> ## Documentation Index
> Fetch the complete documentation index at: https://apie.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Integrations

> Choose the right Apie integration helper for your agent framework or platform.

You use a specific framework — LangChain, OpenAI Agents, CrewAI — or connect to platforms like GitHub and PagerDuty. Apie provides thin wrappers that map framework events to Apie telemetry and guardrails.

Pick your framework below. Every integration page shows TypeScript and Python examples with minimal and production metadata variants.

## Decision matrix

| Your runtime                      | Integration                                                            | Effort         |
| --------------------------------- | ---------------------------------------------------------------------- | -------------- |
| MCP host (Cursor, Claude Desktop) | [MCP proxy](/mcp/proxy)                                                | Config only    |
| LangChain / LangGraph             | [LangChain](/integrations/langchain)                                   | \~5 lines      |
| OpenAI Agents SDK                 | [OpenAI Agents](/integrations/openai-agents)                           | \~5 lines      |
| OpenAI / Anthropic tool calls     | [LLM tool calls](/integrations/llm-tool-calls)                         | Per tool call  |
| CrewAI / AutoGen / LlamaIndex     | [CrewAI, AutoGen, LlamaIndex](/integrations/crewai-autogen-llamaindex) | Per step       |
| Vercel AI SDK                     | [Vercel AI](/integrations/vercel-ai)                                   | Per generation |
| GitHub, PagerDuty, Linear, etc.   | [Platform connectors](/integrations/platform-connectors)               | Per action     |
| Custom agent                      | [Choose how to instrument](/getting-started/choose-how-to-instrument)  | Varies         |

## Common pattern

All framework integrations follow the same pattern:

1. Create an Apie client and call `ready()`
2. Open a run with `withRun` / `with_run`
3. Pass the Apie handler or hooks to your framework inside the run
4. Framework events are tracked automatically

<CodeGroup>
  ```ts TypeScript theme={null}
  import apie from "./apie.config";
  import { ApieCallbackHandler } from "@apie-sh/sdk/integrations";

  await apie.ready();

  const handler = new ApieCallbackHandler(apie, {
    defaultEnvironment: "production",
  });

  await apie.withRun({ inputSummary: "Process request" }, async () => {
    // Pass handler to your framework
    await agent.invoke(input, { callbacks: [handler] });
  });
  ```

  ```python Python theme={null}
  from apie.config import apie
  from apie import ApieCallbackHandler

  apie.ready()

  handler = ApieCallbackHandler(apie, default_environment="production")

  def run_agent(run):
      # Pass handler to your framework
      agent.invoke(input, callbacks=[handler])

  apie.with_run({"inputSummary": "Process request"}, run_agent)
  ```
</CodeGroup>

## Import paths

<CodeGroup>
  ```ts TypeScript theme={null}
  import { ApieCallbackHandler, createApieRunHooks } from "@apie-sh/sdk/integrations";
  // or from main package:
  import { withOpenAIToolCall } from "@apie-sh/sdk";
  ```

  ```python Python theme={null}
  from apie import ApieCallbackHandler, with_openai_tool_call
  # or:
  from apie.integrations.langchain import ApieCallbackHandler
  ```
</CodeGroup>

## Framework guides

<CardGroup cols={2}>
  <Card title="LangChain / LangGraph" icon="link" href="/integrations/langchain">
    Callback handler and graph node wrappers.
  </Card>

  <Card title="OpenAI Agents" icon="robot" href="/integrations/openai-agents">
    Run hooks for agent lifecycle.
  </Card>

  <Card title="LLM tool calls" icon="message" href="/integrations/llm-tool-calls">
    OpenAI and Anthropic native tools.
  </Card>

  <Card title="CrewAI, AutoGen, LlamaIndex" icon="users" href="/integrations/crewai-autogen-llamaindex">
    Task and step wrappers.
  </Card>

  <Card title="Platform connectors" icon="building" href="/integrations/platform-connectors">
    GitHub, PagerDuty, Linear, observability.
  </Card>

  <Card title="Vercel AI" icon="bolt" href="/integrations/vercel-ai">
    Generation tracking.
  </Card>
</CardGroup>