> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runagain.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# RunAgain

> Observe and evaluate your agents. Traces, eval scores, and regression diffs — straight to your dashboard and CLI.

RunAgain is an **observability + evaluation platform** for LLM agents. Point any
OpenTelemetry-instrumented agent at RunAgain and get full-fidelity traces, eval
scores, drift detection, and regression diffs — for agents built on the
**Claude Agent SDK**, the **Vercel AI SDK**, or driven from **Claude Code** in
your terminal.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Send your first trace in a couple of minutes.
  </Card>

  <Card title="Trace Claude Code" icon="terminal" href="/integrations/claude-code">
    Capture your terminal Claude Code sessions as traces.
  </Card>

  <Card title="Observability" icon="eye" href="/concepts/observability">
    How traces, spans, and observation types work.
  </Card>

  <Card title="Evaluations" icon="list-checks" href="/concepts/evaluations">
    LLM-judge, assertion, rubric, and dataset scoring.
  </Card>
</CardGroup>

## What you get

<CardGroup cols={3}>
  <Card title="Observability" icon="eye">
    Full-fidelity traces of every run, tool call, token and latency.
  </Card>

  <Card title="Evaluations" icon="list-checks">
    LLM-judge, assertion, rubric and dataset scoring — or bring your own.
  </Card>

  <Card title="Drift detection" icon="git-compare-arrows">
    Catch quality, latency and cost drifting from baseline.
  </Card>

  <Card title="Tool-call mocking" icon="webhook">
    Freeze flaky or paid APIs so eval runs stay deterministic.
  </Card>

  <Card title="Tool simulation" icon="flask-conical">
    Stress-test how your agent reacts to simulated tools.
  </Card>

  <Card title="Datasets & experiments" icon="database">
    Version datasets and score experiments against a baseline.
  </Card>
</CardGroup>

## How it works

<Steps>
  <Step title="Instrument your agent">
    Add the RunAgain SDK, the Vercel AI SDK telemetry exporter, or enable
    Claude Code's OpenTelemetry — all speak OTLP.
  </Step>

  <Step title="Traces stream to RunAgain">
    Spans are ingested over OTLP/HTTP at `https://ingest.runagain.ai`,
    authenticated with a project API key.
  </Step>

  <Step title="Observe, score, and iterate">
    View traces, run evals, watch for drift, and compare experiments in the
    dashboard at [app.runagain.ai](https://app.runagain.ai).
  </Step>
</Steps>

Ready? Head to the [Quickstart](/quickstart).