HermesWatcher
Search⌘K For brandsSetup help
StartStart hereSetup plannerInstall Hermes AgentChat from your phoneYour first 24 hours
Use casesWorkflow blueprintsCase studiesUse-case collectionsCommunity libraryPrompt library
LearnWhat is Hermes Agent?Guideswitcheer's WingtipsTopicsFAQCommand cheat sheetGlossarySOUL.md gallery
ToolsTools & integrationsAll messaging platformsSkills directoryPlugins directorySkills, plugins & MCP
TroubleshootReleases
Work with usServicesNewsletterFor brands: partner with usFor AI agentsContactAboutFollow @HermesWatcher on X ↗ (opens in a new tab)

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

Republished in his own words, with credit.

witcheerBy witcheer · Nous Research

Back to wingtips

#42 · the compaction-summary model

· Models, providers & cost · CLI / Desktop / Gateway

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:

SourcesHermes docs: Context Compression And Caching

All tips are written by witcheer and collected here with credit. Card images stay on his X posts.

witcheer says each tip ran on a real Hermes box before it shipped. Hermes changes fast, so check your version and the linked doc.