MiniLetter
Read newsletters in one calm place
What it does
MiniLetter pulls newsletters out of your inbox and turns them into a focused daily reading flow. Connect Gmail or Outlook, review what you want to keep, and read one issue at a time without inbox noise. Original newsletters stay first. Optional AI Briefs are there when you want the short version, but MiniLetter is built around calmer reading, not replacing everything with summaries.
Does a similar job
all alternatives →
- LALoomLetter – an app to organize newsletters and listen on the go2025 · loomletter.app · ▲14
Hi HN, I love newsletters. I first started signing up for Market Briefs right after COVID—trying to figure out why everyone was so scared of another market crash. It was exciting at first, but juggling a startup meant I couldn’t keep up, and soon my inbox was a mess of unread emails. I’d often ask myself: do I read them all, or delete and start fresh? That’s why I built LoomLetter—a simple iOS app that pulls in all your newsletter emails into one place, lets you organize them into custom lists, and even reads them aloud using AI. I built it as a one-man project to solve my own problem of…
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 · 28d 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