Integrations

Runback sits above your stack.

It doesn't replace LangChain, CrewAI, or the AI SDK — it governs whatever you built on top of them. Use the SDK for the deepest capture, or send traces from any framework over OpenTelemetry.

LLM Providers
OpenAI
Anthropic
Gemini
Meta / Llama
Mistral AI
Hugging Face
Agent Frameworks
Vercel AI SDK
LangChain
CrewAI
Ollama
Instrumentation
OpenTelemetry
Python
TypeScript
Your agentsLangChainCrewAIVercel AI SDKyour own loop
One line in
OpenTelemetry
or @runback/sdk
Runback
ObserveReplayGateAudit

Whatever the framework, you can drill into any step:

research-email-agent · run failedclick any step ↓
Tool call · send_email — failed here
tool
send_email
status
error
input
{ "to": "alex[at]acme.co", "body": "Next.js 16 summary…" }
Invalid recipient — the model wrote the address in plain text ("[at]") instead of a valid email. The run failed here.
Using a specific model? Runback is model-agnostic.
OpenAIAnthropicLlamaMistralGeminiCohereGroqBedrock

Whatever model you call, Runback records it automatically — the inspector and monitoring don't care which provider you use. Stepreplay — re-running a captured step against a live model — supports OpenAI, Anthropic, and Groq-hosted open models today; more providers are on the roadmap.

The deepest path

Vercel AI SDKNative SDK · deepest

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" });

Not sure which of the three integration paths fits your setup? Read the full walkthrough →

Any framework, via OpenTelemetry

Point your OTLP trace exporter at Runback. Every example below also needs these three environment variables:

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>"
OpenAI / Anthropic SDKsOpenTelemetry · Python or JS

Auto-instrument the official SDKs with OpenLLMetry. 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
LangChain & LangGraphOpenTelemetry

Instrument with OpenInference (or OpenLLMetry) and point the OTLP exporter at Runback.

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

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

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.
LlamaIndexOpenTelemetry

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

pip install openinference-instrumentation-llama-index
# LlamaIndexInstrumentor().instrument(); then the env vars below.
Anything else (raw OpenTelemetry)OpenTelemetry · any language

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>"
Don't see your tool?

If it speaks OpenTelemetry GenAI conventions, it already works. Tell us what you use and we'll confirm the mapping — read the guide or open a live run.

Then it connects out to your stack.

Capture is half the story. Runback pushes the record into the systems your organization already runs — so it's governance that lives in your ecosystem, not another console to check.

Identitynative
Okta · Azure AD / Entra · Google Workspace · Auth0

SSO via OIDC, domain-routed, with provisioning.

CI / CDnative
GitHub Actions · GitLab CI · Jenkins

The eval release gate runs in your pipeline and fails the build on a regression.

Incident & chatalerts · webhooks
Slack · PagerDuty · Opsgenie · Microsoft Teams

Alert rules route failures and error-rate spikes to email, Slack, or any webhook.

Regulatory evidenceread-only API
EAAPL — AU Enterprise AI Patterns

A scoped, read-only key exposes your live EU AI Act / ISO 42001 / NIST AI RMF / APRA CPS 230 control status to EAAPL's evidence pack. No ingest, no run content.

SIEM & observabilityopen API · webhooks
Splunk · Datadog · Elastic

Stream run summaries, audit records, and ledger checkpoints out via the REST API and outbound webhooks.

Data warehouseAPI · export
Snowflake · BigQuery · S3

Export signed audit records and run data to your lake for retention and analytics.

Your cloudself-host
AWS · Azure · GCP · on-prem

Self-host the whole platform in your perimeter — your data never leaves.

Don't see yours? Everything is reachable through the open REST API and outbound webhooks — tell us what you runand we'll confirm the wiring.

Need audit coverage inside an AU regulatory evidence pack? See the EAAPL integration →