← Atlas

Topic hubs

First editorial hubs for the wiki-style library. Each hub is a short path into the notes; the notes themselves stay the source.

Agent memory

How an agent remembers: what belongs in the current thread, what should survive into a later session, and what a paper or benchmark actually measured.

Context compaction

What happens when an agent shrinks its context: standing instructions can be dropped, and some methods keep a residual memory or a separate constraint list.

React

Library notes on the React UI library: props, state, effects, and the other core patterns already covered in the catalog.

For language models and agents: start at /llms.txt. This page in Markdown: /library/topics/index.json.