HNHacker News
TopNewBestAskShowJobs

Zakaria_Gamal

2 karma · joined February 16, 2026

Hi, I’m Zakaria — a mid-level AI engineer focused on building production-grade AI systems.

Over the past three years I’ve worked on RAG-based LLM systems, semantic search pipelines, and computer vision services for KYC and content moderation. Most of my work revolves around taking models from prototype to reliable production systems — optimizing retrieval, reducing hallucinations, improving latency, and making AI services actually usable in real-world environments.

I enjoy working on system design challenges around context memory, vector search, caching strategies, and scalable inference APIs. Currently exploring more advanced agent orchestration and multi-agent workflows.

submissionscomments
Zakaria_Gamal··on [dead]
Hey HN community, I've created an agentic AI system using a Model Context Protocol (MCP) server, based on my ongoing tutorial series: https://github.com/zkzkGamal/Agentic-AI-Tutorial. The system uses LangChain for orchestration and LangGraph for stateful workflows, with the MCP server handling tool integrations, data access, and real-time decision-making. It's designed for autonomy—agents can reason, plan, and execute tasks like API calls or database interactions without constant human input. Chapter 5 dives into production deployment (still in progress, but this project is a practical case study). Open to feedback on improving security, scalability, or adding features like multi-agent collaboration. What agentic setups are you working on?
Zakaria_Gamal··on [dead]
Hey HN, I'm Zakaria, a dev from Cairo building open-source tools. After my earlier prototypes kept failing on complex tasks (e.g., hallucinating unsafe commands), I added a router that classifies queries, plans multi-step actions, and executes with local package management—all offline on Linux. Key features:

Router Branching: Uses LangGraph for conditional flows—classifies as conversational, planning-needed, or direct-execute. Handles tool calls safely with confirmations for risky stuff. Safe Package Mgmt: Installs dependencies locally without internet, avoiding supply-chain risks. REPL-like Execution: Stateful code interp for persistent sessions.

It's built with Python/LangChain, runs on any Linux box. Here's a quick example: Ask it to "analyze this PDF and plot data"—it plans, browses the file, executes via tools, and outputs. Repo: https://github.com/zkzkgamal/zkzk-agent (stars/feedback welcome!) What do you think—any ways to harden the router against edge cases? Or integrations you'd want (e.g., more bio/chem tools)? This framing emphasizes progress from your old posts, adds tech depth, and invites input. If it doesn't take off, analyze the comments and iterate—many viral projects started with flops. Good luck; HN can be unpredictable, but building genuinely useful stuff is the real win! If you share more project details, I can refine this further.

Zakaria_Gamal··on Agentic AI Tutorial: Step-by-Step Guide to Building Autonomous Agents (GitHub)
Update: Chapter 4 is now complete and live in the repo!

This chapter dives into LangGraph for real agent orchestration: - Build ReAct-style agents with tool calling - Visualize graphs (nodes/edges/conditional routing) using Graphviz – super visual and satisfying - Handle state updates live, multi-agent collaboration patterns, self-refinement loops - Full executed notebook showing a simple agent reasoning through queries (e.g., math tools, search integration)

All local-first with Ollama, plus OpenAI/Gemini support.

Repo: https://github.com/zkzkGamal/Agentic-AI-Tutorial (Chapter4 folder has the notebook + code)

Chapter 5 (Personal Finance Tracker Agent with FastAPI + ChromaDB RAG) is next and almost ready.

Feedback super welcome – especially on the LangGraph patterns or what real-world agents you'd like to see built!

Thanks for any upvotes/comments – still early days :)

Zakaria_Gamal··on Agentic AI Tutorial: Step-by-Step Guide to Building Autonomous Agents (GitHub)
Hi HN, sharing my open-source tutorial on Agentic AI. It walks through creating intelligent agents that can reason, plan, and act— with practical code examples in Python. Aimed at devs interested in the next wave of AI beyond basic LLMs. Questions or suggestions welcome!
Zakaria_Gamal··on Local AI Assistant for Linux That Runs Commands
I’ve been working on zkzkAgent v2, a self-hosted AI assistant for Linux that executes system tasks based on natural language commands. It’s privacy-first, fully local, and designed for developers/self-hosters who want real automation instead of just advice.

Highlights in v2:

Network-aware actions & Wi-Fi auto-reconnect

Image search & download from DuckDuckGo

Streaming token-by-token responses

Quick install script for fast setup

Optional voice input/output (Whisper + TTS)

Human confirmation for dangerous operations

All processing happens locally — nothing goes to the cloud. It can manage files, processes, deployments, and system commands with AI assistance.

GitHub: https://github.com/zkzkGamal/zkzkAgent

Would love feedback, ideas, or discussion on self-hosted AI agents.

Zakaria_Gamal··on StudyWithMiku: Open-source AI study assistant
Hi HN,

I built StudyWithMiku, an open-source AI study assistant that:

Ingests PDFs automatically (drop into a folder)

Embeds them into ChromaDB

Uses RAG for grounded answers

Maintains conversational memory with LangGraph

Outputs synthesized character voice using Coqui TTS + DiffSinger

Runs locally (Ollama supported) or with cloud LLMs

The goal was to combine:

• Retrieval-augmented generation • Stateful agent orchestration • Tool execution (web/system tools) • Persistent memory • Character-specific TTS

into one cohesive system.

Engineering challenges included:

Chunking strategy and retrieval accuracy

Avoiding recursive agent tool loops

Managing CUDA/PyTorch/protobuf conflicts

Keeping latency reasonable with local models + TTS

It’s Linux-first (Ubuntu recommended) and GPU helps, but CPU works.

I’m particularly interested in feedback on:

RAG optimization approaches

LangGraph/agent architecture patterns

TTS expressiveness tuning

Local LLM deployment tradeoffs

Happy to answer technical questions.