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

# Introduction

> The ticket-oriented workspace for agentic debugging. Learn how to solve backlog bugs through evidence correlation and compound engineering.

# Welcome to OpenBug Documentation

### Get started in 30 seconds

**Prerequisites**

* Node.js 20+ installed
* An OpenBug account and API key from the dashboard ([`app.oncall.build`](https://app.oncall.build/))

#### Install OpenBug CLI

```bash theme={null}
npm install -g @openbug/cli
```

#### Start using OpenBug CLI

```bash theme={null}
cd your-project

# One-time setup per machine
debug login <your-api-key>

# Start OpenBug Cli
debug

# Start your app under OpenBug's debugger
debug npm run dev
```

On first use, `debug login` stores your API key in `~/.openbug/config`. After that, you can prefix any command with `debug` to launch the interactive logs. For AI chat interface run `debug`.

<Note>
  Continue with:

  * [**Quickstart**](/quickstart) — step-by-step guide to your first AI-assisted session
  * [**Common workflows**](/development) — real-world debugging patterns for single and multi-service apps
  * [**Troubleshooting**](/build-with-openbug/troubleshooting) — installation and setup tips if you run into issues
</Note>

### What it does for you

* **Real-time debugging:** run any command through OpenBug CLI, stream logs live, and ask the AI to explain failures or propose fixes while the process runs.
* **Multi-service log Q\&A:** query logs across multiple services that share the same project ID (frontend, backend, workers, microservices).
* **Contextual code inspection:** let the AI read targeted slices of code (when code\_available: true) to explain or fix issues it detects in logs.
* **Cross-service correlation:** with the local cluster server, AI can reason across all registered services in a project, pick which service to inspect, and trace issues end to end.
* **Tooling you control:** AI uses local tools (read\_file, grep\_search, tail\_logs, grep\_logs, get\_recent\_errors, read\_logs) and respects logs\_available / code\_available flags.

### Why devs love OpenBug CLI

* Works in the terminal you already use (Ink-based UI with split panes for logs and AI chat; keyboard shortcuts for focus, view toggles, clearing panes).
* **Live log awareness:** logs are captured character-by-character via node-pty, so AI always has the freshest context without reloading.
* **Flexible access control:** per-service openbug.yaml flags gate code and log access; safe for production (log-only) or full-access development.
* **Multi-service ready:** cluster mode groups services by project ID, enabling unified debugging across devices or pods with minimal setup.
* **Concrete, actionable help:** AI doesn’t just diagnose; it reads code (when allowed), searches it, inspects logs, and returns specific fixes or steps.