🛠️ All DevTools

Show HN: SubjectiveZero, an open-source agentic node editor for creative coding Hey there,<p>My name is Clem, I&#x27;ve been a solo indie dev for a couple years now, exploring frontier tech like XR and agentic workflows in the context of creative &#x2F; interactive work.<p>I&#x27;ve been building creation tools for a while and some common design challenge is to figure out the right level of abstraction for your tool. You can always make it super advanced and complex with low level concepts (shader composition, actual code etc.) but then you get something with a high complexity &#x2F; learning curve. On the other hand, if you make your tool too high level, it might be easier to use at first, but people will most likely hit a wall eventually and start fighting with your tool to get their edge case done (you see that on mobile a lot actually).<p>With this prototype (called SubjectiveZero), I&#x27;d like to imagine that we can kind of move the &quot;slider&quot; on the abstraction layer, meaning that you can actually start with prompts that describe the goal, and you can go as high level (stay with abstract prompts) or low level as you&#x27;d like (more specific prompts, or even edit the generated code directly)! The agent orchestration actually understand your context and work along side with you to figure out what could be the best node graph structure for your project (that and some fun little procedural UI done at the node level).<p>If i had to pitch it in 30 seconds, I&#x27;d say &quot;Think TouchDesigner and friends but with agent orchestration&quot;.<p>When you use it, it will generate real native code (Swift&#x2F;Metal for now) that you can actually hot reload and iterate on either manually or through agents. It&#x27;s still an early prototype and macOS only for now, but I&#x27;d love to get genuine feedback that could help me drive where this project should go next (or not).<p>Lastly, I&#x27;m absolutely open and upfront on the fact that I used agentic coding for this, but as people say: &quot;kept on a short leash&quot;. The architecture and specs were relatively well thought out and I personally prefer to be in the loop and review all the code being written to make sure it&#x27;s going in the right direction.<p>Oh and it&#x27;s open source :-)<p>Hope you like it! <a href="https:&#x2F;&#x2F;sxp.studio&#x2F;apps&#x2F;subz" rel="nofollow">https:&#x2F;&#x2F;sxp.studio&#x2F;apps&#x2F;subz</a>

Surprising lessons from my research scientist job search

Proton AG Services is currently experiencing some issues

Write code like a human will maintain it

A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.

A modern, C++-native, test framework for unit-tests, TDD and BDD - using C++14, C++17 and later (C++11 support is in v2.x branch, and C++03 on the Catch1.x branch)

AI-generated videos to maximally drive a target brain region

[Other] Let's build a simple interpreter for APL – part 1

Build your own vulnerability harness

Why American ambulance rides are so expensive

Show HN: Rubiks Cube Solver Speedcube is an open-source platform for speedcubers featuring a Rubik&#x27;s Cube solver, competition timer, algorithm library, and AI-assisted cube recognition directly in the browser.<p>Built with React, TypeScript, Rust, and Python, the project aims to become an all-in-one platform for cubers—from beginners to competitive solvers.<p><a href="http:&#x2F;&#x2F;github.com&#x2F;williamisnotdefined&#x2F;rubiks-cube-solver&#x2F;" rel="nofollow">http:&#x2F;&#x2F;github.com&#x2F;williamisnotdefined&#x2F;rubiks-cube-solver&#x2F;</a>

Building a real-time AI tutor for 5-year-olds

Ancient Roman Board Game

How GitHub gave every repository a durable owner

Show HN: Reviving my 2001 college band with AI 25 years ago, I was approached to join a band called Fading Maize at Ripon College in Wisconsin. We did what we could with what we had. We recorded 3 albums over the next 3 years and played at as many bars and coffee shops as we could. We built a website with Microsoft Frontpage. Then we all went our separate ways, got married, had kids, focused on other things.<p>Earlier this year I had the idea to approach the lead singer who wrote all of the lyrics and melodies to the stuff we played back then and wanted to &quot;reimagine&quot; everything in 2026 using AI. That&#x27;s the project I want to share here!<p>The site has a before&#x2F;after player where you can flip between the original dorm-room recording and the 2026 version mid-song without losing your place, so you can hear exactly what changed. The original 2001 website is preserved and browsable at <a href="https:&#x2F;&#x2F;www.fadingmaize.com&#x2F;2001" rel="nofollow">https:&#x2F;&#x2F;www.fadingmaize.com&#x2F;2001</a>, rough edges intact.<p>On the AI question, since it&#x27;s the elephant: the songs, lyrics, and arrangements are the original human work from 2001-2003. AI gets a bad rap and I can totally see why, but our case was different. We wrote the lyrics, we created the melodies, we played the parts, it just didn&#x27;t sound as good as we heard it in our own heads.<p>Being fully transparent about our use of AI, sticking tightly to our original lyrics and melodies, but making full use of AI to give us the studio, session players, and production budget we never had seemed like the right balance of concerns.<p>I&#x27;m super proud of how it turned out and the transparency we&#x27;ve used along the way. Happy to discuss the audio pipeline, the site (Next.js), or what it&#x27;s like to A&#x2F;B your 20-year-old self!

OpenAI faked inability to search training data, hid billions of logs, NYT says

Show HN: Pylon Sync, an agent-first full-stack realtime framework I created Pylon to make it easier to move from hobby projects to full production apps.<p>When I work on hobby projects, I usually use React or Next.js because they are quick to set up and easy to deploy on Vercel. For production apps, I separate the frontend and backend, then deploy the backend on AWS. But setting up a full backend on AWS can be complex and costly, especially for simple apps.<p>Pylon is a full-stack, real-time framework that includes server-rendered React, TypeScript functions, entities, policies, real-time sync, built-in authentication, and support for background and scheduled jobs. By default, it uses SQLite, but you can switch to Postgres for production. The authentication system is heavily inspired by better-auth. The runtime is a Rust server that runs TypeScript functions and server-rendered React using Bun.<p>Pylon itself is inspired by Rails and focuses on convention over configuration, so you have fewer decisions to make before deploying. This approach applies to modern React apps, real-time sync, TypeScript server functions, authentication, job management, and deployment.<p>One of Pylon’s main goals is agent compatibility. It lets coding agents build and deploy apps with no setup, quick understanding, secure defaults, and easy deployment, all without requiring any third-party services. Pylon works for both quick projects and production apps where performance, observability, ownership, and self-hosting matter.<p>While it’s easy to self-host Pylon apps, Pylon Cloud provides managed hosting with a developer experience similar to Vercel. You can deploy from git or the CLI, get an instant URL, add custom domains, and go live in seconds. Each app runs on its own server, which can scale to zero, with TLS and global caching enabled.<p>If you have experience with Next.js, Vercel, Convex, Supabase, Firebase, better-auth, or Rails, I’d love to hear your feedback.<p>Create your first app: npm create @pylonsync&#x2F;pylon@latest<p>Website: <a href="https:&#x2F;&#x2F;www.pylonsync.com" rel="nofollow">https:&#x2F;&#x2F;www.pylonsync.com</a><p>Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;pylonsync&#x2F;pylon" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;pylonsync&#x2F;pylon</a><p>Docs: <a href="https:&#x2F;&#x2F;docs.pylonsync.com&#x2F;introduction" rel="nofollow">https:&#x2F;&#x2F;docs.pylonsync.com&#x2F;introduction</a><p>LLMS: <a href="https:&#x2F;&#x2F;docs.pylonsync.com&#x2F;llms.txt" rel="nofollow">https:&#x2F;&#x2F;docs.pylonsync.com&#x2F;llms.txt</a><p>Skill: npx skills add pylonsync&#x2F;pylon<p>Examples: <a href="https:&#x2F;&#x2F;github.com&#x2F;pylonsync&#x2F;pylon&#x2F;tree&#x2F;main&#x2F;examples" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;pylonsync&#x2F;pylon&#x2F;tree&#x2F;main&#x2F;examples</a>

Show HN: I built a web tool to see and edit what an AI thinks before it answers I run a small AI lab and playground and got super excited about Anthropics paper &quot;Verbalizable Representations Form a Global Workspace in Language Models&quot; (<a href="https:&#x2F;&#x2F;transformer-circuits.pub&#x2F;2026&#x2F;workspace&#x2F;index.html" rel="nofollow">https:&#x2F;&#x2F;transformer-circuits.pub&#x2F;2026&#x2F;workspace&#x2F;index.html</a>)<p>It talks about how they use a tool they call a Jacobian Lens to view inside the middle layers of LLM while it&#x27;s working before it commits to a word (token).<p>I wanted to see if I could get a version of this running on the open models and to my surprise it worked! I ran some experiments with it and build a public facing free tool anyone can use with your own prompts.<p>Ask the model to describe a symbol of &quot;three curving lines of water&quot; and you can watch &quot;ocean&quot;, &quot;sea&quot;, and &quot;surf&quot; light up a few layers deeper before it settles on &quot;waves&quot;.<p>You can also edit the internal state. Insert &quot;fire&quot; into the middle layer of the ocean prompt and the answer shifts to something about heat.<p>For fun &#x2F; curiosity sake, I also developed way to let the model read its own inner workspace and then decide to suppress or amplify a concept, and run the prompt again.<p>Interesting finding from running it across models. J-lens beats a plain logit lens on some architectures and does nothing on others, and it isn&#x27;t about size. A 0.5B Qwen reads better than a 2.8B Pythia. Every Pythia I tried gained basically nothing; the Llama and Qwen models gained a lot. <a href="https:&#x2F;&#x2F;lucid.earthpilot.ai&#x2F;research" rel="nofollow">https:&#x2F;&#x2F;lucid.earthpilot.ai&#x2F;research</a><p>This is a 48 hour old project based on emerging research and built on a small model, a small probe set on rented GPUs - but I found it genuinely exciting. The code is open.<p>I also included a page context &quot;Docent&quot; AI agent you can chat with about whatever you see to help understand what is going on.<p>Happy to have folks poke around and break it.<p>I imagine the applications for allowing models to self-reflect &#x2F; edit internal states can be useful for alignment, confidence, bias detection, etc. and this tool lets you play with the early stages of that.

GPT-5.6 <a href="https:&#x2F;&#x2F;deploymentsafety.openai.com&#x2F;gpt-5-6&#x2F;gpt-5-6.pdf" rel="nofollow">https:&#x2F;&#x2F;deploymentsafety.openai.com&#x2F;gpt-5-6&#x2F;gpt-5-6.pdf</a><p><a href="https:&#x2F;&#x2F;developers.openai.com&#x2F;api&#x2F;docs&#x2F;guides&#x2F;latest-model" rel="nofollow">https:&#x2F;&#x2F;developers.openai.com&#x2F;api&#x2F;docs&#x2F;guides&#x2F;latest-model</a>

Show HN: Devthropology – Better Insights for GitHub Repos Devthropology is a passion project built on top of GitHub pull data. The name is a play on developer anthropology. Pull request data can be cut a lot of ways. The functionality has been built out of curiosity as I want to see different insights into codebases that I work on. Some of the data is typical and other parts I haven&#x27;t seen elsewhere.<p>I think of this as an improved GitHub Insights page, with faster performance, more detail, and a focus on how work moves through a codebase. The main entity is a contributor, which has two sides: authoring PRs and reviewing&#x2F;giving feedback to others. From there, you can see repository wide stats, user interactions, contribution trends, file health, and collaboration patterns. Some insights are useful for understanding velocity and code health in the AI era.<p>Details for each page:<p>- Homepage: A high level summary of the repository. Showing age, file types, active contributors, new and churned users. I track the author age at merge, so you can see the tenure of people shipping changes over time.<p>- File explorer: One of my favorite parts. I build a graph of files, tracking renames and moves, to build a complete history. Rolling up, every file and folder is assigned an outlook such as active, developed, stale, touched by people who are likely gone. You can easily see contributor timelines, recent changes, and for some files, their rename&#x2F;move history and related files that often change together (useful for a coding agent).<p>- Trends: The densest page, showcasing the velocity of contributions and trying to understand if AI is helping ship more. Charts are cut by year for comparisons, tracking PR size, output, rounds of review, and approval latency by different percentiles. PRs are further cut into bucketed sizes to help drill in deeper. Helps to show that smaller PRs are likely still faster to ship while very large PRs (product of AI?) are slowing down.<p>- Relationships: A graph of interactions between contributors, weighted by PR activity, with a simple algorithm. Communities are grouped with links showing one way vs bidirectional. You can adjust time or raise the score to filter out noise. Clicking on contributors shows the scores of interactions and if they mostly give or receive feedback.<p>- Contributors: Search all contributors, showing a few lifetime metrics. Clicking in shows an overview of their profile with some high level details. A few author&#x2F;reviewer specific stats are shown across four time frames with their rank, each row is clickable. Below that is recent author&#x2F;reviewer PR activity, including rounds, comments, and review timing.<p>- Author&#x2F;Reviewer reports: A handful of metrics showing performance of a contributor from both sides of a PR, one as an author and one as a reviewer. Cells are color coded and bucketed into tiers to easily see where someone sits in the repository. Can be filtered by user, team, or time.<p>Couple of key terms and limitations:<p>- Contributor is any account that has authored or commented on a PR that’s been merged. This can include bots - Round of review &#x2F; “round” occurs when a nonauthor leaves comments and the author pushes more commits; tries to simulate a back and forth. - “Effective&quot; approval is the approval that actually matters for merging, i.e. the first approval after the last round of review. Example: A opens a PR, B approves, C then requests changes and A pushes more commits, C approves, C&#x27;s approval is the effective one (B&#x27;s is stale). - Trends&#x2F;Reports can be filtered by team but unfortunately without a private API key, I cannot sync teams. For a few repos I have created a few small teams<p>Please take a look, there&#x27;s a lot of buttons, dropdowns, and clickable links. The demo repos were selected because they are private companies building in the open, with patterns similar to private repos: smaller contributor sets and more activity per contributor.<p>Appreciate any feedback below or at hey@devthropology.com