AI/ML Engineer · AI agents, developer tools, and applied machine learning
I build AI agents, developer tools, and applications with Python, Go, and TypeScript. My work brings together model integration, local inference, and dependable software engineering.
Website · X — @moelkholy95 · LinkedIn · PyModel · Email
- AI agents and MCP: coding workflows, tool integrations, and structured decision systems.
- Local AI: LLM inference, quantization, and evaluation on Apple Silicon.
- Applied engineering: Go services, Next.js applications, and forecasting workflows.
| Project | What it does |
|---|---|
| Pythinker Code | AI coding agent for desktop, terminal, and editors, with parallel agents, tool approvals, MCP, and ACP support. |
| Pythinker AI | Python framework for personal AI agents with messaging integrations, persistent memory, MCP tools, and an OpenAI-compatible API. |
| Jev Judge MCP | Typed tools connecting coding agents to TypeSafe's Jev model for verification, classification, ranking, and decisions. |
| Defensive Design | An agent skill for handling failures, setting security boundaries, and verifying software changes. |
| Agent CI Optimizer | An agent skill and supporting tools for measuring CI bottlenecks and improving build speed while preserving reliable checks. |
| Metal Inference | An agent skill and memory-budget tools for selecting and running local language models on Apple Silicon. |
| Area | Technologies |
|---|---|
| Languages | Python, Go, TypeScript |
| AI and ML | PyTorch, scikit-learn, Hugging Face, MCP |
| Applications and data | React, Next.js, FastAPI, PostgreSQL, Redis |
| Infrastructure | Docker, GitHub Actions, Linux, AWS |
M.S. in Applied Artificial Intelligence — Eastern University




