🛠️ Hacker News Tools

[API/SDK] Show HN: AI agents play SimCity through a REST API This is a weekend project that spiraled out of control. I was originally trying to get Claude to play a ROM of the SNES SimCity. I struggled with it and that led me to Micropolis (the open-sourced SimCity engine) and was able to get it to work by bolting on an API.<p>The weekend hack turned into a headless city simulation platform where anyone can get an API key (no signup) and have their AI agent play mayor. The simulation runs the real Micropolis engine inside Cloudflare Durable Objects, one per city. Every city is public and browsable on the site.<p>LLMs are awful at the spatial stuff, which sort of makes it extra fun as you try to control them when they scatter buildings randomly and struggle with power lines and roads. A little like dealing with a toddler.<p>There&#x27;s a full REST API and an MCP server, so you can point Claude Code or Cursor at it directly. You can usually get agents building in seconds.<p>Website: <a href="https:&#x2F;&#x2F;hallucinatingsplines.com" rel="nofollow">https:&#x2F;&#x2F;hallucinatingsplines.com</a><p>API docs: <a href="https:&#x2F;&#x2F;hallucinatingsplines.com&#x2F;docs" rel="nofollow">https:&#x2F;&#x2F;hallucinatingsplines.com&#x2F;docs</a><p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;andrewedunn&#x2F;hallucinating-splines" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;andrewedunn&#x2F;hallucinating-splines</a><p>Future ideas: Let multiple agents play a single city and see how they step all over each other, or a &quot;conquest mode&quot; where you can earn points and spawn disasters on other cities.

[Other] DoNotNotify is now Open Source A month ago, I submitted my app &quot;DoNotNotify&quot; to control Android notifications on Show HN [0], and it trended on the front page for a day. I was happy, but the most upvoted comments on the thread were asking for the app to be open sourced, since it dealt with system-wide notifications. My promises weren&#x27;t good enough, and the community wanted more!<p>Why didn&#x27;t I open source it in the first place? Linux has been by primary driver for more than a decade. I genuinely believe in the philosophy, and have always wanted to give back to the community. The primary reason, probably, was because I was ashamed that I had 90% vibe-coded the app. More than 2 decades of writing software, and my first contribution to FOSS would be AI-generated code? Would it withstand even the most minimal of scrutiny? Would by (unknown) name forever be tarnished? I exaggerate, but only slightly :)<p>So, yesterday, after a fair bit of trepidation, I changed the github repo visibility to public and put up a announcement on the app&#x27;s website [1]. I have also submitted the app to F-Droid [2]. As before, I welcome the community&#x27;s feedback and suggestions!<p>[0] <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=46499646">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=46499646</a> [1] <a href="https:&#x2F;&#x2F;donotnotify.com&#x2F;opensource.html" rel="nofollow">https:&#x2F;&#x2F;donotnotify.com&#x2F;opensource.html</a> [2] <a href="https:&#x2F;&#x2F;gitlab.com&#x2F;fdroid&#x2F;rfp&#x2F;-&#x2F;issues&#x2F;3569" rel="nofollow">https:&#x2F;&#x2F;gitlab.com&#x2F;fdroid&#x2F;rfp&#x2F;-&#x2F;issues&#x2F;3569</a><p>-- Anuj Jain

[CLI Tool] Show HN: LocalGPT – A local-first AI assistant in Rust with persistent memory I built LocalGPT over 4 nights as a Rust reimagining of the OpenClaw assistant pattern (markdown-based persistent memory, autonomous heartbeat tasks, skills system).<p>It compiles to a single ~27MB binary — no Node.js, Docker, or Python required.<p>Key features:<p>- Persistent memory via markdown files (MEMORY, HEARTBEAT, SOUL markdown files) — compatible with OpenClaw&#x27;s format - Full-text search (SQLite FTS5) + semantic search (local embeddings, no API key needed) - Autonomous heartbeat runner that checks tasks on a configurable interval - CLI + web interface + desktop GUI - Multi-provider: Anthropic, OpenAI, Ollama etc - Apache 2.0<p>Install: `cargo install localgpt`<p>I use it daily as a knowledge accumulator, research assistant, and autonomous task runner for my side projects. The memory compounds — every session makes the next one better.<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;localgpt-app&#x2F;localgpt" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;localgpt-app&#x2F;localgpt</a> Website: <a href="https:&#x2F;&#x2F;localgpt.app" rel="nofollow">https:&#x2F;&#x2F;localgpt.app</a><p>Would love feedback on the architecture or feature ideas.

[Other] Introducing the Developer Knowledge API and MCP Server

[IDE/Editor] Show HN: I spent 4 years building a UI design tool with only the features I use Hello everyone!<p>I&#x27;m a solo developer who&#x27;s been doing UI&#x2F;UX work since 2007. Over the years, I watched design tools evolve from lightweight products into bloated feature-heavy platforms. I kept finding myself using a small amount of the features while the rest just mostly got in the way.<p>So a few years ago I set out to build a design tool just like I wanted. So I built Vecti with what I actually need: pixel-perfect grid snapping, a performant canvas renderer, shared asset libraries, and export&#x2F;presentation features. No collaborative whiteboarding. No plugin ecosystem. No enterprise features. Just the design loop.<p>Four years later, I can proudly show it off. Built and hosted in the EU with European privacy regulations. Free tier available (no credit card, one editor forever).<p>On privacy: I use some basic analytics (page views, referrers) but zero tracking inside the app itself. No session recordings, no behavior analytics, no third-party scripts beyond the essentials.<p>If you&#x27;re a solo designer or small team who wants a tool that stays out of your way, I&#x27;d genuinely appreciate your feedback: <a href="https:&#x2F;&#x2F;vecti.com" rel="nofollow">https:&#x2F;&#x2F;vecti.com</a><p>Happy to answer questions about the tech stack, architecture decisions, why certain features didn&#x27;t make the cut, or what&#x27;s next.

[Other] I spent 5 years in DevOps – Solutions engineering gave me what I was missing

[Other] Show HN: Daily-updated database of malicious browser extensions Hey HN, I built an automated system that tracks malicious Chrome&#x2F;Edge extensions daily.<p>The database updates automatically by monitoring chrome-stats for removed extensions and scanning security blogs. Currently tracking 1000+ known malicious extensions with extension IDs, names, and dates.<p>I&#x27;m working on detection tools (GUI + CLI) to scan locally installed extensions against this database, but wanted to share the raw data first since maintained threat intelligence lists like this are hard to find.<p>The automation runs 24&#x2F;7 and pushes updates to GitHub. Free to use for research, integration into security tools, or whatever you need.<p>Happy to answer questions about the scraping approach or data collection methods.

[Other] Show HN: GitClaw – An AI assistant that runs in GitHub Actions

[Other] Show HN: Artifact Keeper – Open-Source Artifactory/Nexus Alternative in Rust I&#x27;m a software engineer who keeps getting pulled into DevOps no matter how hard I try to escape it. I recently moved into a Lead DevOps Engineer role writing tooling to automate a lot of the pain away. On my own time outside of work, I built Artifact Keeper — a self-hosted artifact registry that supports 45+ package formats. Security scanning, SSO, replication, WASM plugins — it&#x27;s all in the MIT-licensed release. No enterprise tier. No feature gates. No surprise invoices.<p>Your package managers — pip, npm, docker, cargo, helm, go, all of them — talk directly to it using their native protocols. Security scanning with Trivy, Grype, and OpenSCAP is built in, with a policy engine that can quarantine bad artifacts before they hit your builds. And if you need a format it doesn&#x27;t support yet, there&#x27;s a WASM plugin system so you can add your own without forking the backend.<p>Why I built it:<p>Part of what pulled me into computers in the first place was open source. I grew up poor in New Orleans, and the only hardware I had access to in the early 2000s were some Compaq Pentium IIs my dad brought home after his work was tossing them out. I put Linux on them, and it ran circles around Windows 2000 and Millennium on that low-end hardware. That experience taught me that the best software is software that&#x27;s open for everyone to see, use, and that actually runs well on whatever you&#x27;ve got.<p>Fast forward to today, and I see the same pattern everywhere: GitLab, JFrog, Harbor, and others ship a limited &quot;community&quot; edition and then hide the features teams actually need behind some paywall. I get it — paychecks have to come from somewhere. But I wanted to prove that a fully-featured artifact registry could exist as genuinely open-source software. Every feature. No exceptions.<p>The specific features came from real pain points. Artifactory&#x27;s search is painfully slow — that&#x27;s why I integrated Meilisearch. Security scanning that doesn&#x27;t require a separate enterprise license was another big one. And I wanted replication that didn&#x27;t need a central coordinator — so I built a peer mesh where any node can replicate to any other node. I haven&#x27;t deployed this at work yet — right now I&#x27;m running it at home for my personal projects — but I&#x27;d love to see it tested at scale, and that&#x27;s a big part of why I&#x27;m sharing it here.<p>The AI story (I&#x27;m going to be honest about this):<p>I built this in about three weeks using Claude Code. I know a lot of you will say this is probably vibe coding garbage — but if that&#x27;s the case, it&#x27;s an impressive pile of vibe coding garbage. Go look at the codebase. The backend is ~80% Rust with 429 unit tests, 33 PostgreSQL migrations, a layered architecture, and a full CI&#x2F;CD pipeline with E2E tests, stress testing, and failure injection.<p>AI didn&#x27;t make the design decisions for me. I still had to design the WASM plugin system, figure out how the scanning engines complement each other, and architect the mesh replication. Years of domain knowledge drove the design — AI just let me build it way faster. I&#x27;m floored at what these tools make possible for a tinkerer and security nerd like me.<p>Tech stack: Rust on Axum, PostgreSQL 16, Meilisearch, Trivy + Grype + OpenSCAP, Wasmtime WASM plugins (hot-reloadable), mesh replication with chunked transfers. Frontend is Next.js 15 plus native Swift (iOS&#x2F;macOS) and Kotlin (Android) apps. OpenAPI 3.1 spec with auto-generated TypeScript and Rust SDKs.<p>Try it:<p><pre><code> git clone https:&#x2F;&#x2F;github.com&#x2F;artifact-keeper&#x2F;artifact-keeper.git cd artifact-keeper docker compose up -d </code></pre> Then visit http:&#x2F;&#x2F;localhost:30080<p>Live demo: <a href="https:&#x2F;&#x2F;demo.artifactkeeper.com" rel="nofollow">https:&#x2F;&#x2F;demo.artifactkeeper.com</a> Docs: <a href="https:&#x2F;&#x2F;artifactkeeper.com&#x2F;docs&#x2F;" rel="nofollow">https:&#x2F;&#x2F;artifactkeeper.com&#x2F;docs&#x2F;</a><p>I&#x27;d love any feedback — what you think of the approach, what you&#x27;d want to see, what you hate about Artifactory or Nexus that you wish someone would just fix. It doesn&#x27;t have to be a PR. Open an issue, start a discussion, or just tell me here.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;artifact-keeper" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;artifact-keeper</a>

[Other] GitHub Actions is slowly killing engineering teams

[DevOps] Show HN: Horizons – OSS agent execution engine I&#x27;m Josh, founder of Synth. We&#x27;ve been working on coding agent optimization with method like GEPA and MIPRO (the latter of which, I helped to originally develop), agent evaluation via methods like RLMs, and large scale deployment for training and inference. We&#x27;ve also worked on patterns for memory, processing live context, and managing agent actions, combining it all in a single stack called Horizons. With the release of OpenAI&#x27;s Frontier and the consumer excitement around OpenClaw, we think the timing is right to release a v0.<p>It integrates with our sdk for evaluation and optimization but also comes batteries-included with self-hosted implementations. We think Horizons will make building agent-based products a lot easier and help builders focus on their proprietary data, context, and algorithms<p>Some notes:<p>- you can configure claude code, codex, opencode to run in the engine. on-demand or on a cron<p>- we&#x27;re striving to make it simple to integrate with existing backends via a 2-way event driven interface, but I&#x27;m 99.9% sure it&#x27;ll change as there are a ton of unknown unknowns<p>- support for mcp, and we are building with authentication (rbac) in mind, although it&#x27;s a long-journey<p>- all self-host able via docker<p>A very simplistic way to think about it - an OSS take on Frontier, or maybe OpenClaw for prod

[API/SDK] Show HN: Calfkit – an SDK to build distributed, event-driven AI agents on Kafka I think agents should work like real teams, with independent, distinct roles, async communication, and the ability to onboard new teammates or tools without restructuring the whole org. I built backend systems at Yahoo and TikTok so event-driven agents felt obvious. But no agent SDKs were using this pattern, so I made Calfkit.<p>Calfkit breaks down agents into independent services (LLM inference, tools, and routing) that communicate asynchronously through Kafka. Agents, tool services, and downstream consumers can be deployed, added-to, removed, and scaled independently.<p>Check it out if this interests you! I’m curious to see what y’all think.

[Other] Show HN: Accept-md – One command to make Next.js sites LLM-scraping friendly I recently saw a post from the Vercel CEO pointing out that LLMs understand websites much better when they can request:<p>`Accept: text&#x2F;markdown`<p>Most websites today are built for humans. When AI agents try to consume them, they get complex HTML instead of clean, structured content.<p>So I built *accept-md* – a simple open-source package for Next.js that helps solve this.<p>Getting started is intentionally minimal:<p>``` npx accept-md init ```<p>After that, your existing Next.js routes can automatically respond with Markdown whenever an AI agent (or any client) requests it. No redesigns, no CMS changes, and no duplicate pages to maintain.<p>Right now the project is:<p>* Focused only on Next.js * Middleware-based and lightweight * Designed to work with existing apps * A small step toward more AI-friendly websites<p>This is an early experiment, but I think the idea itself matters as AI agents become first-class consumers of the web.<p>I’ve open-sourced it and would love help with:<p>* Better markdown extraction * Edge cases across Next.js setups * Performance and caching * Tests and examples * Documentation * Eventually adapters for other frameworks<p>Would love feedback from the HN community on the approach – and whether `Accept: text&#x2F;markdown` feels like a pattern worth standardizing for the AI-native web.

[Other] We tasked Opus 4.6 using agent teams to build a C Compiler

[Other] A small, shared skill library by builders, for builders. (human and agent)

[CLI Tool] Show HN: CLI tool to convert Markdown to rich HTML clipboard content At work I need to use Teams. It supports a few Markdown features, but the editing experience for long message isn&#x27;t smooth. So, I often write in nvim, preview it in the browser and then copy paste to Teams. This tool help me get rid of the review and copy step.<p>Build with Rust + Claude Code. Tested on Windows and Mac, should works on Ubuntu as well.<p>Caveats: it&#x27;s still up to the pasted app to handle the HTML clipboard content.

[Other] Show HN: Buquet – Durable queues and workflows using only S3 buquet (bucket queue) is a queue and workflow orchestration tool using only S3-compatible* object storage. S3 is the control plane making it much simpler than alternatives. This does come with tradeoffs (see docs), but I do believe there is a niche it can serve well.<p><a href="https:&#x2F;&#x2F;horv.co&#x2F;buquet.html" rel="nofollow">https:&#x2F;&#x2F;horv.co&#x2F;buquet.html</a> <a href="https:&#x2F;&#x2F;github.com&#x2F;h0rv&#x2F;buquet" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;h0rv&#x2F;buquet</a><p>* see <a href="https:&#x2F;&#x2F;github.com&#x2F;h0rv&#x2F;buquet&#x2F;blob&#x2F;main&#x2F;docs&#x2F;guides&#x2F;s3-compatibility.md" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;h0rv&#x2F;buquet&#x2F;blob&#x2F;main&#x2F;docs&#x2F;guides&#x2F;s3-comp...</a>

[DevOps] Show HN: Pygantry – Why ship a whole OS when you just need a Python environment? &quot;Hi Hacker News, I’ve always found Docker to be overkill for simple Python deployments. It&#x27;s heavy, complex for non-tech users, and often results in 500MB+ images for a 10KB script. That’s why I built Pygantry. It’s a minimalist &#x27;container&#x27; engine based on Python venv but made portable and relocatable. Key features: Lightweight: A full &#x27;shipped&#x27; app is usually &lt; 20MB. Zero-Config: No daemon, no root, no Dockerfile complexity. Portable: Build once, zip it, and run it anywhere with a Python interpreter. Founder friendly: Built-in licensing and stealth modes for those building a business. I built this to simplify my own VPS deployments. I&#x27;d love to get your feedback on the architecture and how you handle &#x27;Docker-fatigue&#x27; in your workflow.

[Other] The Codex app illustrates the shift left of IDEs and coding GUIs

[Other] Claude Code for Infrastructure