Save 70-90% in tokens per session3 points·by hasna·4 miesiące temu·2 commentsI built something which seems really promising for coding agents, that during early evals shows to be saving between 70% to 90% in token spend per session.It's still early, but there is a gap in the way coding agents work.Will be back with more soon.2 commentsPost comment[–]danielsokil·4 miesiące temureplyhttps://github.com/hasna/terminal[–]Orchestrion·4 miesiące temureplyInteresting, I've also been working on a protocol to help agents use fewer tokens. We look forward to more information!
It's still early, but there is a gap in the way coding agents work.
Will be back with more soon.