Integrations Overview

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.

Recommended order

Start with the framework your production workload already uses.
If you are unsure, use the OpenAI SDK guide because it maps cleanly to most OpenAI-compatible clients.
Add the Xenovia Python SDK when you need policy checks around downstream actions.

Agent endpoint integrations

Every agent has an OpenAI-compatible endpoint on the Xenovia runtime. Any client that accepts a custom base_url works without further changes, and every call passes through Xenovia’s policy and trace pipeline.

https://runtime.xenovia.io/{agent_id}/v1

Provider credentials are configured on the agent and resolved server-side. So is the model: the model field in your request is replaced with the model configured on the agent. Use your framework’s OpenAI-compatible client for every supported provider, including Anthropic, Bedrock, Vertex AI, Microsoft Foundry and Gemini; provider-native SDKs use different API paths and cannot target the endpoint.

OpenAI SDK

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

LangChain

Python and JS chains, agents, and RAG pipelines.

LlamaIndex

RAG pipelines and agentic query engines.

OpenAI Agents SDK

Multi-agent orchestration with the Responses API.

Vercel AI SDK

Next.js and edge streaming.

AutoGen / CrewAI

Multi-agent frameworks that can sit on top of an OpenAI-compatible endpoint.

SDK hooks

The Xenovia Python SDK (pip install "xenovia-sdk>=0.2.1") checks agent actions such as tool calls, tool results, memory writes, and context summaries against the same agent’s controls, through POST /v1/execute on the runtime with the agent’s xe_ key.

from xenovia_sdk import Xenovia

xenovia = Xenovia(api_key="xe_...", auto_session=True)

@xenovia.guard(operation="payments.transfer")
def transfer_funds(amount: int, to: str) -> dict:
    return run_transfer(amount, to)

response = transfer_funds(500, "acct_123")  # a XenoviaResponse
if response.is_success():
    receipt = response.result  # what transfer_funds returned

Model and tool-call checks run the agent’s policies and guardrails; tool-result, memory-write, and context-summary checks run guardrails only.

Xenovia Python SDK

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

Choose the right guide

	Agent endpoint	SDK hooks
What is governed	Every LLM call through the endpoint	Agent actions such as tool calls, memory writes, and summaries
Code change required	`base_url` swap only	A hook, `execute()` call, or `@guard()` decorator
Policy input	Full LLM request context	Stage, operation, and payload
Trace contains	LLM request and response, tokens, latency, tool calls	Operation, stage, payload, decision, and session
Session tracking	Automatic via Xenovia session resolution	Explicit `session_id` or `auto_session=True`

Use both together: the endpoint for LLM governance, the SDK 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/{agent_id}/v1.
If the framework makes risky local calls after the model response, add the Xenovia Python SDK alongside it.

Supported endpoint paths

Endpoint	Use case
`POST /v1/chat/completions`	Chat, agents, tool calling
`POST /v1/responses`	OpenAI Agents SDK and multi-step runs

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.

Start Here

Integrations

Platform

Integrations Overview

Recommended order

Agent endpoint integrations

OpenAI SDK

LangChain

LlamaIndex

OpenAI Agents SDK

Vercel AI SDK

AutoGen / CrewAI

SDK hooks

Xenovia Python SDK

Choose the right guide

If your framework is not listed

Supported endpoint paths

​Recommended order

​Agent endpoint integrations

OpenAI SDK

LangChain

LlamaIndex

OpenAI Agents SDK

Vercel AI SDK

AutoGen / CrewAI

​SDK hooks

Xenovia Python SDK

​Choose the right guide

​If your framework is not listed

​Supported endpoint paths

Recommended order

Agent endpoint integrations

SDK hooks

Choose the right guide

If your framework is not listed

Supported endpoint paths