OK, so, I too have built a local index tool called slopdex [1].
It's very simple, parses the repo code and docs with treesitter, indexes it, vectorizes everything, then allows you do things like create a map of the codebase or do a semantic search.
One cool trick that does work well is the cross-search command, which allows you to do a duplicate code search using the vector index. This gets rid of a blind spot that lots of LLMs have that make it create lots of dupliclate helper functions. This works quite well in practice.
It has a few evals that I'm still working on, showing only modest improvements in token usage when using the map command, maybe around ~10% less. I think this can depend a lot on the type of task though.
Would be happy to hear any feedback.
[1]: https://github.com/ninjaxtools/slopdex
It's very simple, parses the repo code and docs with treesitter, indexes it, vectorizes everything, then allows you do things like create a map of the codebase or do a semantic search.
One cool trick that does work well is the cross-search command, which allows you to do a duplicate code search using the vector index. This gets rid of a blind spot that lots of LLMs have that make it create lots of dupliclate helper functions. This works quite well in practice.
It has a few evals that I'm still working on, showing only modest improvements in token usage when using the map command, maybe around ~10% less. I think this can depend a lot on the type of task though.
Would be happy to hear any feedback.
[1]: https://github.com/ninjaxtools/slopdex