# witcheer's Wingtips #42: the compaction-summary model

Written by [witcheer](https://x.com/witcheer) at Nous Research. Republished with credit.

Canonical: https://hermeswatcher.com/wingtips/42  
Published: 2026-08-10  
[Original](https://notwitcheer.github.io/hermes-recipes/wingtips/42-the-compaction-summary-model/) · [On X](https://x.com/witcheer/status/2086745372521591061) · [Full collection](https://notwitcheer.github.io/hermes-recipes/) · [Official docs](https://hermes-agent.nousresearch.com/docs/developer-guide/context-compression-and-caching)

[Source Markdown](https://raw.githubusercontent.com/notwitcheer/hermes-recipes/8653fb699a137a32e81936fa33cabacd3f4f2095/docs/wingtips/42-the-compaction-summary-model.md): use this file as the base for relative links in the verbatim text below.

Sources: [Hermes docs: Context Compression And Caching](https://hermes-agent.nousresearch.com/docs/developer-guide/context-compression-and-caching)


Hermes Wingtips #42: the compaction-summary model

every time your context compacts, a model reads the whole transcript and writes the summary. by default that model is your main chat model. 

if you run a frontier model, you are paying frontier price for housekeeping, and the pause you feel at every compaction is frontier latency too.

you can move that job to a fast, cheap model. below, the switch on my own agent: