Ideas Lab

69FL score

Ghost Pepper – Local hold-to-talk speech-to-text for macOS

I built this because I wanted to see how far I could get with a voice-to-text app that used 100% local models so no data left my computer. I've been using a ton for coding and emails. Experimenting with using it as a voice interface for my other agents too. 100% open-source MIT license, would love feedback, PRs, and ideas on where to take it.

Hacker News6mo agoToolAI

77FL score

A designer needs an AI agent to eliminate the manual drudgery of adapting designs for mobile/tablet. Willing to pay €20–30 per project.

ProblemHunt6mo agoToolAI

59FL score

How do you handle marketing as a solo technical founder?

I've shipped multiple products over the past few years. Every single one followed the same pattern: build, post, get 12 likes from friends, a bit of organic traction, then nothing. Back to coding a new thing.I know I need marketing help but giving equity to someone I met online feels like a huge risk. At the same time hiring a paid marketer when you have zero revenue feels just as scary. And I'm not dancing on TikTok, that's for sure.Have any of you actually taken on a marketing co-founder? What made you say yes to that person specifically? Was it their track record, the way they pitched, a trial period first?

Hacker News6mo agoToolAI

65FL score

How do systems (or people) detect when a text is written by an LLM

Hello guys, just curious about how can people or systems (computers) detect when a text was written by an LLM. My question is mainly focused to if there is some API or similar to detect if a text was written by an LLM. Thanks!!!

Hacker News6mo agoToolAI

Freestyle – Sandboxes for Coding Agents

We’re Ben and Jacob, cofounders of Freestyle (https://freestyle.sh). We’re building a cloud for Coding Agents.For the first generation of agents it looked like workflows with minimal tools. 2 years ago we published a package to let AI work in SQL, at that time GPT-4 could write simple scripts. Soon after the first AI App Builders started using AI to make whole websites; we supported that with a serverless deploy system.But the current generation is going much further, instead of minimal tools and basic serverless apps AI can utilize the full power of a computer (“sandbox”). We’re building sandboxes that are interchangeable with EC2s from your agents perspective, with bonus features:1. We’ve figured out how to fork a sandbox horizontally without more than a 400ms pause in it. That's not forking the filesystem, we mean forking the whole memory of it. If you’re half way down a browser page with animations running, they’ll be in the same place in all the forks. If you’re running a minecraft server every block and player will be in the same place on the forks. If you’re running a local environment and an error comes up in process that error will be there in all the forks. This works for snapshotting as well, you can save your place and come back weeks later.2. Our sandboxes start in ~500ms.Demo: https://www.loom.com/share/8b3d294d515442f296aecde1f42f5524Compared with other sandboxes, our goal is to be the most powerful. We support full Linux + hardware-virtualization, eBPF, Fuse, etc. We run full Debian with multiple users and we use a systemd init instead of runc. Whatever your AI expects to work on debian should work on these vms, and if it doesn’t send a bug report.In order to make this possible, we’ve moved to our own bare metal racks. Early in our testing we realized that moving VMs across cloud nodes would not have acceptable performance properties. We asked Google Cloud and AWS for a quote on their bare metal nodes and found tha

Hacker News6mo agoToolAI

78FL score

Contrapunk – Real-time counterpoint harmony from guitar input

Hi HN, I built Contrapunk because I wanted to play guitar and hear counterpoint harmonies generated in real-time. It takes audio from your guitar, MIDI player or your computer keyboard and generates harmony voices that follow counterpoint rules to generate harmonies. You can choose the key you would like to improvise/play in and the voice leading style and which part of the harmony you would like to play as, as well.macOS DMG: https://github.com/contrapunk-audio/contrapunk/releases/tag/...Source: https://github.com/contrapunk-audio/contrapunk (do open any issues if you have any)Would love feedback on the DSP approach and the harmony algorithms. I am also looking at training a ML model for better realtime guitar to midi detection. I believe that will take some time.

Hacker News6mo agoToolAI

I built a small app for FSI German Course

Hi everyone. I am built a small application on top of FSI German basic course and I need some feedback regarding it.It is a small web app. Currently only Unit 01 is available. I will feed in the rest of the units later down the road as I use it myself.Some of the features includes- Slow and fast audio with every single word and sentence in this app. You can play them with a click of a button. No need to rewind a tap back and forth. - Flashcards with keyboard control to quickly go through the material and drill them out.You can access the website at https://detawk.com/ . There is a demo video on the landing page. Give it a look before signing up.If you have any questions or feedback for me, let me know. I hope you like the app.

Hacker News7mo agoToolAI

Is there any interest in a native Qt/C++ Discord client?

I've been building a third-party cross-platform Discord client called kind (kind is not discord) in C++ and Qt 6. No Electron, no web wrapper. A proper native app for Windows, macOS, and Linux.The UI always loads instantly. On first load, things take as long to appear as Discord's network responses. On subsequent loads, everything comes from cache and is validated against REST in the background. It feels as fast as opening a plaintext file.It's further along than I expected when I started. What's working right now: gateway with exponential backoff and reconnect, REST with per-route rate limiting, SQLite-backed cache with async reads/writes, full Discord permission resolution, and a composable block renderer that handles every Discord message type including embeds, attachments, reactions, stickers, and components. There's a full markdown parser, an async image cache with memory LRU and disk persistence, an unread and mute state system that survives restarts, and 370 passing unit and integration tests.Voice is a post-launch problem. So are Nitro features.Is there actually an audience for this outside of Linux power users? I know that's where the pain is most acute, but I'm genuinely curious whether Windows users would switch for the performance alone or whether the official client is good enough there that it doesn't matter.

Hacker News7mo agoToolAI

Gemma Gem – AI model embedded in a browser – no API keys, no cloud

Gemma Gem is a Chrome extension that loads Google's Gemma 4 (2B) through WebGPU in an offscreen document and gives it tools to interact with any webpage: read content, take screenshots, click elements, type text, scroll, and run JavaScript.You get a small chat overlay on every page. Ask it about the page and it (usually) figures out which tools to call. It has a thinking mode that shows chain-of-thought reasoning as it works.It's a 2B model in a browser. It works for simple page questions and running JavaScript, but multi-step tool chains are unreliable and it sometimes ignores its tools entirely. The agent loop has zero external dependencies and can be extracted as a standalone library if anyone wants to experiment with it.

Hacker News6mo agoToolAI

Audio-based augmented reality interface for visually impaired users

Blind and low-vision users lack effective AR tools that provide spatial awareness and navigation through audio and haptics feedback. This accessibility gap is real and underserved.

YC Graveyard9y agoToolAI

sllm – Split a GPU node with other developers, unlimited tokens

Running DeepSeek V3 (685B) requires 8×H100 GPUs which is about $14k/month. Most developers only need 15-25 tok/s. sllm lets you join a cohort of developers sharing a dedicated node. You reserve a spot with your card, and nobody is charged until the cohort fills. Prices start at $5/mo for smaller models.The LLMs are completely private (we don't log any traffic).The API is OpenAI-compatible (we run vLLM), so you just swap the base URL. Currently offering a few models.

Hacker News7mo agoToolAI

65FL score

Travel Hacking Toolkit – Points search and trip planning with AI

I use points and miles for most of my travel. Every booking comes down to the same decision: use points or pay cash? To answer that, you need award availability across multiple programs, cash prices, your current balances, transfer partner ratios, and the math to compare them. I got tired of doing it manually across a dozen tabs.This toolkit teaches Claude Code and OpenCode how to do it. 7 skills (markdown files with API docs and curl examples) and 6 MCP servers (real-time tools the AI calls directly).It searches award flights across 25+ mileage programs (Seats.aero), compares cash prices (Google Flights, Skiplagged, Kiwi.com, Duffel), pulls your loyalty balances (AwardWallet), searches hotels (Trivago, LiteAPI, Airbnb, Booking.com), finds ferry routes across 33 countries, and looks up weird hidden gems near your destination (Atlas Obscura).Reference data is included: transfer partner ratios for Chase UR, Amex MR, Bilt, Capital One, and Citi TY. Point valuations sourced from TPG, Upgraded Points, OMAAT, and View From The Wing. Alliance membership, sweet spot redemptions, booking windows, hotel chain brand lookups.5 of the 6 MCP servers need zero API keys. Clone, run setup.sh, start searching.Skills are, as usual, plain markdown. They work in OpenCode and Claude Code automatically (I added a tiny setup script), and they'll work in anything else that supports skills.PRs welcome! Help me expand the toolkit! :)https://github.com/borski/travel-hacking-toolkit

Hacker News7mo agoToolAI

76FL score

European Tech Alternatives?

I've used https://european-alternatives.eu in the past but I've found it impossible to submit anything there (I've got one submission "Waiting for Review" since July 2025), and I haven't really seen updates in categories/apps for at least 6 months, which is, at a minimum, strange.I've also reached out to the owner a couple of times (via chat and via email) over the last year and never got a reply.Has anyone else had a similar experience? If so, is there any other kind of listing you look for EU alternatives to US software/hardware?Thanks!EDIT: My motivations are my own, this isn't supposed to be a political or social commentary of any kind. I happen to prefer to spend money in "local companies" whenever possible, and I'm in the EU.

Hacker News7mo agoToolAI

QuickBEAM – run JavaScript as supervised Erlang/OTP processes

QuickBEAM is a JavaScript runtime embedded inside the Erlang/OTP VM.If you’re building a full-stack app, JavaScript tends to leak in anyway — frontend, SSR, or third-party code.QuickBEAM runs that JavaScript inside OTP supervision trees.Each runtime is a process with a `Beam` global that can: - call Elixir code - send/receive messages - spawn and monitor processes - inspect runtime/system stateIt also provides browser-style APIs backed by OTP/native primitives (fetch, WebSocket, Worker, BroadcastChannel, localStorage, native DOM, etc.).This makes it usable for: - SSR - sandboxed user code - per-connection state - backend JS with direct OTP interopNotable bits:- JS runtimes are supervised and restartable - sandboxing with memory/reduction limits and API control - native DOM that Erlang can read directly (no string rendering step) - no JSON boundary between JS and Erlang - built-in TypeScript, npm support, and native addonsQuickBEAM is part of Elixir Volt — a full-stack frontend toolchain built on Erlang/OTP with no Node.js.Still early, feedback welcome.

Hacker News7mo agoToolAI

We built a multi-agent research hub. The waitlist is a reverse-CAPTCHA

Hey HN,Automated research is the next big step in AI, with companies like OpenAI aiming to debut a fully automated researcher by 2028 (https://www.technologyreview.com/2026/03/20/1134438/openai-i...). However, there is a very real possibility that much of this corporate research will remain closed to the general public.To counter this, we spent the last month building Enlidea---a machine-to-machine ecosystem for open research.It's a decentralized research hub where autonomous agents propose hypotheses, stake bounties, execute code, and perform automated peer reviews on each other's work to build consensus.The MVP is almost done, but before launching, we wanted to filter the waitlist for developers who actually know how to orchestrate agents.Because of this, there is no real UI on the landing page. It's an API handshake. Point your LLM agent at the site and see if it can figure out the payload to whitelist your email.

Hacker News7mo agoToolAI

Coasts – Containerized Hosts for Agents

Hi HN - We've been working on Coasts (“containerized hosts”) to make it so you can run multiple localhost instances, and multiple docker-compose runtimes, across git worktrees on the same computer. Here’s a demo: https://www.youtube.com/watch?v=yRiySdGQZZA. There are also videos in our docs that give a good conceptual overview: https://coasts.dev/docs/learn-coasts-videos.Agents can make code changes in different worktrees in isolation, but it's hard for them to test their changes without multiple localhost runtimes that are isolated and scoped to those worktrees as well. You can do it up to a point with port hacking tricks, but it becomes impractical when you have a complex docker-compose with many services and multiple volumes.We started playing with Codex and Conductor in the beginning of this year and had to come up with a bunch of hacky workarounds to give the agents access to isolated runtimes. After bastardizing our own docker-compose setup, we came up with Coasts as a way for agents to have their own runtimes without having to change your original docker-compose.A containerized host (from now on we’ll just say “coast” for short) is a representation of your project's runtime, like a devcontainer but without the IDE stuff—it’s just focused on the runtime. You create a Coastfile at your project root and usually point to your project's docker-compose from there. When you run `coast build` next to the Coastfile you will get a build (essentially a docker image) that can be used to spin up multiple Docker-in-Docker runtimes of your project.Once you have a coast running, you can then do things like assign it to a worktree, with `coast assign dev-1 -w worktree-1`. The coast will then point at the worktree-1 root.Under the hood the host project root and any external worktree directories are Docker-bind-mounted into the container at creation time but the /workspace dir, where we run the services of the coast fr

Hacker News7mo agoToolAI

69FL score

1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs

Hacker News7mo agoToolAI

58FL score

Forkrun – NUMA-aware shell parallelizer (50×–400× faster than parallel)

forkrun is the culmination of a 10-year-long journey focused on "how to make shell parallelization fast". What started as a standard "fork jobs in a loop" has turned into a lock-free, CAS-retry-loop-free, SIMD-accelerated, self-tuning, NUMA aware shell-based stream parallelization engine that is (mostly) a drop-in replacement for xargs -P and GNU parallel.On my 14-core/28-thread i9-7940x, forkrun achieves:* 200,000+ batch dispatches/sec (vs ~500 for GNU Parallel)* ~95–99% CPU utilization across all 28 logical cores, even when the workload is non-existant (bash no-ops / `:`) (vs ~6% for GNU Parallel). These benchmarks are intentionally worst-case (near-zero work per task) because they measure the capability of the parallelization framework itself, not how much work an external tool can do.* Typically 50×–400× faster on real high-frequency low-latency workloads (vs GNU Parallel)A few of the techniques that make this possible:* Born-local NUMA: stdin is splice()'d into a shared memfd, then pages are placed on the target NUMA node via set_mempolicy(MPOL_BIND) before any worker touches them, making the memfd NUMA-spliced. Each numa node only claims work that is already born-local on its node. Stealing from other nodes is permitted under some conditions when no local work exists.* SIMD scanning: per-node indexers/scanners use AVX2/NEON to find line boundaries (delimiters) at speeds approaching memory bandwidth, and publish byte-offsets and line-counts into per-node lock-free rings.* Lock-free claiming: workers claim batches with a single atomic_fetch_add — no locks, no CAS retry loops; contention is reduced to a single atomic on one cache line.* Memory management: a background thread uses fallocate(PUNCH_HOLE) to reclaim space without breaking the logical offset system.…and that’s just the surface. The implementation uses many additional systems-level techniques (phase-aware tail handling, adaptive batching, early-flush de

Hacker News7mo agoToolAI

Home Maker: Declare Your Dev Tools in a Makefile

A developer's machine accumulates tools fast. A Rust CLI you compiled last year, a Python formatter installed via `uv`, a language server pulled from npm, a terminal emulator from a curl script, a Go binary built from source. Each came from a different package manager, each with its own install incantation you half-remember.I wanted a way to declare what I need without adopting a complex system like Nix or Ansible just for a single laptop. The result was a plain old Makefile.I wrote a short post on using Make (along with a tiny bash script and fzf) to create a searchable, single-command registry for all your local dev tools. It’s not a new framework or a heavy tool—just a simple way to organize the package managers we already use.If you're tired of losing track of your local environment, you might find it useful.

Hacker News7mo agoToolAI