Skip to content
View elkaix's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report elkaix

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
elkaix/README.md

Mohamed Elkholy

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

Current focus

  • 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.

Selected projects

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.

Technical toolkit

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

Education

M.S. in Applied Artificial Intelligence — Eastern University

Pinned Loading

  1. Pythinker-ai Pythinker-ai Public

    🤖 — a tiny personal AI agent framework. Chat channels (Slack, Telegram, Discord, WhatsApp, …), memory, MCP, and an OpenAI-compatible API in one small Python core.

    Python 3

  2. PyModel/jev-judge-mcp PyModel/jev-judge-mcp Public

    Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review…

    Python 49 5

  3. PyModel/pythinker-code PyModel/pythinker-code Public

    Next-generation AI coding agent for your terminal — reads code, edits files, runs tools, and integrates with editors via ACP.

    TypeScript 29 9

  4. PyModel/defensive-design PyModel/defensive-design Public

    Agent skill for production resilience: proportional defensive engineering, failure classification, idempotency, backpressure, and evidence-backed verification.

    Python 1 1

  5. PyModel/agent-ci-optimizer PyModel/agent-ci-optimizer Public

    Agent skill: evidence-first CI optimization of push-to-green for any repo (runners, lint/typecheck, sharding, caching, parallel jobs, affected tests, hooks).

    Python

  6. PyModel/metal-inference PyModel/metal-inference Public

    Python 1