Quickstart

From nothing to a visible trace in one sitting. Rius needs three things: an account, an API key, and two lines of instrumentation.

1. Sign in

Open eu.console.rius-glassflow.com  and click Continue. Sign in with your work email, or create an account if this is your first visit. You land in your default workspace.

2. Create an API key

The Get started page generates an instrumentation prompt you can paste straight into Claude Code, which installs the SDK and wires the key in for you. To do it by hand instead, keep following this page.

Click Create API key and name the key after the agent or environment that uses it:

The full key is shown exactly once. The server stores only a hash, so copy it into your secret manager now; if you lose it, revoke the key and issue a new one.

3. Instrument your agent

pip install "glassflow-rius[anthropic]" anthropic

import anthropic
import rius
 
rius.init(api_key="gf_...", service_name="my-agent")
claude = anthropic.Anthropic()  # reads ANTHROPIC_API_KEY
 
@rius.observe
def handle(query: str) -> str:
    response = claude.messages.create(
        model="claude-haiku-4-5-20251001",
        max_tokens=200,
        messages=[{"role": "user", "content": query}],
    )
    return response.content[0].text
 
handle("What should I check when a collector drops spans?")

npm install @glassflow-ai/rius @opentelemetry/api @anthropic-ai/sdk \
  @arizeai/openinference-instrumentation-anthropic

import Anthropic from '@anthropic-ai/sdk'
import { init, observe } from '@glassflow-ai/rius'
 
const rius = init({ apiKey: 'gf_...', serviceName: 'my-agent' })
await rius.ready  // auto-instrumentation is attached before the first call
 
const claude = new Anthropic()  // reads ANTHROPIC_API_KEY
 
const handle = observe(async function handle(query: string) {
  const message = await claude.messages.create({
    model: 'claude-haiku-4-5-20251001',
    max_tokens: 200,
    messages: [{ role: 'user', content: query }],
  })
  const [block] = message.content
  return block.type === 'text' ? block.text : ''
})
 
await handle('What should I check when a collector drops spans?')

init once at startup, then wrap the functions that make up your agent’s steps: @rius.observe in Python, observe() in TypeScript. The Anthropic call needs nothing at the call site: auto-instrumentation picks it up and emits the generation span, so the trace you are about to see carries the model, token counts, and cost. The configuration reference covers everything init accepts.

4. Run it and watch the trace arrive

Run your agent once, any run counts. The Traces view checks for new traces automatically, no reload needed:

Open the trace to see every step on the waterfall, including token counts, cost, and any errors along the way:

Next steps

• Exploring traces: the waterfall, the map view, and span detail in depth.
• MCP: connect Claude, Cursor, or your editor and query the traces you just sent in plain language.
• SDK: instrumentation beyond the basics, privacy controls, sampling.
• Monitoring live agents: add heartbeat=True to init() and the Agents view shows whether your agent is alive between runs.