Local-first semantic paging and durable virtual memory for bounded AI context
2 files for Codex and OpenCode: write-timeless-technical-prose, library-of-context AGENTS.md — 680 tokens loaded in every session.
AGENTS.md A 680 tok .agents/skills/write-timeless-technical-prose/SKILL.md A 116 tok These files are hwillGIT/library-of-context's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.