WebPizza AI - Private PDF Chat
POC: Private PDF AI using only your browser with WebGPU
What it does
I built this POC to test if complete RAG pipelines could run entirely client-side using WebGPU. Key difference: zero server dependency. PDF parsing, embeddings, vector search, and LLM inference all happen in your browser. Select a model (Llama, Phi-3, Mistral), upload a PDF, ask questions. Documents stay local in IndexedDB. Works offline once models are cached. Integrated WeInfer optimization achieving ~3.76x speedup over standard WebLLM through buffer reuse and async pipeline processing.
Does a similar job
all alternatives →- IBI built a free in-browser Llama 3 chatbot powered by WebGPU2024 · github.com · ▲547
I spent the last few days building out a nicer ChatGPT-like interface to use Mistral 7B and Llama 3 fully within a browser (no deps and installs). I’ve used the WebLLM project by MLC AI for a while to interact with LLMs in the browser when handling sensitive data but I found their UI quite lacking for serious use so I built a much better interface around WebLLM. I’ve been using it as a therapist and coach. And it’s wonderful knowing that my personal information never leaves my local computer. Should work on Desktop with Chrome or Edge. Other browsers are adding WebGPU support as well - see…
- WEWebGPU enables local LLM in the browser – demo site with AI chat2025 · andreinwald.github.io · ▲145
Browser LLM demo working on JavaScript and WebGPU. WebGPU is already supported in Chrome, Safari, Firefox, iOS (v26) and Android. Demo, similar to ChatGPT https://andreinwald.github.io/browser-llm/ Code https://github.com/andreinwald/browser-llm - No need to use your OPENAI_API_KEY - its local model that runs on your device - No network requests to any API - No need to install any program - No need to download files on your device (model is cached in browser) - Site will ask before downloading large files (llm model) to browser cache - Hosted on Github…
- BRBrowserAI – Run LLMs directly in browser using WebGPU (open source)2025 · github.com · ▲85
Check out this impressive project that enables running LLMs entirely in the browser using WebGPU. Key features: - Zero token costs, no cloud infrastructure required - Complete data privacy through local processing - Simple 3-line code integration - Built on MLC and Transformer.js The benchmarks show smaller models can effectively handle many common tasks. Currently the project roadmap includes: - No-code AI pipeline builder - Browser-based RAG for document chat - Analytics/logging - Model fine-tuning interface
- OSOpen source alternative to ChatGPT and ChatPDF-like AI tools2023 · github.com · ▲234
Hey everyone, We have been building SecureAI Tools -- an open-source application layer for ChatGPT and ChatPDF-like AI tools. It works with locally running LLMs as well as with OpenAI-compatible APIs. For local LLMs, it supports Ollama which supports all the gguf/ggml models. Currently, it has two features: Chat-with-LLM, and Chat-with-PDFs. It is optimized for self-hosting use cases and comes with basic user management features. Here are some quick demos: * Chat with documents using OpenAI's GPT3.5 model: https://www.youtube.com/watch?v=Br2D3G9O47s * Chat with documents…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology