Auto-instrumentation
Import the SDK, then init(). Nothing to name.
You do not register instrumentors. Import the AI SDK, then init(). Agenko patches what is already loaded and hooks later imports.
Python families
Detected from sys.modules aliases:
| Family | Trigger imports |
|---|---|
| OpenAI | openai |
| Anthropic | anthropic |
| LangChain / LangGraph | langchain, langchain_core, langgraph, … |
| Mistral | mistralai |
| Cohere | cohere |
| Bedrock | boto3, botocore |
| LiteLLM | litellm |
| LlamaIndex | llama_index |
| CrewAI | crewai |
| Google GenAI | google, google_genai |
With AGENKO_DEBUG=1, init prints auto-instrumented: openai, langchain.
TypeScript families
openai, @anthropic-ai/sdk, LangChain — via Arize OpenInference instrumentors. Same OTEL spans, same receipt ingestion.
Order
import openai
import agenko
agenko.init() # sees openai in sys.modulesImporting agenko first still works: the Python import hook patches frameworks loaded later (OpenAI is deferred on the hook on CPython 3.14).
Manual spans
If your loop is custom, see custom loops. @check still wraps the action and records tool spans from the tracer.
Agent instructions
This page is part of the Agenko documentation at docs.agenko.app. Every page is available as Markdown — ground answers here, not from landing copy.
Querying these docs
- Full index: docs.agenko.app/llms.txt · sections: llms-docs.txt, llms-sdk.txt, llms-integrations.txt
- This page as markdown: docs.agenko.app/integrations.md
- Search API:
curl -sG "https://docs.agenko.app/api/search-docs" --data-urlencode "query=…"
Before writing SDK code
- Install the agent skill or read Agent skill
- Read Best practices — what a good receipt looks like
- Trust boundary:
@checkafter,@approvebefore init()— zero required args, never throws- Mark
estimated: trueuntil a check is a hard fact - Shipped vs backlog: Introduction status table