Skip to content
View Wellington01's full-sized avatar
🎯
Focusing
🎯
Focusing
143 followers · 557 following

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault Contributor

Organizations

@kodustech

Block or report Wellington01

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Wellington01/README.md

Wellington Santana

Co-founder & CTO at Kodus. We build open source AI code review.

Our agent, Kody, reviews pull requests on GitHub, GitLab, Bitbucket and Azure DevOps. Most AI reviewers hand a raw diff to a model and ship whatever comes back — which is why they're noisy. We run a deterministic AST engine first and give the LLM structured context instead, so it has fewer chances to invent a problem that isn't there.

Model agnostic (Claude, GPT, Gemini, Llama, or any compatible endpoint), no markup on your LLM spend, and self-hostable end to end.

Before this: co-founder & CTO at ez.devs.

Lately I've been thinking about observability for non-deterministic systems — I gave a talk on it (logs-que-a-ia-entende), and it keeps turning out to be the hard part of shipping agents.

kodus.io · @wellingtoncvs · LinkedIn · Bauru, Brazil 🇧🇷

Pinned Loading

  1. kodustech/kodus-ai kodustech/kodus-ai Public

    AI Code Review with Full Control Over Model Choice and Costs.

    TypeScript 1.3k 125

  2. kodustech/kodus-graph kodustech/kodus-graph Public

    Code graph builder for AI code review — parses 14 languages into structural graphs for blast radius, risk scoring, and test gap analysis.

    TypeScript