmark-App-Id": process.env.AGENTMARK_APP_ID!,
  },
});
For local development, npx @agentmark-ai/cli dev accepts the same OTLP format at http://localhost:9418/v1/traces, so you can point any instrumentor at your dev server before sending to the cloud.

​
Supported semantic conventions

AgentMark reads several attribute conventions and normalizes them into one trace model — model, token usage, input and output messages, tool calls, and span kind — so cost and latency are computed the same way regardless of which library produced the span.
ConventionRecognized byNotes
OpenTelemetry GenAI (gen_ai.*)The official gen_ai semantic conventionsThe default. Spec-compliant emitters (including Pydantic AI via Logfire) work with no extra mapping
OpenInferenceopeninference.span.kind and llm.* attributesThe Arize instrumentor ecosystem — see OpenInference
OpenLLMetry / Tracelooptraceloop.* and indexed gen_ai.prompt.* / gen_ai.completion.* attributesTraceloop and OpenLIT instrumentors — see OpenLLMetry
Spans that match none of these are still stored with their attributes intact; only the normalized fields (model, tokens, I/O) depend on a recognized convention.

​
What AgentMark does with a span

Once a span arrives, AgentMark:
  • Classifies it as a model call (GENERATION) or another operation (SPAN), and resolves a span kind — llm, tool, agent, retrieval, embedding, or guardrail.
  • Extracts the model, token counts, input and output, tool calls, and settings.
  • Computes cost from the model and token counts using its pricing model.
No span kind or attribute mapping is required from you — AgentMark infers it from the convention the instrumentor used.

​
Next steps

OpenInference

Trace LangChain, LlamaIndex, CrewAI, and the rest of the OpenInference ecosystem

OpenLLMetry

Trace AutoGen, Semantic Kernel, Agno, and other Traceloop/OpenLIT-instrumented frameworks

AgentMark SDK tracing

Instrument your own code directly with the AgentMark SDK

Traces and logs

Explore the traces once they arrive

​
Have questions?

Reach out any time: