Amartya Gaur
03Agent systems
← The index

Repo-to-docs retrieval

A repo map, two indexes, and no benchmark yet.

Made for
manu docs
Years
2026
Status
Prototype

The retrieval layer for a pipeline that turns a repository into documentation: a tree-sitter and personalized-PageRank repo map after Aider’s, an AST-chunked code index and a prose index over pgvector, each pinned to its own embedding model. Wired end to end, with no retrieval benchmark in it yet. I wrote the decision record surveying how Cursor and Cody do this before the code, built the repo-map third of it, and then wrote down which two thirds I had not.