Web RAG to generate perplexity like answers from your docs [in browser]
How It Works - Offline Indexing: Docs are processed and embedded using the GTE-small model at build time. Browser-Based Magic: - SQLite database (stored in the browser) for vector search. - Local embedding model for query processing. - Local LLaMA model for response generation using WebLLM. - Everything Happens Locally: No data leaves the user’s device. Key Benefits - No API Costs: Everything runs in the browser—zero backend expenses. - Unlimited Chats: No rate limits or usage restrictions. - Privacy-First: Your data stays on your device, always. You can find the code here:…
What it does
In the maker’s words, at launch
How It Works - Offline Indexing: Docs are processed and embedded using the GTE-small model at build time. Browser-Based Magic: - SQLite database (stored in the browser) for vector search. - Local embedding model for query processing. - Local LLaMA model for response generation using WebLLM. - Everything Happens Locally: No data leaves the user’s device. Key Benefits - No API Costs: Everything runs in the browser—zero backend expenses. - Unlimited Chats: No rate limits or usage restrictions. - Privacy-First: Your data stays on your device, always. You can find the code here: https://github.com/Cloud-Code-AI/AkiraDocs
Does the same job
all alternatives →
LatticeDB – Like SQLite but for graph databases12d ago · github.com · ▲190We have been using graph DBs more and more at work. I found them painful to work with locally and decided to try and build something better.
- EAEatmydata.ai – Local-First Question-to-SQL-to-Dashboard AIJun 2026 · eatmydata.ai · ▲8
Yet another "talk to your data and build a dashboard" app, where data does not leave your browser. You ask a question, agents produce multiple SQL queries to in-browser sqlite, never seeing results, and write dashboard configuration code. The data you analyze will be indexed with a local semantic index (embeddings generation + sqlite vector search fully local). Next, sandboxed QuickJS runs this code to produce rich dashboards directly in your browser, no backend attached. This is a fully frontend app (except OpenRouter or other remote LLM). All data sent to LLM's is heavily sanitized and…
- PVParqDB – Vector search in the browser from Parquet over HTTP"16d ago · search.parqdb.io · ▲26
Search a 100,000-article ParqDB index directly in the browser with MiniLM, HTTP Range, Parquet, and WebAssembly.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
