Show HN: Vho – AST-based analysis for better AI refactoring of large codebases • Hacker News Board

Show HN: Vho – AST-based analysis for better AI refactoring of large codebases

#1

Post by huali » Mon, Jan 05, 2026, 2:24 AM UTC

Show HN: Vho – AST-based analysis for better AI refactoring of large codebases
vue-hook-optimizer.vercel.app

Re: Show HN: Vho – AST-based analysis for better AI refactoring of large codebases

#2

Post by huali » Mon, Jan 05, 2026, 2:25 AM UTC

Most AI coding tools fail at large-scale refactoring because they lack a structural understanding of the code's "gravity."

I've been experimenting with applying the Label Propagation Algorithm (LPA) to AST dependency graphs. By treating variables and functions as nodes, we can identify communities (clusters) within a single file.

I integrated this into a tool for Claude Code called VHO. It helps dismantle monolithic React/Vue hooks by grounded mathematical analysis rather than just LLM prediction.

Technical breakdown:

AST Parsing: To build the reference graph. LPA: To find the optimal boundaries for extraction. Agentic Execution: Using Claude Code to perform the actual file I/O and refactoring. Is graph-theory-assisted refactoring the future of AI coding? I'd love to discuss the methodology.

Link: https://github.com/zcf0508/vue-hook-optimizer

Re: Show HN: Vho – AST-based analysis for better AI refactoring of large codebases

#3

Post by veeduzyl » Tue, Jan 13, 2026, 2:42 PM UTC

I’m experimenting with a cold guardrail for refactor risk. If it blocks you (or fails to), feedback is here: GitHub Discussion: “Feedback: tell me when it interrupts you”