Skip to main content
Use Adaline Integrations when your application already runs through an AI framework, provider SDK, gateway, or OpenTelemetry pipeline. Integrations let you keep your existing application structure while sending logs, traces, spans, model calls, tool calls, retrieval steps, and agent activity into Adaline. This path is best when you want to observe production traffic without hand-building every trace and span yourself.

​
When to use integrations

Use caseStart here
You use LangChain, LangGraph, LlamaIndex, DSPy, LiteLLM, Pydantic AI, AutoGen, CrewAI, Mastra, Vercel AI SDK, or OpenTelemetry.Framework integrations
You want to connect provider traffic from OpenAI, Anthropic, Google, Vertex AI, Azure, Bedrock, Groq, OpenRouter, Together AI, xAI, or another supported provider.AI provider integrations
You want the fastest provider-compatible logging path by changing the base URL.With Adaline Proxy
You need complete control over custom traces, spans, sessions, variables, and metadata.With Adaline SDKs or With Adaline API

​
What integrations should capture

A good integration sends enough information for Adaline to understand what happened and improve the agent later:
  • Trace and span names that describe the workflow.
  • Model requests and responses.
  • Tool calls, arguments, responses, and status.
  • Retrieval, embedding, guardrail, command, or custom workflow spans when available.
  • Latency, token usage, cost, model, and provider details.
  • Session, environment, release, route, prompt, agent, and customer-safe metadata.
  • User feedback or application outcome when you can safely send it.

​
Browse integrations

All integrations

Browse Adaline integrations for AI providers, frameworks, gateways, agents, and OpenTelemetry.

OpenTelemetry

Send OTLP traces from OpenTelemetry-compatible applications into Adaline.
https://mintcdn.com/adaline/Um_T8BffW4hfcoYD/images/icons/langchain.svg?fit=max&auto=format&n=Um_T8BffW4hfcoYD&q=85&s=0133af6154fe31fefda23420a6478ace

LangChain

Observe LangChain chains, tools, retrieval, and model calls in Adaline.
https://mintcdn.com/adaline/Um_T8BffW4hfcoYD/images/icons/langgraph.svg?fit=max&auto=format&n=Um_T8BffW4hfcoYD&q=85&s=1d6dd52f67db7747f003fd49c84c25b0

LangGraph

Capture stateful graph execution, agent steps, and tool use.
https://mintcdn.com/adaline/asQy_HFY3PYbBCEt/images/icons/vercel-ai.svg?fit=max&auto=format&n=asQy_HFY3PYbBCEt&q=85&s=bc57c08fe97ca9f2cac62016bfca1ca7

Vercel AI SDK

Observe generateText, streamText, tool calls, and multi-step AI SDK flows.
https://mintcdn.com/adaline/asQy_HFY3PYbBCEt/images/icons/litellm.svg?fit=max&auto=format&n=asQy_HFY3PYbBCEt&q=85&s=c85c55824791ea3f146e5fe3245a53a3

LiteLLM

Attach Adaline while keeping your existing LiteLLM provider routing.

​
Verify the integration

After wiring an integration, run one known request in staging and confirm:
  1. The request appears in Logs.
  2. The trace has readable spans for model calls, tools, retrieval, or agent steps.
  3. The trace includes environment, route, release, prompt, or agent metadata.
  4. Tokens, latency, cost, model, and provider details appear where supported.
  5. Sessions or Behaviors become useful once enough production traffic arrives.
If the integration does not expose the level of detail you need, use With Adaline SDKs, With Adaline API, or Advanced usage for more control.