Vdiff is a CLI tool that combines deterministic analysis with LLM reasoning to help developers prioritize and review AI-
I was thinking about building something that would guide me during development and during PR reviews. Something that would give me signals based on facts, risks, and evidence. Not just one LLM reviewing the code it generated. The initial idea was to add a deterministic review layer and combine that with LLM reasoning, and use that to find gaps in code and point me to the most important places, so I don't need to read line by line.
I ended up building a tool called vdiff, and it is working very well for me, and I'm constantly improving it. It is a CLI that analyzes your git diffs and gives you a structured report: what changed, what's risky, and what's missing. It uses tree-sitter for AST diffs and an LLM on top, so you get actual evidence for each finding, not just vibes.
Some of the output signals: - Tells you if it's safe to merge, with a risk score - Lists what's wrong, how confident it is, and shows the evidence - Dependency graph for blast radius analysis - Review memory (tracks resolved/reopened findings across sessions) - You can point it at a spec or PRD, and it checks if the changes actually match - Structural metrics (acyclicity, depth, equality, graph)
It runs locally; I didn't want the tool publishing the code