Buy A Modem

Launch HN: Drafted (YC P26) – Models for residential architecture

I’m Nick, founder of Drafted (https://www.drafted.ai). We’re training models that generate residential architecture from structured design constraints.Product demo: https://www.youtube.com/watch?v=8QkJ7jNU9y4Residential architecture is still one of the most expensive, slow, and inaccessible creative processes in the world. Designing a custom home typically costs $10,000–$50,000 or more, takes months, and requires making major decisions before most people can even visuali

Show HN: HashMeterAi – Private AI Token Real Usage Meter for All Models

The honest, local-first usage meter for AI coding tools. Claude Code, Codex, Kimi, Qwen CLI, HashCortx, HashCerebrum — unified into one clean dashboard with usage based trophies :)

Show HN: Ghostty in-browser with real client-side back end

A real work in progress I've got here. Our good friend Ghostty is now haunting the browser.Ghostty Playground is an experimental project based on ghostty-web. It includes the full Ghostty terminal with configs, like themes and keybinds (config panel is based on zerebos' ghostty-config).It runs a real Linux-like backend directly in the browser via BrowserPod with a dedicated filesystem, port-listening, bash, git, node.js, npm etc.It includes the ability to download small AI models via H

How Qualcomm Cashes In On The $600 Billion AI Binge

Qualcomm (QCOM) is one of the most important companies in mobile computing. Its processors and cellular modems power billions of smartphones worldwide, while its licensing business generates high-margin royalty revenue from essential wireless patents. The company has also expanded its tech into automobiles, virtual reality headsets, and AI PCs.

Best Friends Murder GIF by Kelsea Ballerini

Best Friends Bff GIF by evite

zakes bantwini dancing GIF by Universal Music Africa

Your Wi-Fi limits gigabit internet. Optimize it anyway.

If you're paying for a gigabit internet plan, that essentially means that your connection to the ISP can theoretically reach around 1Gbps. However, it doesn't mean every device in your home will see ...

Show HN: Clor – give your agent claws

At my last job I spent a year building an agentic coding platform used by hundreds of thousands of people. Along the way I tried building a hosting service on OpenClaw, and also ran Hermes myself for a while. Both projects have some great feature ideas, but when I tried to use them for real work they failed more often than not, and their security models worried me. I just couldn't see either one becoming something I'd trust enough for myself/friends/family. After a lot of exp

Show HN: OMT – A simple Python CLI for testing local Ollama models

Selecting the "best" local model usually depends on the task and the hardware.I created this script as an easy way to test local Ollama models and keep the test output organized.When you run the script interactively, it asks which model you want to use, what your prompt is, how many times you want to run it, and (optional) the temperature you'd like to set. It can also be scripted with command-line flags.The output is saved in Markdown/JSON within an organized file structure

Launch HN: Hyper (YC P26) – Company brain to power agentic development

Hey HN, we’re Shalin & Kanyes, best friends who've been hacking together for 10+yrs, and now founders of Hyper (https://heyhyper.ai/). Hyper is a shared “company brain” that plugs into information flowing inside a company to make AI agents and automations better and ultimately save people time.Models have gotten good enough that they can (mostly) take on long-horizon, complex tasks. We believe the bottleneck now is that these smart-enough models often lack information abo

Show HN: Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud

Hi HN, we’re Nick and Drew, and we’re building boxes.dev – the first cloud-only agentic dev environment (ADE) that gives every Codex and Claude Code agent its own cloud computer.We’re two engineers who previously built Gem (co-founder/CTO and first hire), and we spent the last year coding almost exclusively using Codex and Claude Code. It’s been a huge change to how we code, and it’s been exhilarating seeing the models keep getting better – but we eventually realized that developing on loca

Bad MCP design costs your agent 5x more tokens

I recently did some tests on two MCPs with identical functionalities. Turns out one of them has really bad performance. So I wanna share those bad MCP design patterns that cause this.It all started when I wrote an MCP Server (MCP-A) for a to-do list app. Later, the app officially released its own MCP Server (MCP-B). Both MCPs have the same functionalities and hit the same backend API.The experiment is set up as follows:- Both MCP Servers connect to the same ToDo list account, and it will be rese

Show HN: On-device transcriber that's 97% accurate at identifying speakers

I’ve spent the last seven months building a tool I wish I’d had in my previous roles. MimicScribe is a macOS menu bar app that fits the "AI notetaker" category. It has accurate on-device speaker identification (a first possibly?), real-time meeting talking points for discovery calls, and a fully keyboard- and voice-driven interface.I believe the accuracy of the speaker ID system is its biggest strength. I used fluid audio’s port of (https://github.com/fluidInference&#x2F

Show HN: I benchmarked LLM agents on fixing real-world security vulnerabilities

I built a benchmark with 20 real CVEs across 18 Python projects (Pillow, GitPython, yt-dlp, urllib3, etc). I've run it over 5 LLM agents (3 OpenAI, 2 poolside) and 3 different prompts (full advisory, locate, diagnose) with a total of 300 runs. The agents are tasked to fix security vulnerabilities in a sandboxed environment and they are scored against a hidden security tests from the maintainer's own fix.Best solve rate was 50%. On the other 50%, some fixes are sometimes coherent and pa

Show HN: Lazarus, a coding agent for long-horizon tasks

I have been interested in long-horizon coding tasks for a while, especially with benchmarks like FrontierSWE, where even the best coding agents like Codex and Claude Code struggle to complete tasks.These agents come with a collection of tools like bash, file edits, grep, glob, etc.Lazarus takes a different approach. The idea is to give the model exactly one tool: a persistent Python runtime.Model writes Python code, executes it, and receives stdout/stderr. Through Python it inspects repos,

Launch HN: General Instinct (YC P26) – Frontier models on edge devices

Hey HN, Guanming and Bill here from General Instinct (https://general-instinct.com/).After years of working in robotics, we kept running into the same problem: the best models never fit the hardware we actually had available.The models that performed best were usually designed around datacenter assumptions: large GPUs, lots of memory bandwidth, and reliable network access. But most physical systems have the opposite constraints.That led us down the path of figuring out how much of

Show HN: I nerfed our coding agents on purpose

Tl;dr: I trained a classifier to route to the least expensive model and reasoning depth to complete the request. Coupling that with additional automated token efficiency techniques has yielded 3x usage for the same spend. For anyone interested in trying it themselves: https://nerfguard.comVarious teammates and I switched over to Codex from Claude Code recently. We still bounce between the tools, but Codex’s speed and steerability coupled with performance gains were hard to ignore. One