alt Hacker NewsSQLite + GPT5.4 works very well for me.
My biggest success is a Roslyn method that takes a .NET solution and converts it into a SQLite database with Files, Lines, Symbols, and References tables. I've found this approach to perform substantially better than a flat, file-based setup (i.e., like what Copilot provides in Visual Studio). Especially, for very large projects. 100+ megs of source is no problem. The relational model enables some really elegant [non]queries that would otherwise require bespoke reflection tooling or a lot more tokens consumed.
Replies
superjan • yesterday at 2:06 PM
Is this something you can share in more detail? Did you document a skill for the LLM to use? And with what tasks do you see most improvement?
Interesting... what is the use case for the AI that is querying it? Is it how to develop additional features for integration with your app or do you have some other use case? Code review/audit/debugging/etc. For AI developing against an API I would think an OpenAPI json file would do the trick.
Is the Roslyn method called as part of the build/publish?