Key concepts

This is the "how does this actually work?" section. The canonical URL is /docs/key-concepts. Same list, so a fetch of this snapshot still answers the question.

You do not have to read these in order. Linux first. Local hatch. Bring your own keys.

• The workspace: the assistant's brain is a folder of plain-text files on disk.
• Skills and tools: tools are atomic actions. Skills bundle tools plus instructions.
• Memory and context: persistent knowledge versus what fits in the current turn.
• Model profiles: which LLM runs which job. You bring the keys.
• Channels: desktop app, Telegram, Slack, phone, and other ways to talk.
• Scheduling: one-shot and recurring work on the assistant's clock.
• Web search: BYO Brave, Perplexity, Tavily, or Firecrawl. No Aevum-metered search in 0.1.
• OAuth integrations: connect Slack, Gmail, and other services with your credentials.
• Self-improving skills: completed work can become a reusable managed skill.

Next: Getting started, Skills reference.