{"slug": "vector-local-code-summariser", "title": "Vector : local code summariser", "summary": "A developer built Vector, a local code summariser that generates TL;DRs, purpose descriptions, key functions with line ranges, dependencies and gotchas for individual files, GitHub repos or whole project folders, plus a project overview covering tech stack, architecture, entry points and a suggested reading order. Built and tested on an HP Victus laptop with a 6 GB RTX 4050, it runs on local Ollama models so code never leaves the machine, and its watch mode re-summarises files automatically on save. The developer reports that a 40-file project which took about 120 minutes to understand by reading now takes 30 minutes, with a cached re-run at 10 seconds.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady](https://dev.to/challenges/hacktoberfest-week3-2026-10-19)*\n\nEveryone has opened an unfamiliar repo and spent the first hour just trying to work out what it does. Vector is my lazy answer to that hour.\n\nVector is a local code summariser. Give it a file, a GitHub repo, or an entire project folder, and it tells you what the code is for before you read any of it. Every file gets a TL;DR, its purpose, key functions with line ranges, dependencies, and gotchas. For a whole project it also writes an overview: tech stack, architecture, a directory map, entry points, how to run it, and an ordered \"start reading here\" list.\n\nThe laziest part is watch mode. Point Vector at a folder, edit a file, and a fresh summary shows up on its own a few seconds later. You never have to ask.\n\nIt's for anyone who reads more code than they write: students inheriting a messy assignment, Hacktoberfest contributors landing in a new repo, and anyone who has ever said \"wait, what does this module do?\"\n\n[https://vector-frontend-dxot.onrender.com](https://vector-frontend-dxot.onrender.com)\n\n[https://github.com/amitsinha-cell/vector.git](https://github.com/amitsinha-cell/vector.git)\n\n**The open pieces**\n\n**My hardware is the whole story.** I built and tested this on an HP Victus laptop with an RTX 4050 (6 GB VRAM, 50W TGP). That is not a big machine, and it shaped every decision:\n\n**What went wrong.** `gemma4:e4b` is 6.6 GB on disk and my card has about 5 GB free, so part of it runs on CPU. I added a smaller-model retry and kept E2B one dropdown away.\n\nMy favourite bug: the UI said \"Ollama isn't running\" while Ollama was fine. The real cause was a CORS preflight rejection. Vite had moved to port 8081 and the backend's allowlist didn't include it, so the browser never read `/health`. The fix was easy, but the real lesson was that \"backend unreachable\" and \"Ollama down\" are different failures and the UI should say which one it is. It does now.\n\n**Your code stays on your machine.** A code summariser is a poor fit for a closed API. People paste private, unreleased, or employer-owned code into it. With local models the code never leaves the laptop. The UI shows a \"100% local\" badge, and a hosted fallback exists only as an opt-in setting that is off by default, with a warning before any code is sent.\n\n**Watch mode is only practical when inference is free.** An assistant that re-summarises every time you save a file would run up an API bill quickly. Locally, the only cost is electricity.\n\n**Swapping models is a dropdown.** I could try Gemma 4 against Qwen2.5-Coder on my own files and pick per task. A closed API doesn't let me do that.\n\n**It works offline.** Once the models are pulled, Vector needs no internet except for GitHub repo mode.\n\n**Customising is possible.** Because the weights are open, I can fine-tune a small Gemma on code-summary pairs next. I've fine-tuned small Gemma models before, and that path is closed with a hosted API.\n\n**Where closed still wins.** Large frontier models write better summaries of huge, tangled files. For \"tell me what this folder is about,\" a small local model with good chunking was good enough, and it was private.\n\nFor example: \"A 40-file project that took me about 120 minutes to understand by reading now takes 30 minutes, and the cached re-run takes 10 seconds.\"", "url": "https://wpnews.pro/news/vector-local-code-summariser", "canonical_source": "https://dev.to/amit_sinha_2a6ee473012f2d/vector-local-code-summariser-1k63", "published_at": "2026-10-25 16:07:11+00:00", "updated_at": "2026-10-25 16:13:14.004705+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models", "ai-products"], "entities": ["Vector", "Ollama", "Gemma", "Qwen2.5-Coder", "GitHub", "Hacktoberfest", "HP Victus", "RTX 4050"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/vector-local-code-summariser", "markdown": "https://wpnews.pro/news/vector-local-code-summariser.md", "text": "https://wpnews.pro/news/vector-local-code-summariser.txt", "jsonld": "https://wpnews.pro/news/vector-local-code-summariser.jsonld"}}