What Gets Created
When Wolffish launches for the first time, it creates your workspace at~/.wolffish/workspace/ and copies the default configuration files from the bundled defaults. Here’s what gets created:
The Workspace
Onboarding Flow
Since v1.0.289 onboarding is a theme, a language, and then the chat — nothing else.- Appearance — pick a theme and a language.
- Chat. You land in the conversation.
- Provider Configuration — configure at least one provider before your first message: DeepSeek (recommended), Anthropic, OpenAI, or any of the others — or Ollama for local inference.
Ollama is no longer a step. A first run used to walk you from the welcome screen into install Ollama, and from there into pick your Ollama model — two full-screen pages carrying none of the app’s navigation, so anyone who simply did not want a local model had nowhere to go. Wolffish now treats Ollama as what it is: one optional provider among several. The model picker no longer exists as a screen at all; it is the Ollama panel of Settings → Models, where you go when you actually want it. Launch itself now asks Ollama nothing — no probe, no tag list, no quietly rewriting your configuration before the window is up.
Customizing Your Agent
After the initial setup, you’ll want to edit two files:user.md
Tell Wolffish about yourself — your name, preferences, projects, tech stack. The more context you provide, the more relevant the agent’s responses.
soul.md
Define the agent’s personality, tone, and behavioral guidelines. This is the character your agent takes on.
What Happens on Every Launch
After the first launch, each subsequent startup:- Reads
config.jsonfor model and provider settings - Initializes the 15 brain modules via the event bus (corpus)
- Indexes workspace markdown files into
cortex.db(SQLite FTS5) - Starts background processes (file watcher, cron scheduler)
- Checks provider health for the cloud APIs you configured (Ollama is watched in the background only once you have opted into it)