Send traces to Coach

Coach ingests OTLP/JSON at http://127.0.0.1:5899/v1/traces, bearer-authed with a locally generated key. Any of the three ways below works - pick whichever fits your stack.

Get your ingest key

Every Coach install generates a local key. It’s printed in the terminal when Coach starts and shown on the Waiting for traces screen - or read it from the API:

curl -s http://127.0.0.1:5899/api/info | grep -o '"apiKey":"[^"]*"'

Glassray SDK
OpenTelemetry exporter
Raw OTLP

The @glassray/tracing SDK handles OTLP encoding, gzip, batching, and retries. Wrap your agent with trace, and each step with llm / tool:

npm install @glassray/tracing

import { Glassray } from "@glassray/tracing";

const glassray = new Glassray({ environment: "local", agent: "support-bot" });

await glassray.trace("handle-ticket", { customer: "acme" }, async (t) => {
  // Capture the user's question as the trace input (the SDK can't see closures).
  t.setInput(userMessage);

  const plan = await t.llm(
    "answer",
    { model: "claude-opus-4-8", provider: "anthropic", input: userMessage },
    () => anthropic.messages.create(request), // usage + output captured from the response
  );

  const order = await t.tool("lookup-order", { input: { orderId: "4821" } }, () =>
    lookupOrder("4821"),
  );

  return plan;
});

await glassray.flush(); // serverless: waitUntil(glassray.flush())

Point the SDK at your local Coach (it defaults to Glassray Cloud):

export GLASSRAY_ENDPOINT="http://127.0.0.1:5899"
export GLASSRAY_API_KEY="<your-local-key>"

Token usage is extracted automatically from the model response (usage.input_tokens/output_tokens, or the OpenAI equivalents). model and provider on t.llm populate the LLM span; t.setInput / an input option capture prompts the SDK can’t otherwise see.

Already instrumented with OpenTelemetry? Point your existing exporter at Coach - no Glassray SDK. Coach speaks OTLP/HTTP JSON.

export OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:5899"
export OTEL_EXPORTER_OTLP_PROTOCOL="http/json"
export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer <your-local-key>"

Works with any OTel-compatible GenAI instrumentation (OpenLIT, OpenLLMetry, OpenInference, or a self-hosted Collector). The same wire format powers hosted Glassray - see OpenTelemetry ingestion for the attribute contract.

Send an OTLP/JSON envelope directly - the wire format the SDK produces. Gzip is accepted and decoded transparently.

curl -X POST http://127.0.0.1:5899/v1/traces \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <your-local-key>" \
  -d '{ "resourceSpans": [ /* ... */ ] }'

A 200 with an empty {} body acknowledges the batch.

How ingest behaves

Live

Every ingested trace is pushed to the dashboard over SSE - the view updates without a refresh.

Batch-friendly

Spans are merged by span id, so a batch exporter that flushes one trace across several POSTs accumulates instead of overwriting.

Fault-tolerant

A malformed trace in a batch is skipped and logged - the batch’s other traces still land.

Bounded

Request bodies are capped at 16 MiB - an over-limit POST is rejected whole, so keep exporter batches under the cap.

Once traces are flowing, head to Find & fix deviations to run discovery and turn what it finds into evals.

Get started

Glassray CLI

Coach (local)

Concepts

Trace sources

Glassray SDK

Integrations

Explore

Send traces to Coach

Get your ingest key

How ingest behaves

Live

Batch-friendly

Fault-tolerant

Bounded

​Get your ingest key

​How ingest behaves

Live

Batch-friendly

Fault-tolerant

Bounded

Get your ingest key

How ingest behaves