Skip to main content

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.

​
config.json

Located at brain/config.json, this file stores application-level settings. It’s read on startup and can be modified via the Settings UI or by editing the file directly.

​
Configuration Fields

{
  "mind": {
    "provider": "ollama",
    "model": "gemma3:4b"
  },
  "providers": {
    "anthropic": {
      "apiKey": "",
      "model": "claude-sonnet-4-20250514"
    },
    "openai": {
      "apiKey": "",
      "model": "gpt-4o"
    },
    "ollama": {
      "host": "http://localhost:11434",
      "model": "gemma3:4b"
    }
  },
  "language": "en"
}

​
Field Reference

FieldDescription
mind.providerActive LLM provider: anthropic, openai, or ollama
mind.modelActive model name
providers.anthropic.apiKeyAnthropic API key
providers.openai.apiKeyOpenAI API key
providers.ollama.hostOllama server URL (default: http://localhost:11434)
languageUI language: en (English) or ar (Arabic)

​
Provider Cascade

When the active provider fails, Wolffish cascades through alternatives: 
Claude → OpenAI → Ollama
Providers without configured API keys are skipped. Ollama is always available as the final fallback (assuming it’s running).
API keys are stored in plain text in config.json. This is by design — Wolffish is a local-first app and your workspace is your own. If you version-control your workspace with git, add brain/config.json to .gitignore.