NoemaAI Launch
I wanted to share a use case for Noema Overfit, a model-paging system available today in the Noema app. For disclosure, I founded Noema and I am part of the team that has helped develop the system. The way it works is that the non-expert weights remain resident in memory, while the model’s routed expert weights are read from storage as needed. This makes it possible to run models that would otherwise exceed the device’s available memory, with the expected tradeoff of higher time to first token and slower generation. For a 699-token initial prompt, I measured: Prefill speed: 34.4…
NoemaAI Launch launched on September 25, 2025 with 8 votes, #1,468 of 8,160 launches that month and more than 50% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
Noema is a privacy-first local AI app for iPhone. Build a personal knowledge base with PDFs, textbooks, and notes, run Hugging Face models offline (GGUF, MLX, SLM), and chat fast and privately: your data never leaves your device.
Noema is a private local AI assistant for iPhone, iPad, Mac, and Vision Pro. Run language models, search your files, and use tools on device.
Run language models, search your files, and use tools on your Apple devices. Load local models, Apple Foundation Models, and support models from one native library. Chats, projects, and tool history sync across your Apple devices. Select a model installed on your awake Mac and use it from your iPhone or iPad. The model stays on the Mac; only requests and replies are sent. GGUF, MLX, Core ML, ExecuTorch, and Apple Foundation Models in one native client. Read PDFs more thoroughly and ground answers in your own datasets with retrieval that stays on device. Open web evidence, inspect citations, and connect MCP tools when the task needs them. Continue chats across devices and use the models…from noemaai.com
In the maker’s words, at launch
I wanted to share a use case for Noema Overfit, a model-paging system available today in the Noema app. For disclosure, I founded Noema and I am part of the team that has helped develop the system. The way it works is that the non-expert weights remain resident in memory, while the model’s routed expert weights are…
Does a similar job
all alternatives →
I made an app to use local AI as daily driver2024 · recurse.chat · ▲637Hi Hackers, Excited to share a macOS app I've been working on: https://recurse.chat/ for chatting with local AI. While it's amazing that you can run AI models locally quite easily these days (through llama.cpp / llamafile / ollama / llm CLI etc.), I missed feature complete chat interfaces. Tools like LMStudio are super powerful, but there's a learning curve to it. I'd like to hit a middleground of simplicity and customizability for advanced users. Here's what separates RecurseChat out from similar apps: - UX designed for you to use local AI as a daily driver.…
Noodle SeedJan 2026 · noodleseed.com · ▲432Hi HN! I’m Uzair, Founding Engineer of Noodle Seed. We enable businesses to deploy native apps inside ChatGPT conversations when users need recommendations. What we built: A multi-tenant no-code platform that helps businesses create custom ChatGPT Apps. When someone asks “find me a legal firm in Austin,” businesses using our platform appear with their own branded app - complete with UI components, interactive elements, and real-time information. Not random results from old training data, but actual custom experiences with each business’s branding. Try it: We’re in limited beta with founding…
- IBI built a non-linear UI for ChatGPT2024 · grafychat.com · ▲459
Hi HN, I built this out of frustration of the evergrowing list of AI models and features to try and to fit my workflow. The visual approach clicks for me so i went with it, it provides more freedom and control of the outcome, because predictable results and increased productivity is what I’m after when using conversational AI. The app is packed with features, my most used are prompt library, voice input and text search, narration is useful too. The app is local-first and works right in the browser, no sign up needed and it's absolutely free to try. BYOAK – bring your own API Keys. Let me…
Core – open source memory graph for LLMs – shareable, user owned2025 · github.com · ▲112I keep running in the same problem of each AI app “remembers” me in its own silo. ChatGPT knows my project details, Cursor forgets them, Claude starts from zero… so I end up re-explaining myself dozens of times a day across these apps. The deeper problem 1. Not portable – context is vendor-locked; nothing travels across tools. 2. Not relational – most memory systems store only the latest fact (“sticky notes”) with no history or provenance. 3. Not yours – your AI memory is sensitive first-party data, yet you have no control over where it lives or how it’s queried. Demo video:…
Igel – A CLI tool to run machine learning without writing code2020 · github.com · ▲405a delightful machine learning tool that allows you to train, test, and use models without writing code - nidhaloff/igel
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, September 2025
the whole month →
The site hit #1 on HN about a year ago. Got enough traffic that I turned it into a proper API. What's there: - REST API — 35k products, manually filterable by category, free key, 60 req/min - CLI — npx anycrap random -c food - faker.js plugin — bundled, no API call, works offline - HuggingFace dataset — full 35k rows for ML/training https://anycrap.shop/developers
AI · 2025 · anycrap.shop
I made a built-from scratch Wayland Compositor to display any GUI app* in the terminal! I think there is a lot of unexplored potential in custom Wayland compositors, a lot of really cool things you can embed existing applications into! So, I started with embedding apps into the terminal because that is the easiest input/output (output is just utf-8 and I use the great `chafa` library for that, and I just read from stdin for the input). If you have any other ideas for cool Wayland compositors, let me know. I purposedly wrote 80% the app in Typescript to appeal to the most developers and…
Dev tools · 2025 · github.com
- IR
Years ago I stumbled across a basic version of this concept and it stuck with me. I knew if I was ever going to take on such a project, it would need to be flawless, but without coding experience it was just another idea that would never happen. By the end of 2024, as AI coding tools exploded everywhere, I finally had a way to make it real. I started from zero knowledge and spent months collaborating with AI agents as a learning experience. Every pixel and every function went through me. The AI translated what I asked for into code, but every decision was human. I didn't use existing OS…
AI · 2025 · mitchivin.com
