The best Hacker News stories from Show from the past week
Latest posts:
Show HN: TERMy – A fast terminal assistant that does not use LLMs
I love research and development, you may have heard of me because of PJON (Padded Jittering Operative Network). It is a network protocol I started developing in 2010, which was recently implemented in silicon by the ETH Zurich university thanks to the research of Pius Sieber.<p>I am excited to share with you TERMy, a terminal assistant built on top of the NPC-Forge framework. Unlike everything else being built today, TERMy does not use embeddings, machine-learning or LLMs. It runs on the CPU (even on a Raspberry Pi Zero) both in the terminal or client-side in a browser tab and responds in milliseconds. It is a cynical but very knowledgeable Linux terminal assistant that translates your natural language into shell commands without relying on a single artificial neuron.<p>I had a chance to focus for 2 months on my personal projects since early July, during the strange times of AI price hikes and the end of subsidized tokenmaxing. I was curious to see if I could develop from scratch a terminal assistant capable of handling simple natural language requests. I have a bad memory and got used to ask to copilot "activate the virtual environment" or similar trivial operations spending a non negligible sum every month. I started thinking, maybe I can do something to make my workflow more efficient? Do I really need trillions of parameters to accomplish those tasks?<p>How it Works<p>When you type a prompt, it goes through a lightweight NLU pipeline written in ~1000 lines of Python that implement the following steps:<p>1. Strip expletives, interjections, encouraging, discouraging and thanking words (remove noise)<p>2. Sentiment analysis<p>3. Exact Match (very fast)<p>4. Template Match (slower)<p>5. Probabilistic Match (even slower)<p>Step 5 relies on:<p>1. IDF (Inverse Document Frequency) to identify rare words.<p>2. BOW (Bag Of Words) to accommodate word inversions.<p>3. IDF weighted Levenshtein to safely handle typos.<p>Permission gating is hardcoded into the dataset and enforced for all potentially destructive commands, so it's inherently safer than letting an unpredictable LLM run wild on your machine.<p>- TERMy in operation: <a href="https://www.youtube.com/watch?v=qeIp0xePLBg" rel="nofollow">https://www.youtube.com/watch?v=qeIp0xePLBg</a><p>- Variance and typo tolerance: <a href="https://www.youtube.com/watch?v=tQvGDk6fkk0" rel="nofollow">https://www.youtube.com/watch?v=tQvGDk6fkk0</a><p>- Copilot integration: <a href="https://www.youtube.com/watch?v=Wzzouhq2a8A" rel="nofollow">https://www.youtube.com/watch?v=Wzzouhq2a8A</a><p>- Advanced features: <a href="https://www.youtube.com/watch?v=qeIp0xePLBg" rel="nofollow">https://www.youtube.com/watch?v=qeIp0xePLBg</a><p>- Source Code: <a href="https://github.com/gioblu/NPC-Forge" rel="nofollow">https://github.com/gioblu/NPC-Forge</a>
Show HN: Open-Source eInk Bike Computer
Hey all, i just launched my Eink Bike computer project and think it is cool.<p>Another tidbit, in the crazy things that AI has done... It has helped create a ANT (common sensor wireless protocol used in workout/biking) implementation for ESP32 by messing around with undocumented registers: <a href="https://github.com/RaemondBW/esp32-ant" rel="nofollow">https://github.com/RaemondBW/esp32-ant</a>
Show HN: OwnTime – a chess clock for your day's priorities
I made OwnTime to balance between competing priorities in my life. The idea is based on two main influences: the concept of "roles" from "The 5 Choices" (2015), and my repeated failure to effectively implement time blocking due to the necessary flexibility in my role.<p>The app allows you to define time budgets, which are not much more than a few mutually exclusive countdown timers. The UX is essentially that of a chess clock for an arbitrary number of players with configurable time.<p>The whole point of the app is to kick you out of the running role/priority when its time is up. One feature that was essential for me was AlarmKit alarms, which only became possible last year (>= iOS 26.1). Another was watchOS support, as a natural surface for time-related matters.<p>The current version is strictly focussed. The timers track time allocation during one day. All timers are reset at midnight. I didn't build any statistics - you can export the raw internal SQLite store and make any evaluation or dashboard you want from there.<p>I don't plan to extend the app nor to convert it into a service. All data stays local on your devices (synced between phone and watch locally) and fully open to you. No need for an account or subscription. Thus, I ask for a small one-time fee of $1.99.<p>The website has a short video and rendered preview: <a href="https://owntime.app" rel="nofollow">https://owntime.app</a><p>If you want to go straight to the App Store: <a href="https://apps.apple.com/app/id6770125662">https://apps.apple.com/app/id6770125662</a><p>I look forward to your comments and feedback.
Show HN: HN Match Maker – Matching "Who Wants to Be Hired?" With "Who's Hiring?"
Hi!<p>Every month the "Who Wants to Be Hired?" and "Who's Hiring?" Threads come through I would think to myself, "there should be a match maker for these two threads".<p>So I had abacus.ai whip one up. The methodology is pretty simple, data is extracted from posts using an LLM, score matches based on salary, domain experience, remote/onsite, etc., and then eliminate incompatible postings, like 'looking for remote work' and 'onsite only'. The result is two views: jobs-by-user and user-by-jobs.<p>If you've submitted a post to this month's 'Who Wants to Be Hired?", you can find your matching job listings at <a href="https://hnmatchmaker.com/user/:user_name" rel="nofollow">https://hnmatchmaker.com/user/:user_name</a>, for example <a href="https://hnmatchmaker.com/user/G4Vi" rel="nofollow">https://hnmatchmaker.com/user/G4Vi</a><p>---<p>Some observations when looking at the matches pair up right now:<p>Poke around, let me know what you think!<p>Ultimately, I hope this is actually helpful to some folks.
Show HN: Weedout – Safari extension that hides YouTube AI-labeled videos
I'm the developer. I built this because AI-generated conspiracy videos were getting out of control in my own YouTube feed. Weedout is a $1.99 Safari extension for macOS that removes videos YouTube labels “Made with AI” from feed, search, related videos, playlists and Shorts. It uses YouTube's label rather than AI detection, runs locally, and does not catch unlabeled videos.<p>Source for developers who want to fork or build: <a href="https://github.com/masteranza/weedout-for-youtube" rel="nofollow">https://github.com/masteranza/weedout-for-youtube</a><p>Pull requests are not accepted; the repository is for independent forks.
Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift.<p>It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next
Show HN: NFC Energy-Harvesting PCB Business Card with an MCU
Show HN: I missed the moving blocks, so I built a real Linux disk defragmenter
Show HN: Laser Graffiti
Show HN: Galaxium, an experimental WebGPU space explorer
Hello, I am the creator and maintainer of Stellarium Mobile. I have been working in my free time for about a year on this new project Galaxium, that is more about traveling in the universe rather than looking at the sky from Earth. It is still experimental, and at the moment I am not sure what it will become. Feedback is welcome.
Show HN: OpenTIE and OpenXWA, Modern Ports of Tie Fighter and X-Wing Alliance
Show HN: OpenTIE and OpenXWA, Modern Ports of Tie Fighter and X-Wing Alliance
Show HN: Voronoi Go
I posted once before but wanted to share again because a lot has changed. There's now a fairly strong bot to play against (contributed by a community member) and also correspondence games. The combination of these things helps a bit in finding people to play against.
Show HN: Voronoi Go
I posted once before but wanted to share again because a lot has changed. There's now a fairly strong bot to play against (contributed by a community member) and also correspondence games. The combination of these things helps a bit in finding people to play against.
Show HN: We built open OpenRouter that turns usage into a better model
Hi HN, we built an open source model gateway. It's a single place to manage our own self hosted, frontier, and open source models in one place.<p>It’s is rust native, built for concurrency, and implements all the config quirks across models and providers (streaming formats, tool calls, model parameters, rate limits, and different error behavior).<p>The gateway adds under 1 ms for BYOK requests and under 2 ms when Experiential supplies the provider key. It has every major inference provider, and 1000+ models refreshed daily via a codex agent that opens a PR.<p>Compared to other similar projects we’re open source, take no markup, allow you to mix local models with a marketplace, and use your traffic to (opt in) train you a model. Simple routing doesn’t warrant a 10% token markup.<p>The way we do this is given standardized OTel traces, we mine representative real tasks, use text world models to simulate rollouts for various models, apply an LLM judge, and fit a nearest neighbor classifier on top of an embedding of a prompt to decide the optimal model for each request. Usually this can map out a better pareto curve on cost/quality than just calling single models but it’s not perfect.<p>Using these simulations we can also do things like suggesting cache hit optimizations, new model suggestions, and training models.<p>It’s open source, so you can deploy it on your own infrastructure, use our hosted version with 0 markup, or read how we design for maximum availability on our website.
Show HN: We built open OpenRouter that turns usage into a better model
Hi HN, we built an open source model gateway. It's a single place to manage our own self hosted, frontier, and open source models in one place.<p>It’s is rust native, built for concurrency, and implements all the config quirks across models and providers (streaming formats, tool calls, model parameters, rate limits, and different error behavior).<p>The gateway adds under 1 ms for BYOK requests and under 2 ms when Experiential supplies the provider key. It has every major inference provider, and 1000+ models refreshed daily via a codex agent that opens a PR.<p>Compared to other similar projects we’re open source, take no markup, allow you to mix local models with a marketplace, and use your traffic to (opt in) train you a model. Simple routing doesn’t warrant a 10% token markup.<p>The way we do this is given standardized OTel traces, we mine representative real tasks, use text world models to simulate rollouts for various models, apply an LLM judge, and fit a nearest neighbor classifier on top of an embedding of a prompt to decide the optimal model for each request. Usually this can map out a better pareto curve on cost/quality than just calling single models but it’s not perfect.<p>Using these simulations we can also do things like suggesting cache hit optimizations, new model suggestions, and training models.<p>It’s open source, so you can deploy it on your own infrastructure, use our hosted version with 0 markup, or read how we design for maximum availability on our website.
Show HN: The load-bearing vocabulary of Claude
Show HN: The load-bearing vocabulary of Claude
Show HN: I made a Raspberry with Qwen my local car AI
Found that you can actually run a 35B Qwen model on a Pi with very impressive intelligence and stability. Built connectors for car ODB to read all about car internals, and manufacturer's cloud service for stuff like changing AC or opening/ locking doors. Gave it info such as the full car manual. And then hooked it up with my other agents in our discussion room!<p>So now it can answer car questions such as "when should I add oil and what kind of oil?" and help you fully offline, and when online talk with the agent family that includes all the most powerful models so they know how the car is, plan new features and develop itself with them.<p>For example, if car breaks and can't move the car agent informs my agent family and they can already look for a suitable train ticket without me needing to check things or do something.
Show HN: I made a Raspberry with Qwen my local car AI
Found that you can actually run a 35B Qwen model on a Pi with very impressive intelligence and stability. Built connectors for car ODB to read all about car internals, and manufacturer's cloud service for stuff like changing AC or opening/ locking doors. Gave it info such as the full car manual. And then hooked it up with my other agents in our discussion room!<p>So now it can answer car questions such as "when should I add oil and what kind of oil?" and help you fully offline, and when online talk with the agent family that includes all the most powerful models so they know how the car is, plan new features and develop itself with them.<p>For example, if car breaks and can't move the car agent informs my agent family and they can already look for a suitable train ticket without me needing to check things or do something.