app for interaction with documents using local LLM (mini Chat With RTX)
Hello HN! I wanted to share a side project of mine: a fully standalone app that uses a local LLM (specifically Mistral 7B) for document interaction using RAG. It supports a wide variety of document types and is designed to run right after installation. There are still quite a few bugs to iron out and many features I'm excited to add. Considering this is my first time working on such a project, I'm really happy with the progress and am learning a ton! The project is open source, so I please feel free to check out my work and leave any feedback :)
In plain words
Mini Chat With RTX is a standalone application that lets users interact with documents using a local large language model (Mistral 7B) through retrieval-augmented generation. It supports multiple document types and runs immediately after installation without requiring external services. The open-source project is designed for users who want to query and analyze documents privately on their own hardware, with the creator actively working to expand features and address issues.
written from the facts on this page · September 2026
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
Launched alongside, April 2024
the whole month →
Supabase▲2,328The Postgres developer platform is now generally available
Dev tools · 2024 · supabase.com
Cal.com Platform▲1,602Build your pixel-perfect booking experience with Atoms
Dev tools · 2024 · cal.com
deco.cx 2.0▲1,080Build web apps 10x faster with Deno, JSX, TS & Tailwind
Dev tools · 2024 · decocms.com
