8000 oz6un (Mert Ozgun) · GitHub
[go: up one dir, main page]
Skip to content
View oz6un's full-sized avatar
3 followers · 0 following

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Block or report oz6un

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
oz6un/README.md

Mert Ozgun

I tinker on AI-agent tooling and open-source what works.

Formerly at Churnkey: data pipelines and ML research for a payment-recovery engine that's recovered ~$300M in failed payments.

Lisbon · mertozgun.com · x.com/oz6un · contact@mertozgun.com

Popular repositories Loading

  1. ship-loop ship-loop Public

    A Claude Code skill: a disciplined implement → audit → ship loop for delivering substantial code changes with rigor (project-agnostic).

    1

  2. oz6un oz6un Public

  3. devbox devbox Public

    Reproducible, tailnet-only Hetzner dev server wired for Claude Code — hardened, self-alerting, and rebuildable from scratch in minutes.

    Shell

  4. rigor rigor Public

    Rigorous engineering workflows for Claude Code and Codex: playbooks, principles, multi-model review, verification. Ported from pstack.

    TypeScript

  5. ubicloud ubicloud Public

    Forked from ubicloud/ubicloud

    Open source alternative to AWS. Elastic compute, block storage (non replicated), firewall and load balancer, managed Postgres, K8s, AI inference, and IAM services.

    Ruby

  6. amalia-lm-eval amalia-lm-eval Public

    Forked from AMALIA-LLM/amalia-lm-eval

    AMALIA-LM-Eval: Portuguese (pt-PT) benchmark suite

    Python

0