Runback sits above your stack.

The richest integration — full context capture, in-process redaction, and step replay. About three lines.

import { withDebugger } from "@runback/sdk";
import { generateText, stepCountIs } from "ai";

const dbg = withDebugger(model, { runName: "agent", redact: "standard" });
const res = await generateText({
  model: dbg.model,
  tools: dbg.tools(myTools),
  stopWhen: stepCountIs(8),
  prompt: task,
});
await dbg.finish({ output: res.text, status: "success" });

Real node identity, execution order, and state — captured via LangChain's own callback system, not a generic OpenTelemetry flatten that loses the graph's shape. Same tamper-evident digest as every other Runback SDK.

pip install "runback-sdk[langgraph]"

from runback import RunbackCallbackHandler

handler = RunbackCallbackHandler(run_name="my-graph")
result = graph.invoke(inputs, config={"callbacks": [handler]})
handler.finish()

Auto-instrument the official SDKs with OpenLLMetry — the open-source standard Traceloop maintains. No changes to your calls.

pip install traceloop-sdk

from traceloop.sdk import Traceloop
Traceloop.init(
  api_endpoint="https://runback.dev/api/otel",
  headers={"authorization": "Bearer <RUNBACK_API_KEY>"},
)
# your openai / anthropic calls are now traced to Runback

Already on Traceloop's hosted platform? See how it compares →

Instrument with OpenInference (or OpenLLMetry) and point the OTLP exporter at Runback. Building with LangGraph specifically? Use the native SDK above — generic OTel can't preserve a graph's node identity or state, only a plain chain's.

pip install openinference-instrumentation-langchain \
            opentelemetry-exporter-otlp-proto-http

# then export the env vars below, and:
#   LangChainInstrumentor().instrument()

OpenLLMetry instruments CrewAI agents, tasks, and tool calls out of the box.

pip install traceloop-sdk
# Traceloop.init(...) as above — CrewAI spans flow straight in.

Trace queries, retrievers, and LLM calls via OpenInference or OpenLLMetry.

pip install openinference-instrumentation-llama-index
# LlamaIndexInstrumentor().instrument(); then the env vars below.

If it emits GenAI spans, Runback reads it. Set three environment variables and go.

export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT="https://runback.dev/api/otel/v1/traces"
export OTEL_EXPORTER_OTLP_TRACES_PROTOCOL="http/json"
export OTEL_EXPORTER_OTLP_TRACES_HEADERS="authorization=Bearer <RUNBACK_API_KEY>"