Re:Stop Burning Your Context Window – How We Cut MCP Output ...
by mksglu on Saturday February 28, 2026 @04:12PM
(#47200289)
Haven't looked at rtk closely but from the description it sounds like it works at the CLI output level, trimming stdout before it reaches the model. Context-mode goes a bit further since it also indexes the full output into a searchable FTS5 database, so the model can query specific parts later instead of just losing them. It's less about trimming and more about replacing a raw dump with a summary plus on-demand retrieval.
Re:Stop Burning Your Context Window – How We Cut MCP Output ...
by giancarlostoro on Saturday February 28, 2026 @04:58PM
(#47200731)
Yeah I like this approach too. I made a tool similar to Beads and after learning about RTK I updated mine to produce less token hungry output. I'm still working on it.
Re:Stop Burning Your Context Window – How We Cut MCP Output ...
by esperent on Saturday February 28, 2026 @05:18PM
(#47200893)
Does context mode only work with MCPs? Or does it work with bash/git/npm commands as well?
Re:Stop Burning Your Context Window – How We Cut MCP Output ...
by re5i5tor on Saturday February 28, 2026 @08:00PM
(#47202437)
I'm not sure it actually works with MCPs *at all*, trying to get that clarified. How can context-mode get "into the MCP loop"?
Re:Stop Burning Your Context Window – How We Cut MCP Output ...
by re5i5tor on Saturday February 28, 2026 @08:26PM
(#47202628)
See my comment above, context-mode has no way to inject itself into the MCP tool-call - response loop.
Still high-value, outside MCPs.
Re:Stop Burning Your Context Window – How We Cut MCP Output ...
by RyanShook on Saturday February 28, 2026 @04:58PM
(#47200730)
I’m also trying to see which one makes more sense. Discussion about rtk started today: https://news.ycombinator.com/item?id=47189599
I see some of these AI companies adopting some of these ideas sooner or later. Trim the tokens locally to save on token usage.
https://github.com/rtk-ai/rtk