Skip to content
View joemunene-by's full-sized avatar
4 followers · 7 following
  • Nairobi
  • 21:12 (UTC +03:00)

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Shark

Block or report joemunene-by

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
joemunene-by/README.md

I build security tools, full-stack systems, and AI models.
Not wrappers or tutorials — production tools that solve real problems.

Currently training a cybersecurity-focused LLM from scratch.


Portfolio Email GitHub


> whoami

I'm a Computer Science student at Moi University (Nairobi, Kenya) working at the intersection of offensive security, full-stack engineering, and applied AI. I write code that other engineers can trust — clean architecture, real security, no shortcuts.

I also lead Complex Developers — building web platforms, custom tooling, and AI-adjacent products for clients. The company site + CRM runs on Next.js + Prisma + Postgres.

Most of my work is open source. I believe the best way to prove what you can build is to show it.


> cat /etc/skills

Languages
TypeScript JavaScript Python Rust C Bash SQL HCL

Frameworks & Tools
React Next.js Node.js Tailwind Tauri PyTorch Jupyter Prisma PostgreSQL Docker Terraform

Security
Linux Wireshark Burp Suite Metasploit Nmap YARA


> ps aux | grep active

Building now: GhostLM

A cybersecurity-focused language model built from scratch in PyTorch. Decoder-only transformer trained on CVE data, CTF writeups, and security research.

Not a fine-tune. Not a wrapper. A model trained from tokenizer to weights.

GhostLM

Latest drops

secure-mcp — MCP server exposing security tools to AI agents with policy gates, subprocess sandboxing, and audit trails. Fail-closed by default.

CyberBench — Open, reproducible benchmark for evaluating LLMs on cybersecurity reasoning. YAML tasks, pluggable backends, ranked leaderboard.

secure-mcp CyberBench

What I ship

Security tools — Port scanners, traffic analyzers, vulnerability scanners, hash crackers, steganography tools, MAC spoofers, metadata scrubbers

Full-stack apps — AI coding assistants, SaaS dashboards, threat intelligence platforms, mobile health apps

Open source contributions

> git log --oneline

GitHub Streak

> cat README.md | tail -n 3

I'm always open to collaborating on security research, open-source tools, or interesting engineering problems.
If you're building something that matters, I'd like to hear about it.


Nairobi, Kenya · Open to opportunities · joemunene984@gmail.com


Profile Views

Pinned Loading

  1. Network-Traffic-Analyzer Network-Traffic-Analyzer Public

    Network Traffic Analyzer - A production-grade, enterprise-ready network security monitoring tool designed for Security Operations Centers (SOCs), penetration testers, and security researchers. This…

    Python 1

  2. GhostLM GhostLM Public

    An open-source cybersecurity-focused language model built from scratch in PyTorch. Decoder-only transformer trained on CVEs, CTF writeups, and security research.

    Python 2 1

  3. advanced-port-scanner advanced-port-scanner Public

    Detect and analyze network vulnerabilities with this advanced port scanner — multiple scan types and high-performance capabilities for secure assessments.

    Python 1

  4. ai-coding-assistant ai-coding-assistant Public

    An AI assistant which can create full stack website and also full stack applications

    TypeScript 1

  5. sentinelpulse sentinelpulse Public

    Real-time Threat Intelligence Dashboard

    JavaScript

  6. Vulnerabilities-Scanner Vulnerabilities-Scanner Public

    Vulnerabilities Scanner is a lightweight, extensible static scanner for source trees that finds common secrets and insecure patterns.

    Python