YourLocalAI
Desktop RAG app, 100% offline, zero cloud, no subscriptions.
What it does
Strict & Free Chat Modes Strict mode only answers from your uploaded documents and never invents information. Free mode combines your documents with general AI knowledge, clearly labeled. Switch anytime. Document Filtering Select specific documents to query instead of searching everything. Ask questions about just the NDA, just the lease, or any combination you choose.
Does a similar job
all alternatives →
- QPQuilt – Powerful RAG UI for Document QA2024 · quilt.fly.dev · ▲63
Hey HN! We've just launched Quilt, a robust RAG (Retrieval-Augmented Generation) UI that revolutionizes how you interact with your documents. Key features: - Multi-user setup with private/public document collections - Advanced hybrid RAG pipeline combining full-text & vector search - Smart citations with in-browser PDF preview and highlights - Fully customizable settings and prompts through the UI Making an account is free, no need to even use a strong password: this is only to ensure your documents are separate from the rest. We're keen to hear your thoughts and feedback. What features…
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 · 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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
