The Aither World Guide
From "what is an agent?" to a terminal that answers you - one path, nothing skipped.
Welcome to Aither World
What Aitherium, AitherOS and the aw* bricks are - in plain words, before you install anything.
about 5 min · 0 commandsChapter 1Install awdk
One command puts the whole kit on your machine. Then you check it worked.
about 10 min · 5 commandsChapter 2Your first local brain
Run an open model on your own computer, offline. Learn what "8B" and "1-bit" actually mean.
about 20 min · 2 commandsChapter 3Talk to it
Ask your brain one question, then open a chat. Optionally connect to the cloud for the bigger brains.
about 15 min · 4 commandsChapter 4Build your first agent
An agent is a brain plus tools plus a job. You will scaffold one in three files and watch it use a tool.
about 30 min · 4 commandsChapter 5Agent packs
Someone already built the agent you want. Find it, install it, run it - and know what is still coming.
about 15 min · 3 commandsChapter 6Your own hardware
CPU or GPU, laptop or rack - how the open model stack picks a model for what you have, and how a brain gets registered.
about 30 min · 3 commandsChapter 7Deploy on awnix
An immutable Linux built for machines where software writes software. Your agent becomes three lines in a Dockerfile.
about 45 min · 5 commandsChapter 8Many agents, one repo
Two agents editing the same code without sweeping each other's work - leases, a call graph, messaging, memory.
about 30 min · 4 commandsChapter 9The omnibox
Your terminal answers you. Type a question where a command would go.
about 10 min · 4 commandsReference
- Man pages — one page per brick: what it is, what problem it solves, how to install it, where it sits in the path.
- The laws — 23 rules for running agents so the result survives. Every one was a real failure first; chapter 8 is where they start to matter.
- Skills — procedures an agent can load, one file each.