Compact memory to 50%
Status Fixed / completed
Maintainer reply None cached
Activity 2 comments · opened Mar 22, 2025 · closed Jun 10, 2025
We get the most benefits when memory and context understanding are between 50% and 90%. When we compact, we literally lose everything, and for the AI, the compacted data makes no sense.
This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗