{"slug": "everyones-building-ai-agents-heres-the-one-i-built-for-myself", "title": "Everyone’s Building AI Agents. Here’s the One I Built for Myself", "summary": "A developer built a local RAG (Retrieval-Augmented Generation) agent that reads markdown files and answers queries in plain English, running entirely on a personal laptop without cloud APIs. The system uses Ollama for embeddings and Mistral for responses, with ChromaDB for vector storage. The project has been open-sourced on GitHub.", "body_md": "These days, everyone seems to be building AI agents.\n\nSo I figured I should probably build one too.\n\nBut instead of another generic demo, I wanted to solve a small problem I actually had.\n\nOver time, I had collected a bunch of blog posts and technical notes in a folder. I wanted a quick way to understand them without opening every file one by one.\n\nQuestions like:\n\nUploading everything to ChatGPT did not feel right.\n\nMy content. My machine.\n\nSo I built a small local RAG agent.\n\nIt reads markdown files, understands their meaning, and lets me query across all of them in plain English.\n\nUnder the hood, it looks something like this:\n\n```\nMarkdown Files\n      ↓\nChunking & Parsing\n      ↓\nnomic-embed-text (via Ollama)\n      ↓\nChromaDB (local vector storage)\n      ↓\nRelevant Context Retrieval\n      ↓\nMistral (via Ollama)\n      ↓\nAnswer\n```\n\nEverything runs locally on my laptop.\n\nNo cloud. No external APIs. Just Python and a few focused tools.\n\nThe architecture was clear before I started coding. The “vibe coding” part was mostly using AI to speed up repetitive work like tests, boilerplate, and wiring pieces together.\n\nIdea to working CLI in about a week.\n\nI’ve open sourced the project if you want to take a look:\n\n**Repo:** [Knowledge Onboarding Agent](https://github.com/vkondi/knowledge-onboarding-agent)\n\nNext, I might add PDF support and a lightweight web UI.\n\nCurious to know, have you built something similar recently? If yes, what problem did you solve?\n\nAlso curious, if you were building this, would you keep it fully local or use cloud APIs? What would you do differently?", "url": "https://wpnews.pro/news/everyones-building-ai-agents-heres-the-one-i-built-for-myself", "canonical_source": "https://dev.to/vishdevwork/everyones-building-ai-agents-heres-the-one-i-built-for-myself-1plh", "published_at": "2026-05-29 05:05:56+00:00", "updated_at": "2026-05-29 05:11:51.575633+00:00", "lang": "en", "topics": ["ai-agents", "artificial-intelligence", "large-language-models", "ai-tools", "ai-products"], "entities": ["Ollama", "ChromaDB", "Mistral", "nomic-embed-text", "ChatGPT", "Knowledge Onboarding Agent", "vkondi"], "alternates": {"html": "https://wpnews.pro/news/everyones-building-ai-agents-heres-the-one-i-built-for-myself", "markdown": "https://wpnews.pro/news/everyones-building-ai-agents-heres-the-one-i-built-for-myself.md", "text": "https://wpnews.pro/news/everyones-building-ai-agents-heres-the-one-i-built-for-myself.txt", "jsonld": "https://wpnews.pro/news/everyones-building-ai-agents-heres-the-one-i-built-for-myself.jsonld"}}