> For the complete documentation index, see [llms.txt](https://docs.zenml.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zenml.io/kitaru/adapters.md). # Adapters - [Overview](https://docs.zenml.io/kitaru/adapters/adapters.md): One wrapper, no rewrite. Adapters record your existing agent's runs as replayable sessions. - [Record in production](https://docs.zenml.io/kitaru/adapters/record-in-production.md): Take an adapter-wrapped agent to production: register it, give the service its own credential, and know exactly what recording does to your request path. - [Pydantic AI](https://docs.zenml.io/kitaru/adapters/pydantic-ai.md): Wrap any PydanticAI agent once with KitaruAgent. Every run records as a session, and the same wrapper executes replays. - [LangGraph](https://docs.zenml.io/kitaru/adapters/langgraph.md): Record LangGraph, LangChain, and Deep Agents invocations with the kitaru-langgraph adapter package - [OpenAI Agents SDK](https://docs.zenml.io/kitaru/adapters/openai-agents.md): Record and replay non-streaming OpenAI Agents SDK runs with the separately packaged Kitaru v2 adapter - [Claude Agent SDK](https://docs.zenml.io/kitaru/adapters/claude-agent-sdk.md): Record one-shot Claude Agent SDK queries and rerun them with prompt, model, and SDK MCP tool overrides - [Mastra](https://docs.zenml.io/kitaru/adapters/mastra.md): Record Mastra agent runs, import existing trace exports, and replay with recorded conversation context - [Vercel AI SDK](https://docs.zenml.io/kitaru/adapters/vercel-ai.md): Record and replay AI SDK 7 ToolLoopAgent and generateText calls with the Kitaru Vercel AI SDK adapter. - [Importer-backed adapters](https://docs.zenml.io/kitaru/adapters/importer-backed.md): Record runs of an agent that already reports to Langfuse, Braintrust, LangSmith, Logfire, or Arize Phoenix by importing each run's provider trace as a session - [No adapter for your framework](https://docs.zenml.io/kitaru/adapters/custom.md): No adapter for your framework? Import the traces you already have, or generate a project-local adapter with the adapter-builder skill. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.zenml.io/kitaru/adapters.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.