2026-10-31 07:14 UTC
@FaceDeer@fedia.io @eicker@lemmy.world @floofloof@lemmy.ca @fonix232@fedia.io @naeap@sopuli.xyz
When you add the additional codebase memory, that will also add all those mcp tools to each round-trip to the llm model. Do you still see improvements and less filling up if your context? Just curious how it works out; I can imagine that a text based memory that explains the architecture of the codebase would help as well. Not sure about the difference if using a graph to store the code context?
Replies (0)
No replies.