arminpasalic

arminpasalic / vectoria

Public

Browser-first text exploration, clustering, and semantic search. Use AI to analyze, search, and chat with your private documents without ever uploading them to the internet - all running on your own device.

vectoria.app browser cluster-analysis exploratory-data-visualizations llm rag
15
0
100% credibility
Found Feb 10, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

Vectoria is a fully browser-based tool for loading text files, automatically creating interactive 2D maps of similar ideas, enabling fast searches, and using local AI to answer questions about your data.

How It Works

1
🌐 Discover Vectoria

You find this free browser tool for exploring your text files like notes, spreadsheets, or research data.

2
📁 Upload your file

Drag in a CSV, Excel, JSON, or text file containing your documents or notes.

3
📝 Pick your text

Choose the column with the words you want to explore and hit process.

4
✨ Magic map appears

Watch as your data transforms into an interactive 2D map with colorful groups of similar ideas.

5
Explore your map
🔍
Quick keyword search

Type words to instantly highlight and list matching documents.

🤖
Ask the AI

Switch to AI mode and ask natural questions for smart answers with sources.

6
📊 Filter and dig deeper

Apply filters on dates, categories, or numbers to focus on specific parts.

🎉 Unlock insights

You discover hidden patterns, topics, and answers right in your browser, all private and fast.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 14 to 15 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is vectoria?

Vectoria is a browser-first text exploration tool that lets you analyze, cluster, and semantically search private documents entirely on your device using JavaScript and WebGPU. Load CSV, Excel, JSON, or TXT files, pick a text column, and it generates interactive 2D UMAP visualizations with HDBSCAN clusters, hybrid keyword-vector search, and RAG chat—all without ever uploading data to the internet. It's privacy-focused vectorial exploration for personal or sensitive docs.

Why is it gaining traction?

It stands out by ditching servers for true offline capability after initial model download, with multilingual embeddings handling 100+ languages and local LLMs like Gemma or Llama for on-device chat. Developers dig the zero-infra setup—no APIs, just launch in Chrome/Edge and explore clusters or query via semantic search. The interactive viz and persistent IndexedDB storage make iterating on datasets feel instant.

Who should use this?

Researchers clustering qualitative data or papers, analysts at vectorial consulting firms handling confidential docs, or solo devs building personal knowledge bases from notes. Perfect for vectorians exploring multilingual corpora without cloud risks, or teams needing quick device-based exploration and RAG on spreadsheets.

Verdict

Try it for local-first semantic analysis—docs are solid, features work out-of-box on decent GPUs. With 14 stars and 1.0% credibility, it's early-stage but promising; fork and contribute to mature it.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.