Skip to content
View HOLYKEYZ's full-sized avatar
:octocat:
:octocat:
69 followers · 8 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy BrainAchievement: Pull Sharkx2Achievement: YOLOAchievement: QuickdrawAchievement: Starstruck

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy BrainAchievement: Pull Sharkx2Achievement: YOLOAchievement: QuickdrawAchievement: Starstruck

Highlights

Organizations

@IntellectSafe

Block or report HOLYKEYZ

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
HOLYKEYZ/README.md

joseph


agentic engineer

bridging AI alignment and production systems. building tools that matter.

🎯 what I Do

ai safety - researching and engineering safeguards for AI systems, including red teaming
fullstack development - scalable web applications from concept to production
agentic engineering - coding at the speed of thought
local llms - tinkering with local models — guardrails, uncensoring, just experimenting...

building real-time solutions to world problems through software

🛠️ tech Arsenal

systems & core
C holyC python typeScript

frontend
react next JS tailwindCSS shadcn/ui

backend
nodeJS django flask fastAPI

infrastructure & deployment
supabase neon postgreSQL mongoDB docker
vercel render

ml / ai
PyTorch HuggingFace transformers LiteRT

📊 activity

GitHub Stats GitHub Streak Top Languages

🤝 open to collaboration

working on AI safety & red teaming, scalable systems, agentic/local ai?, let's talk.

Email WhatsApp Twitter HuggingFace

Pinned Loading

  1. IntellectSafe IntellectSafe Public

    AI defense infrastructure against manipulation, misuse, hallucinations, and synthetic deception.

    Python 20 2

  2. model-unfetter model-unfetter Public

    The production engine for directional ablation. Unalign / remove models censorship efficiently on any hardware.

    Python 29 2

  3. ModelFang ModelFang Public

    AI red teaming, jailbreaking, and all forms of adversarial attacks for security purposes

    Python 21 4

  4. mayo mayo Public

    my autonomous 3riple-LLMs agents for my github actions & workflows(opens suggestive PRs every hour)

    Python 15 9