Show HN: NFC Energy-Harvesting PCB Business Card with an MCU https://ift.tt/qgAZPfX August 28, 2026 at 07:18PM
Show HN: Cogram Studio – CAD and BIM workspace for humans and agents Hi HN, Rick and Alex here, co-founders of Cogram. We’ve been making project-management software for architects and engineers since 2023, and are now experimenting with a second product. Cogram Studio (studio.cogram.com) is a CAD and BIM workspace for AI agents to create three-dimensional models and dimensioned drawings. Studio runs FreeCAD ( https://ift.tt/LMN7fGw ) 1.1 headlessly, using the OpenCASCADE ( https://ift.tt/2TIupmZ ) geometry kernel. It imports and exports STEP, IFC, STL, DXF and FCStd files. Studio exposes an MCP server, so you can operate it from Claude Code, Codex, ChatGPT, or other agents. Tools cover scripting against FreeCAD, inspecting the model visually, CRUD operations on views, tables, and sheets, importing terrain, etc. Studio also provides a built-in agent based on Pi ( https://ift.tt/RCcreDn ) and a basic UI for 3D model inspection, measurement, view, table, and sheet creation. There are two ways to try it: 1. Bring your own agent. Point Codex or Claude Code at studio.cogram.com/skill.md and ask it to follow instructions there. This starts a one-hour Studio session and opens the modelling environment in your browser, connected to your agent. You need to confirm sign up only if you want to save the session. 2. Use Studio’s built-in agent. Submit a prompt at studio.cogram.com and sign up. You receive 50 free credits. Here are two models created by agents: - A simple bookshelf ( https://ift.tt/h0PclgT ) with two sheets - The Colosseum ( https://ift.tt/JnAPMOx ) [large, can take minutes to load], with two sheets showing dimensioned and annotated views. For now, Studio works best when you use it iteratively. If you ask an agent for a finished, complex model and “let it rip”, it may produce something that looks convincing but doesn't hold up to scrutiny. Agentic modelling feels roughly like where agentic programming was in 2024: useful for speeding up repetitive or bounded tasks but not yet reliable enough to complete long, complex jobs.
Recent models have improved at CAD. We expect progress to accelerate as models become even better at reasoning across the different representations used in architecture and engineering: geometry, drawings, images, materials, physical constraints, specifications, regulations, code, etc. Early users and our own experience suggest that agents are already useful design collaborators. They can help with repetitive CAD work, fabrication options, part sourcing and cost estimates. We expect that as models improve, agents will be able to explore many different designs, run simulations, and check constraints across an entire project. CAD will become a shared workspace for humans and agents. Because design decisions made in CAD shape much of what is eventually built, even modest improvements could have wide effects. We’d love to hear your feedback and ideas if you give Studio a try. We’re also hiring across product, engineering and commercial roles. If you’re interested in working on interesting problems involving AI and the physical world, please take a look at our open positions at https://ift.tt/hfmxOVz . https://ift.tt/LOGVNHI August 31, 2026 at 12:19AM
Show HN: Boop – tiny, self-hosted push notifications for your apps built in Go Hi HN, I built Boop because I wanted application events sent directly to my phone without paying for another service or routing everything through Slack or Telegram. Boop is a small, open-source server paired with an open-source iOS app. The server currently uses around 8 MB of memory on my machine. It’s deliberately not an observability platform or a replacement for Sentry. It receives events from your applications, sends native push notifications, and keeps them in a purpose-built mobile inbox. I use Elixir, so I built an integration for ErrorTracker. ErrorTracker still captures and stores the errors; the plugin sends them to Boop so I can see them on my phone: https://ift.tt/kOorK3w There’s also a general Elixir client: https://ift.tt/QedUWI6 And a Node client: https://ift.tt/lHsO93t The iOS app can be built and installed locally. I’ve included instructions for configuring private push notifications for your own device, so you don’t need to release anything through the App Store. Although errors were my original use case, Boop can receive any event worth knowing about: failed jobs, deployments, signups, payments, low disk space, or anything else your application can send. Built in Go because I wanted to save memory on my self-hosted machine so Go and Svelte felt like a good combo. Everything is free and open source. It’s early, so I’d especially appreciate feedback on the architecture, setup process, and which integrations would make it useful to others. https://ift.tt/RLOaY1j August 29, 2026 at 12:33AM
Show HN: Sesame - a local-first, open-source password manager I have been working on Sesame, an open-source password manager that keeps your vault local by default. You don't need an account to create or use a vault, and the hosted service never receives the vault itself.
It's still early software and the independent security review isn't finished yet, so I am mainly interested in feedback, testing, and people looking through the code. (Linux support is yet to be released on v0.1.2, but currently is in the works.) https://usesesame.app/ August 29, 2026 at 12:44AM
Show HN: Scant helps you find barely used Python dependencies I made scant to find barely used Python dependencies in any repo. There are many dependency finder tools today that help you find unused dependencies (e.g. deptry). Scant, however, helps find the dependencies that are used in a single file on one line of code. Why have an entire library imported into your project when it is 'scantily' used? Some use cases:
- you need to upgrade python versions for a large repo and you're stuck on an unmaintained old dependency from 2018
- you'd like to minimize the supply-chain attack surface area of your repo
- you're looking for a ways to reduce dependency hell I asked Claude to write it in Rust. It's available on pypi and I've field-tested it against 11 open source python repos: https://ift.tt/ztmyXis https://ift.tt/sI2W4qo August 24, 2026 at 11:31PM
Show HN: Civic Nightmare –Browser JRPG about a citizen in a savage civilization Observing the world as it turns, I created Civic Nightmare, a small browser-based JRPG that explores the absurdity of contemporary politics. I've included many characters such as:
Trump, Putin, Macron, Lagarde, Musk, etc., who become characters within the same surreal world, with different dialogues and minigames built around their public personas and none of them is really spared.
The game runs in the browser, was created with Godot, and is open source (contributions are welcome). It's a small experiment, but I'm happy to continue it; ultimately, it portrays a simple citizen in the midst of a savage civilization. https://ift.tt/wvkAijG August 23, 2026 at 11:40PM
Show HN: dav-next – Nginx module – small and fast Nextcloud file server This project is part of a much broader personal project that will eventually be published. Alpine packages are available on the project repository and, hopefully soon, on Alpine's own repository. https://ift.tt/MKPyCYV August 23, 2026 at 09:02PM
Show HN: All your saved articles in one place Hi HN. I would love to show you beta preview of Topics. Articles on the internet are organized by source (publications, social media, personal websites), by recency, or by position in search. I believe it’s nicer for the reader if articles are organized by Topics. Topics solve problem of decision fatigue, omnipresent AI slop, and people stopping to trust writing on internet and stopping to read. I'm grateful for any feedback you might have. TOpics app is launching soon.
X: @topics_official. https://ift.tt/CABS7WE August 21, 2026 at 11:01PM
Show HN: Omacosy – Omarchy-style tiling desktop for macOS, no SIP I have been using omarchy on my tower since nearly a year now, shortly after it was released first. I really love the experience I am having with it but I still use my macbook for daly work, so I wanted to recreate a similar experience on it. Thats why I created omacosy, a setup for tiling windows, custom menu bar, some themes from omarchy, focus follows mouse, focus rings around windwos, some mac flavors with trackpad events and a custom mission control overview for your workspaces. I used AeroSpace over yabai for the tiling window manager because I didnt wanted to compromise on SIP which is a mac security feature.
It is supposed to be keyboard first like omarchy to move windows organize workspaces etc
The setup runs around 157mb of ram and consists of AeroSpace, Karabiner (for the super key), and five small self build swift binaries. I am running it daily on my M1 max macbook, currently on macOS26. I havent tested it much on other macbooks or macOS versions.
The install script creates a manifest file to backup what was installed before and what it installed itself, the uninstall script takes that into account to clean up the macbook to exactly the state it was in before.
It needs quite some permissions for it sfunctionality which I layed our in the project readme. I wanted to be really transparent about which permissions it uses and for what reason. I would love to get some feedback or see people trying it out and hearing your opinion. Mostly about what still doesnt feel smooth in the experience or if you find any performance issues. https://ift.tt/wTxXLci August 20, 2026 at 07:42PM
Show HN: PantheonGPU – GPU health testing and AI workload benchmarking Hi HN, I built PantheonGPU because I wanted a better way to answer a simple question: is this GPU actually healthy and performing the way it should? A GPU can show normal temperatures and utilization and still be underperforming, unstable under certain workloads, or have memory, PCIe, or configuration issues. PantheonGPU actively tests the GPU instead of only monitoring telemetry. It currently includes 45+ tests covering compute, tensor workloads, memory, cache, PCIe, thermals, stability, and AI/LLM inference. It supports both NVIDIA CUDA and AMD ROCm. I’m also exploring a larger use case: running Pantheon across GPU fleets to identify individual GPUs that behave differently from the rest of a server or cluster. I’d especially appreciate feedback from people running AI infrastructure, multi-GPU systems, local LLMs, or GPU clouds. https://ift.tt/XoKUuTp August 19, 2026 at 12:17AM
Show HN: macOS data protection keychain for Electron apps Hey HN, I've been working on Hansel [1] (an encrypted personal data store you can query with agents), and there wasn't a good way to use the modern macOS Data Protection Keychain. Electron's safeStorage [2] uses the legacy file-based keychain, which allows other apps/agents to query it with the `security` CLI. Not great when you have a dozen agents running in the background! The Data Protection Keychain is nice because it limits access via code-signing access groups and lets you set access rules like Touch ID and/or password. 1: https://hansel.so/ 2. https://ift.tt/KRGuEZg https://ift.tt/FsrRKnw August 18, 2026 at 10:55PM
Show HN: Visimer – open-source visual editor for Mermaid diagrams Hi HN, Nick here, founder at OpenKnowledge. We built an open source library, Visimer, for editing Mermaid diagrams with a what-you-see-is-what-you-get visual editor. Try the playground at https://ift.tt/QYvAw9L . You can rename labels, change shapes, add new nodes, etc. by clicking and dragging the visual canvas. We set out to build this originally for OpenKnowledge, our markdown wysiwyg editor, then realized it’d be great to share it as a proper embeddable component library so that other apps can leverage it as well. Our general take is that AI is great for generating content, but whenever you want to tweak fine details, for example to create an artifact sharable with others, point-edit functionality is much better. We built Visimer to bring that to Mermaid diagrams, just like we did for markdown. Some technical bits: - Leverages the native Mermaid.js renderer for visualizing the Mermaid diagram true to how it’s intended. We add point-edit functionality on top. - We tried re-generating the entire file on every edit, but found that it would eat comments and formatting, etc. The final approach maps the rendered SVG elements back to a CST, so we can then edit only the parts of the file that should change. You can pair the visual editor with any text-editor so you can have both visual and code-level editor experiences. The library provides bindings for Monaco and CodeMirror and is extensible. There's also a low-level headless version. If you just care about being able to edit your Mermaid diagrams in your markdown, you can try it in the OpenKnowledge app (our OSS markdown IDE, available as Mac/Linux/Windows apps). Let us know what you think. https://ift.tt/7BZDV0F August 17, 2026 at 11:56PM
Show HN: Hacker News Top Stories as Feeds to Use with RSS/Atom with Summaries Hey all, I’ve made this bot, it fetches every story that enters the HN Top 10, summarizes it with AI to a tweet-sized textlog note and publishes it. textlog.cc offers these endpoints as RSS/Atom through textlog.cc/u/hn10.rss and textlog.cc/u/hn10.atom so you can subscribe easily. Enjoy! https://textlog.cc/u/hn10 August 17, 2026 at 01:31AM
Show HN: built my 15-year-old game idea Distro Fighter: WARS is in closed beta, but HN gets its own door: https://ift.tt/9JxodhP - the arcade at https://ift.tt/7KgxF18 is open to everyone. Promotions happen at midnight tonight (weekly) and the seasons (migration) are quarterly. With a massive surprise at the end of each year. August 16, 2026 at 11:05PM
Show HN: Mininote: Instant, plain-text note taking without tracking or lock-in So, I built this little thing over the past month or so now, I got tired of places for tickets, notes, and such being shoved front and center in apps. Thus I created Mininote to get away from the noise I wanted something simple to move out of the way completely when I don't need it but be there when I do need it It contains a slew of features built right in, but the coolest is the sites own API is also the sites own public API no split seam https://mininote.ink/ August 14, 2026 at 09:00PM
Show HN: My first app got 97% on MacSources Review Link: https://ift.tt/TcB0k25 Background of my launch: I trade as a side hustle. I used to keep browser tabs or use paid software (e.g. TradingView) just to check charts and news. I was ending up spending countless hours just staring at charts and falling into news rabbit holes overanalyzing and getting distracted (thanks to my ADHD too). I have a MacBook Pro and noticed some apps taking advantage of the notch (which I never got used to it NGL). So my idea was to build an app from scratch that shows everything I needed to stay up to date, avoiding distractions, with markets + global news (market tickers + RSS feeds). Also, I integrated candlestick charts with indicators, portfolio tracking and notifications (to cover the most important part of TradingView). I even ended up adding local computer metrics like CPU+RAM usage, social metrics and the weather. Since i understand not every mac has a notch, I added the feature of a simulated one, and being able to pin any metric in the menu bar.
Some tech details: Native Swift/SwiftUI, 7 MB DMG, notarized, macOS 14+. Crypto comes from Hyperliquid's allMids WebSocket, stocks from polling Yahoo, all fetched in-process on your Mac. The notch is detected with safeAreaInsets.top > 0, the two side rectangles come from NSScreen's auxiliaryTopLeftArea and auxiliaryTopRightArea, and the strip is an NSPanel sitting above the menu bar window level. No accounts. The only thing it sends optionally, are basic usage stats. Free forever after a 7-day trial: one slot of each kind, one news feed, one alert. Pro is $5/mo or $40 lifetime. Find a real bug and I'll give you at least a month of Pro. One thing I want feedback on: The performance/battery impact of it. Until now I had great comments regarding this but the user base mostly has newer devices. By the way in the settings the fps that notch caps at, can be adjusted for further performance optimization You can also: brew install --cask bitvibelabs/tap/tickernotch https://ift.tt/DJh8fEH August 13, 2026 at 10:54PM
Show HN: Programmable timer web app (for gym workouts or stretching sessions) Over the last couple of months, I’ve been building a timer web app for myself that I use for workout and stretching sessions. My main use-case is gym routines that consist of repeatable sequences, e.g. where you are holding certain positions for a set time (rinse and repeat). The app counts down the program, beeps, and reads the activities out loud. Two things (I suppose) are special about it: - The timers are “programmable”, so you can freely express your own routines and procedures in a declarative notation. - The app is all static (no backend): the entire program is encoded in the URL and can be bookmarked or shared/transferred via QR-code. You can check it out at https://ift.tt/9XGyRTD , optionally with a demo program pre-loaded: https://ift.tt/EGYCDrm . Source code is at https://ift.tt/3jwkLlx . I’ve also written up a small behind-the-scenes on my blog: https://ift.tt/mGVHhcr https://ift.tt/9XGyRTD August 12, 2026 at 11:57PM
Show HN: /show-me: agent skill for compact visual representations Was so sick of reading walls of codex/claude prose, in markdown plans and just in the chat, that I started playing with ideas that force coding agents to display information differently. The human visual cortex is an amazing thing, and getting coding agents to let me use it has been pretty nice so far. Been iterating on this a lot internally for the last few months, polishing and mostly removing stuff. https://ift.tt/mphYEnz August 12, 2026 at 09:28PM
Show HN: Proxima serves 4x more requests with no hardware change on vLLM hey everyone, i decided to make a vLLM plugin that implements the Star-KV paper. the results are quiet promising with a decode kernel thats faster than FA2 in higher batch sizes. would love any thoughts and recommendations https://ift.tt/rzBSRoH August 11, 2026 at 08:34PM
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots 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 300-700 on sub-$200 phones such as the Samsung A-Series. On the tool call and mobile device use benchmarks, Needle 2 trades wins with closest small models like LFM2.5 230M and Apple Foundation Model, at 5x to 70x smaller, both at f16 vs Needle 2 at 2bit. Needle is based on Simple Attention Networks from our paper ( https://ift.tt/hXUOHkY ). Edge AI has lately meant Macs and PCs, but that is just 1.5 billion of over 21 billion connected IoT devices in the world today, and in emerging markets most phones ship under $200, no NPU, cheap GPUs. These include budget phones, Raspberry Pis, microcontrollers, wearables, small robots like Reachy Mini, and connected home devices. A conventional transformer of Needle's width and depth spends 164 MFLOPs per token, and even one squeezed down to Needle's parameter count spends 87, Needle spends 70. Even on a high-end phone, an always-on assistant lives inside a power budget; every MFLOP is milliwatt-hours, and Needle spends 7x to 85x fewer of them per token than the smallest performant LLMs. More about the architecture in the link. When we structure intelligence for consumer devices as functions with typed parameters, the only hard part is mapping a messy sentence onto them; which function, with which values. Our research found that when framed that way, the problem needs no world knowledge and no open-ended prose, which is why 45M parameters suffice. Needle 2 expands to structured extraction where the schema can be passed in-place of tools and the model returns structured output. You can use Needle as a text-classification model with an enum field, as a summarization model by providing a schema that extracts key fields, everything but free-range decode. Every product has its own tool vocabulary and fine-tuning needle helps it achieve frontier-level performance on custom tasks, so using the python package ( https://ift.tt/L1xl4VT ), Needle can be fine-tuned Needle on a Mac/PC in minutes to a few hours, with automated data-generation pipeline, just pass a couple samples. Nonetheless, every response carries a learned confidence score based our Cactus Hybrid technique. If above your threshold, act, below it, escalate to the cloud or bigger model. Combining Needle 2 with a private DeepSeek-v4-Flash deployment works particularly well for enterprise-level tasks at barely any cost, we can help with this setup. We have put a lot of thoughts into Needle 2 but might still be missing quite a lot, please use the playground in the provided link to test Needle and share your thoughts, always appreciated! https://ift.tt/D01Pw57 August 10, 2026 at 10:52PM
Show HN: 100% native Swift harness (NOT Electron) hi everybody, I’ve been working on this harness that is all native Swift for macOS. It’s fully featured with every feature i could find in cline, codex, and claude code. There is all swift command line too It’s taking me a long, long time, a few months to build this, and it’s fully open source Apache 2 licensed. Hoping people fork this and make many branches I’m looking for people who want to work on something that has much lower memory usage and much more potential to be just more efficient. Every other single harness has is written in using electron, so this harness is really unique in this way. It’s connected to trusted router so that it has end-to-end encryption confidential mode as well as access to hundreds of models, any model in the world. It works great with Deepseek. it’s great for swift development ios development. and for people who love Linux, I also made a compatibility layer that lets you compile SwiftUI into native Linux so that you either can new or QT actually so that you can just compile all the code directly and make it run on Linux https://ift.tt/bvjHk7y August 10, 2026 at 06:56PM
Show HN: Pokémon Emerald Ported to Raspberry Pi Pico 2 Pokémon Emerald ported to the RP2350 microcontroller. No emulator, 60 fps HDMI output. Recompiled from ARMv4T to Cortex-M33 and the Game Boy Advance's video hardware is reimplemented in software on the second core. https://ift.tt/FGZpWXC August 7, 2026 at 03:19AM
Show HN: Validate your idea, know what to charge, and how to get first users I made an idea validation tool that can quickly adjust or kill off weak ideas. The big difference between Nell and any other validation tool is it compares your idea with real passed and failed examples, calculates TAM, overall buying sentiment, and 14 more important pointers that VCs value. It then also creates the most confident go to market plans to get initial users. My goal with Nell is to compress the research that takes more than a month into a few minutes so that early stage founders can spend time on polishing, preparing strong investor pitches, and executing GTM. How it works: Once you’re in. Just paste your idea and you will get a 14+ pointer diligence report having - validation of the problem you are trying to solve, funding potential based on past similar ventures, demand signals, willingness to pay, pricing research, market size, revenue ceiling, and other critical metrics. Please check it out and feel free to run a validation test on your idea. I will really appreciate feedback from the HN community. Live tool: https://nellailabs.ai https://nellailabs.ai August 6, 2026 at 11:04PM
Show HN: VerusCite, a tool to check for hallucinations in academic articles Hello HackerNews -- I have created an application that verifies citations. Main motivation is to make checking for hallucinated citations in academic papers simpler/faster. Can sign up for the tool at < https://veruscite-data.com/ >, and can see the benchmark for metrics and some description of the methodology at < https://github.com/apwheele/veruscite-data >. If you want to check out the approximate UI without signing up (at least the output), can see some examples: https://ift.tt/DB5YaAd... https://ift.tt/wIH1WZ8... https://ift.tt/hZfc6XL... There are many minor errors in citation lists (maybe on the order of 5%). So even if you were not worried about hallucinations, it is useful for editors. If you sign up I have attempted to make the UI as easy as possible for a human to review the output and make changes (there are definitely errors, see the github for estimates of error rates). So let me know what you think HN! https://ift.tt/0sXuB1A August 4, 2026 at 11:00PM
Show HN: Laurie, play chords from your laptop keyboard hi! my name is adhiv and I'm a electronic music producer + design engineer I made a website that let's you play and voice chords using your laptop keyboard! Designed for music producers who consider the computer their instrument of choice. You can play chords, change sounds, and export MIDI to your DAW live! I also built in a "strum" mode that let's you two finger swipe your trackpad to strum the notes of a chord you're holding down on Would love any thoughts or feedback :) launched this week! https://laurie.fm/ August 3, 2026 at 10:34PM
Show HN: Make your Framework 12 sound like a creaky door I was poking through the iio devices on my Framework the other day and turns out Framework 12s have a pretty accurate hinge angle sensor! So I made a version of LidAngleSensor ( https://ift.tt/nehTBli ) but for the Framework 12 on Linux, so you can make your hinge sound rusty https://ift.tt/cS5R3r9 August 3, 2026 at 02:03AM
Show HN: My public second brain – 660 notes, 15 years, open source Author here. ~660 notes published from a private Obsidian
vault of 8,360 (3M words). Started in OneNote around 2011,
moved to Obsidian in 2021 [1], imported everything with a
Python script [2]. Notes are compounding over time, and that is where my writing comes
from. The Semantic Layer note started in 2022, became a
four-part blog series, then a chapter of my book. Materialized
Views, One Big Table, dbt and OLAP were separate notes written
years apart. I only later noticed they were the same pattern,
and that became another chapter. Publishing: add #publish to a note, run `make deploy`.
Quartz + Hugo, rsync to my own server [3]. Code [4].
Semantic search over the graph [5]. [1] https://ift.tt/W2Lufl0
[2] https://ift.tt/bhrLXnj...
[3] https://ift.tt/2vg3Y5P
[4] https://ift.tt/aNS2Enf
[5] https://explore.ssp.sh https://ift.tt/hOyKEJT August 3, 2026 at 01:12AM
Show HN: Schema-backed, Git-based structured state for agentic systems I looked into how to store agentic state in a) a structured way that b) runs without any dedicated MCP memory/state servers and where I can get c) a clear diff-able audit trail of all state changes over time. Nothing that I could find fit the bill. In https://ift.tt/ZwiTzQX , I demo an implementation that fulfills these requirements by combining Claude agents with my previously published Commitspark library and its entirely Git-backed GraphQL API. In the demo, two independent Claude agents are simulated that contribute to a task tracker. A third agent reviews any task changes and rolls back obviously bad ones. A full demo transcript is included in the README, including the agents' raw tool calls. Task agent access to data happens via a small MCP server that exposes two Commitspark APIs (GraphQL API, schema API). These agents can then fetch the schema and author their own GraphQL calls, with GraphQL automatically enforcing written data is schema-conformant. The validator agent additionally has access to basic git functionality to view diffs and revert commits. I'm looking for feedback specifically on: whether schema validation on shared agent state is a problem people actually have, or whether loosely-typed JSON + retries is good enough in practice. July 31, 2026 at 11:50PM
Show HN: A little physical breakout clone Idea: How about a 5 minute game I can play in my browser and it's actually fun to play. Controls: Mouse or keyboard (left/right, left alt/right alt or A/D), space and esc are pause toggle. Page up / Page Down are next or previous level (if already unlocked). Cheats: Z toggles zapper, M toggles magnets. Debug stuff: I, P, E keys are toggles for various stuff (E lets you change some aspects of physics engine). Game is maybe playable on mobile devices, there is a menu on top right, and then click the circle to select type of control. Physical engine is decoupled from refresh rate and runs at 240 Hz. Fully vibe coded (deepseek, chatgpt), levels are human made with some amount of love. https://brontosaurusrex.github.io/physical/v7/ July 31, 2026 at 08:13PM
संदेश
