5 comments

[ 3.0 ms ] story [ 27.7 ms ] thread
Interesting approach. How does it handle monorepos or repos with unconventional structure? The multi-pass analysis sounds nice, but I’d be curious how consistent the output is across runs if you run it twice on the same repo, do you get basically the same diagram?
How does it handle messy massive codebases?
It's pretty good for me, and I applied it to my project! I want to connect this tool to my Claude Code via an MCP or a plugin. Could I do that as though it were Deepwiki?
Tried it on a few repos — the file-tier prioritization is a nice touch. Skipping lockfiles and generated code saves a lot of noise.

Would be interesting to see this integrated into CI — auto-generate updated diagrams on each PR so architecture docs never go stale.