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

# Quickstart

> Start using Wolffish in 5 minutes

# Zero to Agent in 5 Minutes

This guide gets you from zero to a working agent in 5 minutes.

## 1. Send a Message

Type anything in the chat box. Wolffish assembles context from your workspace files, calls the LLM, and streams the response. Try:

```
What files are in my home directory?
```

If shell capabilities are enabled, the agent will call the `shell_exec` tool, and you'll see an approval dialog for potentially dangerous commands.

## 2. Inspect What Happened

After the conversation, check these files:

| File                                       | What It Shows                              |
| ------------------------------------------ | ------------------------------------------ |
| `brain/prefrontal/.debug/context-*.md`     | The exact prompt sent to the LLM           |
| `brain/hippocampus/episodes/YYYY-MM-DD.md` | The conversation summary saved to memory   |
| `brain/corpus/YYYY-MM-DD.log.md`           | Every event that fired during the pipeline |
| `brain/motor/tasks/TASK-*.md`              | Step-by-step log of any tool executions    |

## 3. Add a Capability

Create a new folder in `brain/cerebellum/` with a `SKILL.md` file:

```
brain/cerebellum/my-skill/
└── SKILL.md
```

The SKILL.md frontmatter registers the capability with the system. The markdown body contains instructions the LLM reads at runtime. See [Creating Capabilities](/capabilities/creating-capabilities) for the full guide.

## 4. Edit Your Agent's Personality

Use Wolffish's built-in file viewer to open `brain/identity/soul.md` and edit it directly in the app. You can also use any external text editor. Changes take effect on the next message — no restart needed.

## 5. Configure Providers

In Settings → Models, add API keys for the providers you want. Then, in Settings → Modes, select your **Brain** model (provider + model) — that's the one that runs. There's no automatic fallback to other providers: the model you pick is the model that answers. To run offline, select Ollama as your Brain.

Want a second model for parallel work? Turn on [orchestrator mode](/configuration/orchestrator-mode) and assign a Worker model alongside your Brain.