Skip to main content
If your stack can speak the OpenAI API, Xenovia usually fits with a base_url change. Start there unless you need to govern actions that happen outside the model call itself.
  1. Start with the framework your production workload already uses.
  2. If you are unsure, use the OpenAI SDK guide because it maps cleanly to most OpenAI-compatible clients.
  3. Add the Xenovia Python SDK when you need policy checks around downstream actions.

​
Proxy mode integrations

Xenovia Runtime is an OpenAI-compatible proxy. Any client that accepts a custom base_url works without further changes, and every call passes through Xenovia’s policy and trace pipeline.
Provider credentials are configured in the proxy and resolved server-side. So is the model: the model field in your request is replaced with the model configured on the proxy. Use your framework’s OpenAI-compatible client for every provider, including Anthropic, Groq, Bedrock, and Gemini; provider-native SDKs use different API paths and cannot target the proxy.

OpenAI SDK

OpenAI SDK badgePython and Node.js. Best default starting point for any OpenAI-compatible client.

LangChain

LangChain badgePython and JS chains, agents, and RAG pipelines.

LlamaIndex

LlamaIndex badgeRAG pipelines and agentic query engines.

OpenAI Agents SDK

OpenAI Agents badgeMulti-agent orchestration with the Responses API.

Vercel AI SDK

Vercel AI SDK badgeNext.js and edge streaming.

AutoGen / CrewAI

AutoGen and CrewAI badgeMulti-agent frameworks that can sit on top of an OpenAI-compatible endpoint.

​
SDK mode

The Xenovia Python SDK (pip install xenovia-sdk) gates arbitrary agent actions such as tool calls, database writes, API requests, and file operations without proxying an LLM call.
The SDK’s hosted decision endpoint (POST /v1/execute) is not live yet, so SDK mode cannot evaluate policy today. See the SDK page for the exact behaviour of each unreachable_mode.

Xenovia Python SDK

Xenovia SDK badgeFull SDK reference for execute(), @guard(), session handling, and error behavior.

​
Choose the right guide

Use both together: proxy mode for LLM governance, SDK mode for downstream tool governance.

​
If your framework is not listed

  • If it accepts an OpenAI-compatible base_url, start from the OpenAI SDK guide.
  • If it only needs HTTP access, point it at https://runtime.xenovia.io/{proxy_id}/v1.
  • If the framework makes risky local calls after the model response, add the Xenovia Python SDK alongside it.

​
Supported proxy endpoints

Embeddings (/v1/embeddings), legacy completions (/v1/completions), and model listing (/v1/models) are not exposed by the runtime today and return 404. Send embedding calls directly to your provider until they are supported.