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

# Framework integrations

> Choose an integration for Vercel AI SDK, LangChain, LangGraph, or Deep Agents.

Connect Silmaril to the framework that runs your model or orchestrates your agent.

Start with the [TypeScript SDK](https://silmaril.dev/docs/sdk/typescript.md) or [Python SDK](https://silmaril.dev/docs/sdk/python.md), then add the integration for your framework.

> [card] [Vercel AI SDK](https://silmaril.dev/docs/sdk/vercel-ai.md)
>
> Check model input with middleware and classify generated text before returning it.

> [card] [LangChain and LangGraph](https://silmaril.dev/docs/sdk/langchain.md)
>
> Add callback handlers to model calls and graph execution in TypeScript or Python.

> [card] [Deep Agents](https://silmaril.dev/docs/integrations/deep-agents.md)
>
> Protect root agents, tool execution, and subagent graphs.

For organization-level Claude protection or gateway-routed model traffic, choose [Claude Enterprise, LiteLLM, or Vercel AI Gateway](https://silmaril.dev/docs/gateways/overview.md).

[Verify your integration](https://silmaril.dev/docs/start/verify.md) after setup and choose the [enforcement mode](https://silmaril.dev/docs/guides/enforcement.md) for each connected boundary.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.