Manual IQ
Your documents. Your machine. No cloud. No hallucinations
What it does
ManualIQ lets you ask plain-English questions about your technical manuals and get precise, cited answers — with page numbers and section references. Cloud or fully offline. When a schematic is referenced, it surfaces the diagram inline. Your PDFs never leave your machine. One install, two modes, zero compromise. 🎯 Launch offer: $149 one-time — use code PRODUCTHUNT at checkout for 50% off. No subscription. No per-query fees after purchase. Yours forever.
Does a similar job
all alternatives →
Inscribe: Offline AI Chat & DocumentsNov 2025 · ▲8Your private AI assistant that works completely offline
- IBI built a SaaS that lets you create digital manuals with drag and drop2025 · chyrid.com · ▲6
My best friend and I developed a SaaS last month while working full-time: Chyrid (chyrid.com). It’s a tool for creating digital manuals without design or coding skills. Users build structured, polished documents with a drag-and-drop editor, and Chyrid handles the formatting—without using AI. We built it because most documentation tools are either too complex or too unstructured. A company is already using it for onboarding and process docs, but we’re still figuring out how to position it and who finds it most useful. Would love any thoughts on potential use cases or feedback on the concept.…
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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com