sigil-cc

Grafana AI observability SDK

Grafana AI observability is a product from Grafana for teams running agents in production. This repo holds the open-source SDKs and the coding-agent plugins that send telemetry to it.

Quick start (with an AI coding agent)

Drop llms.txt into your repo and ask your agent what you want. It handles either case, depending on what your repo is:

• Instrument this codebase with Grafana AI observability: the agent wires the SDK into your app or agent code.
• Set up Grafana AI observability for my coding agent: the agent installs one of the plugins/ launchers to capture sessions from popular coding agents.

Or open the AI Observability plugin in your Grafana Cloud stack and use the onboarding wizard.

Quick start (manual)

Set the AGENTO11Y_* env vars and construct the client. To configure it explicitly instead, see the per-SDK READMEs linked under SDKs.

TypeScript

import { Agento11yClient } from "@grafana/agento11y";

const client = new Agento11yClient(); // reads AGENTO11Y_* env vars

await client.startGeneration(
  { conversationId: "conv-1", model: { provider: "openai", name: "gpt-5" } },
  async (recorder) => {
    recorder.setResult({ output: [{ role: "assistant", content: "Hello" }] });
  },
);

await client.shutdown();

Python

from agento11y import Client, GenerationStart, ModelRef, assistant_text_message

client = Client()  # reads AGENTO11Y_* env vars

with client.start_generation(
    GenerationStart(
        conversation_id="conv-1",
        model=ModelRef(provider="openai", name="gpt-5"),
    )
) as rec:
    rec.set_result(output=[assistant_text_message("Hello")])

client.shutdown()

Go

client := agento11y.NewClient(agento11y.Config{}) // reads AGENTO11Y_* env vars
defer func() { _ = client.Shutdown(context.Background()) }()

ctx, rec := client.StartGeneration(context.Background(), agento11y.GenerationStart{
    ConversationID: "conv-1",
    Model:          agento11y.ModelRef{Provider: "openai", Name: "gpt-5"},
})
defer rec.End()

rec.SetResult(agento11y.Generation{
    Output: []agento11y.Message{agento11y.AssistantTextMessage("Hello from Grafana AI observability")},
}, nil)

SDKs

Language	Package	Path
Go	github.com/grafana/agento11y/go	go/
Python	agento11y	python/
TypeScript/JavaScript	@grafana/agento11y	js/
.NET/C#	Grafana.Agento11y	dotnet/
Java	com.grafana.agento11y	java/

Provider adapters

Language	Providers	Where
Go	Anthropic, OpenAI, Gemini	go-providers/
Python	Anthropic, OpenAI, Gemini	python-providers/
Java	Anthropic, OpenAI, Gemini	java/providers/
.NET	Anthropic, OpenAI, Gemini	dotnet/src/
TypeScript/JavaScript	Anthropic, OpenAI, Gemini	Subpath exports of @grafana/agento11y. See js/README.md.

Framework integrations

Language	Frameworks	Where
Python	LangChain, LangGraph, OpenAI Agents, LlamaIndex, Google ADK, Strands Agents, Claude Agent SDK, LiteLLM, Pydantic AI	python-frameworks/
TypeScript/JavaScript	LangChain, LangGraph, OpenAI Agents, LlamaIndex, Google ADK, Strands, Vercel AI SDK	Subpath exports of @grafana/agento11y. See js/README.md.
Go	Google ADK	go-frameworks/
Java	Google ADK	java/frameworks/

Runnable examples

Self-contained examples grouped into three tiers. See examples/README.md for the full map.

The getting-started quickstarts each make a real LLM call and record the generation to Grafana AI observability.