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

# Introduction

> Raindrop is the monitoring platform for AI agents. Similar to how Sentry tracks errors in your web apps, Raindrop discovers silent agent failures in production.

<Frame>
  <img src="https://mintcdn.com/dawn-a6c57108/4PiD001nHi1Adeom/images/home-overview.png?fit=max&auto=format&n=4PiD001nHi1Adeom&q=85&s=a424a4ded3a62ef6dc5d5779779f55f3" alt="Raindrop home dashboard" width="3840" height="2160" data-path="images/home-overview.png" />
</Frame>

AI agents fail differently than traditional software. A 500 error is obvious. An agent that confidently gives wrong information, forgets what a user said 3 messages ago, or takes a bad path fails silently, invisible to traditional monitoring.

Raindrop helps you:

* **Visualize agent trajectories**: see every tool call, error, and recovery in seconds
* **Detect issues automatically**: choose from presets that catch forgetting, user frustration, and task failures
* **Search across millions of interactions**: find issues in production data with natural language
* **Track custom signals**: define any signal you care about (syntax errors, aesthetic complaints, an agent stuck in a loop) and track it at scale
* **A/B test your agents**: run experiments to validate that fixes actually worked

## Quickstart

Run this in your project directory:

```bash theme={null}
curl -fsSL https://raindrop.sh/install | bash -s -- --cloud
```

It installs the `raindrop` CLI and runs `raindrop cloud setup`, which:

1. Signs you in to Raindrop in the browser.
2. Writes your org write key to `./.env` as `RAINDROP_WRITE_KEY`.
3. Installs the [`raindrop-setup` and `raindrop-investigate` skills](/docs/integrations/skills) and the hosted [MCP server](/docs/mcp/overview) into your coding agents (Claude Code, Cursor, Codex, and others).

Then run `/raindrop-setup` in your coding agent. It finds your AI call sites, instruments them, and checks that events reach Raindrop.

<Tip>
  To send events to a specific [project](/docs/platform/projects), append `--project <slug>`. Setup then prints a prompt to paste into your coding agent in place of `/raindrop-setup`, and the skill writes the slug into your SDK call. The **Get started** page in the dashboard gives you this command with the project already filled in.
</Tip>

Prefer to wire it up yourself? Pick an SDK or integration below.

## Integrate Raindrop

<CardGroup cols={2}>
  <Card title="TypeScript" icon="file-code" href="/docs/sdk/typescript">
    Full-featured SDK with tracing support for Node.js and edge runtimes.
  </Card>

  <Card title="Python" icon="python" href="/docs/sdk/python">
    Native Python SDK for FastAPI, Django, and other Python frameworks.
  </Card>

  <Card title="HTTP API" icon="code" href="/docs/sdk/http-api">
    RESTful API for any language or platform.
  </Card>

  <Card title="Integrations" icon="puzzle-piece" href="/docs/integrations/overview">
    Connect Raindrop with AI frameworks, cloud providers, and developer tools.
  </Card>
</CardGroup>

## Core Features

<CardGroup cols={2}>
  <Card title="Signals" icon="signal" href="/docs/platform/signals">
    Ground truth indicators for agent performance. Track wins, failures, and custom behaviors across all your interactions.
  </Card>

  <Card title="Triage Agent" icon="robot" href="/docs/platform/triage-agent">
    An agent that investigates your AI agents in Slack, on the web, and as an MCP.
  </Card>

  <Card title="Issues" icon="triangle-exclamation" href="/docs/platform/issues">
    Automatic detection of broader distribution changes worth investigating.
  </Card>

  <Card title="Experiments" icon="flask" href="/docs/platform/experiments">
    A/B test your agents to validate changes. Compare models, prompts, and configurations.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.