Skip to content
View hiroyuki117339's full-sized avatar

Organizations

@velcore-consulting

Block or report hiroyuki117339

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
hiroyuki117339/README.md

Hiroyuki Hasegawa

Head of AI-Driven Development · Full-Stack Engineer · Security Researcher

I lead AI-driven development at Velcore Consulting Inc., drawing on extensive experience in full-stack software engineering, system architecture, product development, and technical leadership.

My current work focuses on turning AI-assisted development into reliable engineering practice. I also conduct security research into applications and LLM/AI systems, reporting vulnerabilities in open-source software through coordinated disclosure.

What I work on

  • AI-driven software development and engineering leadership
  • Full-stack product engineering and system architecture
  • macOS application development and local-first AI
  • Application, open-source software, and LLM/AI security
  • Evidence-based vulnerability research and coordinated disclosure

Selected product

A free, privacy-conscious macOS application for recording, transcription, local speaker labeling, and AI-assisted meeting notes.

  • Records microphone and system audio from apps such as Zoom, Google Meet, Microsoft Teams, and YouTube
  • Uses macOS speech recognition for transcription
  • Performs speaker labeling locally, without sending recorded audio or transcripts to an external service
  • Supports AI-assisted editing and meeting notes through user-configured APIs or Codex / Claude Code

Designed and developed by me. The source code is private.

Security research

I independently research security issues in publicly available open-source software, with a focus on application and LLM/AI systems. Validated disclosures will be listed here after coordinated publication.

Links

Popular repositories Loading

  1. mozkey mozkey Public

    Forked from koyasi777/mozkey

    Mozc をベースに、遅延付きライブ変換・ローカル Zenz 補正・ダークテーマ対応・句読点単打確定・文脈を見た変換補正などを統合した、ローカルファーストな日本語入力 fork です。

    C++

  2. oracle oracle Public

    Forked from steipete/oracle

    Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files.

    TypeScript

  3. agmsg agmsg Public

    Forked from fujibee/agmsg

    Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.

    Shell

  4. stop-ai-slop-jp stop-ai-slop-jp Public

    Forked from iKora128/stop-ai-slop-jp

    日本語の文章からAI臭を取り除く Claude Skill

  5. interview-dev-loop interview-dev-loop Public

    Forked from unsu0707/interview-dev-loop

  6. CodexBar CodexBar Public

    Forked from steipete/CodexBar

    Show usage stats for OpenAI Codex and Claude Code, without having to login.

    Swift