KpolitX

Build your own private AI assistant that can plan tasks, use tools, work with files, maintain memory, and operate under controlled guardrails using Ollama and Python. Most people use AI as a chatbot: ask a question, receive an answer, and repeat. A personal agentic system is different. It can understand a goal, break it into steps, use tools, remember useful context, and produce a useful result while running largely on your own computer. In this guide, you'll build a simple but extensible personal AI agent using Ollama and Python . By the end, it will be able to: Accept a task in natural language Plan the steps needed Read and write local files Search notes or documents Call tools safely Keep a record of what it did Improve through feedback 💡 The key idea: An agent is not just a model; it is a model plus tools, memory, planning, and gu...

AI applications are becoming increasingly powerful, but building a serious AI workspace involves much more than connecting a frontend to an API. KODEX is my approach to building a self-hosted, local-first AI workspace designed around agents, tools, model routing, security boundaries and isolated services. Instead of building everything inside one application, KODEX separates responsibilities across multiple services written in Go and Rust , with a modern Next.js frontend. 💡 Project Focus: KODEX Phase 1 focuses on establishing the foundation: authentication, model routing, secure secret handling, network isolation, service boundaries, database separation and a working local-first AI workspace. Layer Technology Responsibility Frontend Next.js + TypeScript Login and AI chat interface ...

Welcome back to the KpolitX tech blog! In the previous articles, we looked at building applications and working with backend technologies. This time, we are moving one step further into the world of DevOps and cloud deployment . Building an application is only one part of software development. The more interesting question is: What happens after you push your code to GitHub? In this project, I built a small Flask application called VaultMart and used it as a practical way to understand how a complete CI/CD pipeline works with GitHub Actions, Docker and AWS . 💡 The goal: Build a workflow where a code change can automatically move through testing, Docker image creation, AWS ECR and deployment to an EC2 server. The final workflow looks like this: Code Change ↓ Git Push ↓ GitHub Actions ↓ Pytest ↓ Docker Build ↓ Amazon ECR ↓ AWS Systems Manager ↓ Ama...