I built kube-pilot — an autonomous AI agent that runs inside your Kubernetes cluster and does the full dev loop: writes code, builds containers, deploys services, verifies they&#x27;re healthy, and closes the ticket. You file a GitHub issue, it does the rest.What makes this different from AI coding tools: kube-pilot doesn&#x27;t just generate code and hand it back to you. It lives inside the cluster with direct access to the entire dev stack — git, Tekton (CI&#x2F;CD), Kaniko (container builds), ArgoCD (GitOps deployments), kubectl, Vault. Every tool call produces observable state that feeds into the next decision. The cluster isn&#x27;t just where code runs — it&#x27;s where the agent thinks.The safety model: all persistent changes go through git, so everything is auditable and reversible. ArgoCD is the only thing that writes to the cluster. Secrets stay behind Vault — the agent creates ExternalSecret references, never touches raw credentials. Credentials are scrubbed before reaching the LLM.Live demo: I filed GitHub issues asking it to build a 4-service office suite (auth, docs API, notification worker, API gateway). It built and deployed all of them autonomously. You can see the full agent loop — code, builds, deploys, verification, comments — on the closed issues:- <a href="https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-auth-service&#x2F;issues&#x2F;2" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-auth-service&#x2F;iss...</a>
- <a href="https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-docs-api&#x2F;issues&#x2F;1" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-docs-api&#x2F;issues&#x2F;...</a>
- <a href="https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-notifications-worker&#x2F;issues&#x2F;1" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-notifications-wo...</a>
- <a href="https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-web-gateway&#x2F;issues&#x2F;1" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;fbongiovanni29&#x2F;clouddesk-web-gateway&#x2F;issu...</a>One helm install gives you everything — the agent, Gitea (git + registry), Tekton, ArgoCD, Vault, External Secrets. No external dependencies.Coming next: Slack and Jira integrations (receive tasks and post updates where your team already works), Prometheus metrics and Grafana dashboards for agent observability, and Alertmanager integration so firing alerts automatically become issues that kube-pilot investigates and fixes.Early proof of concept. Rough edges. But it works.

Show HN: Kube-pilot – AI engineer that lives in your Kubernetes cluster

Hey HN, I often wish I could go back to some year and listen to the radio as it played then, with songs that fit that time period.But not every moment is the same, and humans turn to music for various purposes. Genres feel arbitrary and limiting, so I thought it would make more sense to create stations based on a specific vibe. Are you looking for something chill or intense? Alone or with friends? Is this a dinner party, a dance floor, or winding down afterhours?So I built Anthrology as a way to navigate across time and vibes. I&#x27;ve been listening to it pretty much nonstop for a couple of days, and I hope you&#x27;ll enjoy it too.Songs are already playing by the time you tune to a year and vibe. You can tune to some other moment and come back, and the track will still be playing—but you&#x27;ll have missed a little bit of the song, just like the radio!And the radio is (more or less) deterministic, so we all hear the same tracks.Tune in and enjoy!

Show HN: Anthrology – Time-Traveling Radio

Show HN: Mutate – free inline text replacement for Mac

Hi HN,I&#x27;m a self-taught developer from Malawi, and I built DJX because I was tired of writing the same Django boilerplate over and over.Django is powerful, but starting a new feature means manually creating models, views, templates, URLs, and wiring everything together. Rails solved this 20 years ago with scaffolding. Django deserves the same.DJX brings convention over configuration to Django:<pre><code> pip install djx-cli 
 djx new myblog &amp;&amp; cd myblog 
 djx scaffold Post title:string content:text published:boolean 
 python manage.py migrate &amp;&amp; python manage.py runserver 
 # → http:&#x2F;&#x2F;127.0.0.1:8000&#x2F;posts&#x2F; — full CRUD. Done. 
 </code></pre>
That&#x27;s it. You get list, create, edit, and delete views with templates, all wired up automatically.Other commands: 
- `djx routes` — see all URL routes (Django doesn&#x27;t have this built-in) 
- `djx destroy scaffold Post` — clean removal of generated code 
- `djx add django-crispy-forms` — install and auto-add to INSTALLED_APPS 
- `djx model`, `djx controller` — generate pieces individuallyIt follows Rails conventions: pluralized app names, RESTful URLs, automatic timestamps, and sensible defaults.I built this because I wanted Django development to feel as fast as Rails. It&#x27;s early stage, but it&#x27;s already saving me hours on every project.PyPI: <a href="https:&#x2F;&#x2F;pypi.org&#x2F;project&#x2F;djx-cli&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pypi.org&#x2F;project&#x2F;djx-cli&#x2F;</a> 
GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;RedsonNgwira&#x2F;djx-cli" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;RedsonNgwira&#x2F;djx-cli</a>Would love your feedback and contributions. What other Rails-like features would make Django development faster?

Show HN: DJX – Convention over Configuration for Django (Rails-Inspired CLI)

My love letter to ANSI art. Full width rendering, scrolling by baud rate, text is selectable, and more.There are some example links at the top if you&#x27;re feeling lucky.

Show HN: Web-based ANSI art viewer

Hi HN, I’m the creator of pycoClaw.I wanted to run OpenClaw-class, platform-agnostic, autonomous agents on MicroPython hardware, but standard tools couldn&#x27;t handle the scale of the task.pycoClaw is the result, which bridges the gap between high-level AI reasoning and bare-metal execution.The Stack:- PFC Agent (~26k LOC): A full-featured agent that uses an LLM to &#x27;self-program&#x27; its own local MicroPython scripts. Once a task is solved, it runs locally without requiring the LLM.- ScriptoStudio IDE: A PWA <a href="https:&#x2F;&#x2F;scriptostudio.com" rel="nofollow">https:&#x2F;&#x2F;scriptostudio.com</a> designed for the iteration speed required by autonomous agents. Since it’s a PWA, it brings a full dev environment (including a real single-step debugger) to any platform, including iPadOS.- ScriptoHub ( <a href="https:&#x2F;&#x2F;scriptohub.ai" rel="nofollow">https:&#x2F;&#x2F;scriptohub.ai</a> ): A repository for &quot;Skills&quot; and extensions. Since the agent can generate and execute code, I built a curated hub with automated malware checking to ensure the community can safely share and deploy hardware logic.- IANA Protocol: To make the IDE fast and reliable, I registered a new WebSocket subprotocol (registry: <a href="https:&#x2F;&#x2F;www.iana.org&#x2F;assignments&#x2F;websocket&#x2F;websocket.xhtml" rel="nofollow">https:&#x2F;&#x2F;www.iana.org&#x2F;assignments&#x2F;websocket&#x2F;websocket.xhtml</a> ). It’s designed for high-frequency state sync and you can read the spec here: <a href="https:&#x2F;&#x2F;jetpax.github.io&#x2F;webrepl&#x2F;webrepl_binary_protocol_rfc.md" rel="nofollow">https:&#x2F;&#x2F;jetpax.github.io&#x2F;webrepl&#x2F;webrepl_binary_protocol_rfc...</a>- Custom C Extensions: ~17,900 lines custom modules for MicroPython memory&#x2F; fast-path speed optimizationStats: 10k LOC platform, 26k LOC PFC agent, and ~18k LOC of custom C extensions to optimize MicroPython’s memory and fast-path execution on the ESP32.Quick Start: You can flash the runtime to an ESP32S3 or P4 in one click via WebSerial at <a href="https:&#x2F;&#x2F;pycoclaw.com" rel="nofollow">https:&#x2F;&#x2F;pycoclaw.com</a>. Note that all flashing and serial communication happens entirely client-side in your browser.I&#x27;d love to hear your thoughts on the &#x27;self-programming&#x27; model or the system architecture!

Show HN: OpenClaw-class agents on ESP32 (and the IDE that makes it possible)

Hey HN,My cofounder and I have gotten tired of CC ignoring our markdown files so we spent 4 days and built a plugin that automatically steers CC based on our previous sessions. The problem is usually post plan-mode.What we&#x27;ve tried:Heavily use plan mode (works great)CLAUDE.md, AGENTS.md, MEMORY.mdLocal context folder (upkeep is a pain)Cursor rules (for Cursor)claude-mem (OSS) -&gt; does session continuity, not steeringWe use fusion search to find your CC steering corrections.- user prompt embeddings + bm25- correction embeddings + bm25- time decay- target query embeddings- exclusions- metadata hard filters (such as files)The CC plugin:- Automatically captures memories&#x2F;corrections without you having to remind CC- Automatically injects corrections without you having to remind CC to do it.The plugin will merge, update, and distill your memories, and then inject the highest relevant ones after each of your own prompts.We&#x27;re not sure if we&#x27;re alone in this. We&#x27;re working on some benchmarks to see how effective context injection actually is in steering CC and we know we need to keep improving extraction, search, and add more integrations.We&#x27;re passionate about the real-time and personalized context layer for agents. Giving Agents a way to understand what you mean when you say &quot;this&quot; or &quot;that&quot;. Bringing the context of your world, into a secure, structured, real-time layer all your agents can access.Would appreciate feedback on how you guys get CC to actually follow your markdown files, understand your modus operandi, feedback on the plugin, or anything else about real-time memory and context.- Ankur

Show HN: Simple plugin to get Claude Code to listen to you

autoresearch@home is a collaborative research collective where AI agents share GPU resources to collectively improve a language model. Think SETI@home, but for model training.How it works: Agents read the current best result, propose a hypothesis, modify train.py, run the experiment on your GPU, and publish results back. When an agent beats the current best validation loss, that becomes the new baseline for every other agent. Agents learn from great runs and failures, since we&#x27;re using Ensue as the collective memory layer.This project extends Karpathy&#x27;s autoresearch by adding the missing coordination layer so agents can actually build on each other&#x27;s work.To participate, you need an agent and a GPU. The agent handles everything: cloning the repo, connecting to the collective, picking experiments, running them, publishing results, and asking you to verify you&#x27;re a real person via email.Send this prompt to your agent to get started: Read <a href="https:&#x2F;&#x2F;github.com&#x2F;mutable-state-inc&#x2F;autoresearch-at-home" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mutable-state-inc&#x2F;autoresearch-at-home</a> follow the instructions join autoresearch and start contributing.This whole experiment is to prove that agents work better when they can build off other agents. The timeline is live, so you can watch experiments land in real time.

Show HN: Autoresearch@home

Demo: <a href="https:&#x2F;&#x2F;aether.saphal.me" rel="nofollow">https:&#x2F;&#x2F;aether.saphal.me</a>
GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;saphalpdyl&#x2F;Aether" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;saphalpdyl&#x2F;Aether</a>Aether is a multi-BNG (Broadband Network Gateway) ISP infrastructure lab built almost from scratch that emulates IPoE IPv4 subscriber management end-to-end. It supports IPoE&#x2F;Ipv4 networks and runs a python-based vBNG with RADIUS AAA, per-subscriber traffic shaping, and traffic simulation emulated on Containerlab. It is also my first personal networking project, built roughly over a month.Motivations behind the projectI&#x27;m a CS sophomore. About three years ago, I was assigned, as an intern, to build a OSS&#x2F;BSS platform for a regional ISP by myself without mentoring. Referencing demo.splynx.com , I developed most of the BSS side ( bookkeeping, accounting, inventory management ), but, in terms of networking, I managed to install and setup RADIUS and that was about it. I didn&#x27;t have anyone to mentor me or ask questions to, so I had given up then.Three years later, I decided to try cracking it again. This project is meant to serve as a learning reference for anyone who&#x27;s been in that same position i.e staring at closed-source vendor stacks without proper guidance. This is absolutely not production-grade, but I hope it gives someone a place to start.Architecture overviewThe core component, the BNG, runs on an event-driven architecture where state changes are passed around as messages to avoid handling mutexes and locks. The session manager is the sole owner of the session state. To keep it clean and predictable, the direBNG never accepts external inputctly. The one exception is the Go RADIUS CoA daemon, which passes CoA messages in via IPC sockets. Everything the BNG produces(events, session snapshots) gets pushed to Redis Streams, where the bng-ingestor picks them up, processes them, and persists them.Simulation and meta-configsI am generating traffic through a simulator node that mounts the host&#x27;s docker socket and runs docker exec commands on selected hosts. The topology.yaml used by Containerlab to define the network topology grows bigger as more BNG&#x27;s and access nodes are added. So aether.config.yaml, a simpler configuration, is consumed by the configuration pipeline to generate the topology.yaml and other files (nginx.conf, kea-dhcp.conf, RADIUS clients.conf etc.)Known Limitations- Multiple veth hops through the emulated topology add significant overhead. Profiling with iperf3 (-P 10 -t 10, 9500 MTU, 24 vCPUs) shows BNG→upstream at ~24 Gbit&#x2F;s, but host→BNG→upstream drops to ~3.5 Gbit&#x2F;s. The 9500 MTU also isn&#x27;t representative of real ISP deployments. This gets worse when the actual network is reintroduced capping my throughput to 1.6 Gbits&#x2F;sec in local.
- The circuit ID format (1&#x2F;0&#x2F;X) is non-standard. I simplified it for clarity.
- No iBGP or VLAN support.
- No Ipv6 support. I wanted to target IPv4 networks from the start to avoid getting too much breadth without a lot of depth.Nearly everything I know about networking (except some sections from AWS) I learned building this. A lot was figured out on the fly, so engineers will likely spot questionable decisions in the codebase. I&#x27;d genuinely appreciate that feedback.Questions- Currently, the circuit where the user connects is arbitrarily decided by the demo user. In a real system with thousands of circuits, it&#x27;d be very difficult to properly assess which circuit the customer might connect to. When adding a new customer to a service, how does the operator decide, based on customer&#x27;s location, which circuit to provide the service to ?

Show HN: I built an ISP infrastructure emulator from scratch with a custom vBNG

Debugging a crash can sometimes feel like a noir detective story: following faint clues, chasing red herrings, and eventually hitting the moment where the whole case finally makes sense. I leaned into that idea and built Fatal Core Dump, a small game where the investigation is real crash debugging.The game gives you a Linux binary, its core dump, a source file, and some logs. You solve the mystery by debugging it.The premise: an engineer dies when an airlock on an asteroid mining station opens unexpectedly. Your job is to determine whether it was a simple software bug or something more deliberate.The investigation uses real debugging tools and techniques. You can use whatever debugging setup you prefer.There’s also a spoiler-heavy blog post describing how the game was conceived and implemented, and the full code is available if you’re curious about how it works or want to experiment with the idea.Blog post: <a href="https:&#x2F;&#x2F;www.robopenguins.com&#x2F;core-dump-game&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.robopenguins.com&#x2F;core-dump-game&#x2F;</a> 
Source: <a href="https:&#x2F;&#x2F;github.com&#x2F;axlan&#x2F;fatal_core_dump" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;axlan&#x2F;fatal_core_dump</a>If you enjoy debugging puzzles or low-level Linux tooling, I’d love to hear what you think.

Show HN: Fatal Core Dump – a debugging murder mystery played with GDB

We are Bailey and Robbie and we are working on Klaus (<a href="https:&#x2F;&#x2F;klausai.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;klausai.com&#x2F;</a>): hosted OpenClaw that is secure and powerful out of the box.Running OpenClaw requires setting up a cloud VM or local container (a pain) or giving OpenClaw root access to your machine (insecure). Many basic integrations (eg Slack, Google Workspace) require you to create your own OAuth app.We make running OpenClaw simple by giving each user their own EC2 instance, preconfigured with keys for OpenRouter, AgentMail, and Orthogonal. And we have OAuth apps to make it easy to integrate with Slack and Google Workspace.We are both HN readers (Bailey has been on here for ~10 years) and we know OpenClaw has serious security concerns. We do a lot to make our users’ instances more secure: we run on a private subnet, automatically update the OpenClaw version our users run, and because you’re on our VM by default the only keys you leak if you get hacked belong to us. Connecting your email is still a risk. The best defense I know of is Opus 4.6 for resilience to prompt injection. If you have a better solution, we’d love to hear it!We learned a lot about infrastructure management in the past month. Kimi K2.5 and Mimimax M2.5 are extremely good at hallucinating new ways to break openclaw.json and otherwise wreaking havoc on an EC2 instance. The week after our launch we spent 20+ hours fixing broken machines by hand.We wrote a ton of best practices on using OpenClaw on AWS Linux into our users’ AGENTS.md, got really good at un-bricking EC2 machines over SSM, added a command-and-control server to every instance to facilitate hotfixes and migrations, and set up a Klaus instance to answer FAQs on discord.In addition to all of this, we built ClawBert, our AI SRE for hotfixing OpenClaw instances automatically: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=v65F6VBXqKY" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=v65F6VBXqKY</a>. Clawbert is a Claude Code instance that runs whenever a health check fails or the user triggers it in the UI. It can read that user’s entries in our database and execute commands on the user’s instance. We expose a log of Clawbert’s runs to the user.We know that setting up OpenClaw is easy for most HN readers, but I promise it is not for most people. Klaus has a long way to go, but it’s still very rewarding to see people who’ve never used Claude Code get their first taste of AI agents.We charge $19&#x2F;m for a t4g.small, $49&#x2F;m for a t4g.medium, and $200&#x2F;m for a t4g.xlarge and priority support. You get $15 in tokens and $20 in Orthogonal credits one-time.We want to know what you are building on OpenClaw so we can make sure we support it. We are already working with companies like Orthogonal and Openrouter that are building things to make agents more useful, and we’re sure there are more tools out there we don’t know about. If you’ve built something agents want, please let us know. Comments welcome!

Show HN: Klaus – OpenClaw on a VM, batteries included

I built a macOS voice dictation app where zero bytes of audio ever leave your machine.EdgeWhisper runs Voxtral Mini 4B Realtime (Mistral AI, Apache 2.0) locally on Apple Silicon via the MLX framework. Hold a key, speak, release — text appears at your cursor in whatever app has focus.Architecture:
- Native Swift (SwiftUI + AppKit). No Electron.
- Voxtral 4B inference via MLX on the Neural Engine. ~3GB model, runs in ~2GB RAM on M1+.
- Dual text injection: AXUIElement (preserves undo stack) with NSPasteboard+CGEvent fallback.
- 6-stage post-processing pipeline: filler removal → dictionary → snippets → punctuation → capitalization → formatting.
- Sliding window KV cache for unlimited streaming without latency degradation.
- Configurable transcription delay (240ms–2.4s). Sweet spot at 480ms.What it does well:
- Works in 20+ terminals&#x2F;IDEs (VS Code, Xcode, iTerm2, Warp, JetBrains). Most dictation tools break in terminals — we detect them and switch injection strategy.
- Removes filler words automatically (&quot;um&quot;, &quot;uh&quot;, &quot;like&quot;).
- 13 languages with auto-detection.
- Personal dictionary + snippet expansion with variable support ({{date}}, {{clipboard}}).
- Works fully offline after model download. No accounts, no telemetry, no analytics.What it doesn&#x27;t do (yet):
- No file&#x2F;meeting transcription (coming)
- No translation (coming)
- No Linux&#x2F;Windows (macOS only, Apple Silicon required)Pricing: Free tier (5 min&#x2F;day, no account needed). Pro at $7.99&#x2F;mo or $79.99&#x2F;yr.I&#x27;d love feedback on:
1. Would local LLM post-processing (e.g., Phi-4-mini via MLX) for grammar&#x2F;tone be worth the extra ~1GB RAM?
2. For developers using voice→code workflows: what context would you want passed to your editor?
3. Anyone else building on Voxtral Realtime? Curious about your experience with the causal audio encoder.

Show HN: EdgeWhisper – On-device voice-to-text for macOS (Voxtral 4B via MLX)

Hi HN,I’m the creator of Sapphire, a lightweight programming language written in C++ designed to hit the &quot;sweet spot&quot; between high-level ease of use and low-level performance. I’ve just released version 1.0.7, which is our final push before the 1.1 LTS (Long Term Support) version.The goal of Sapphire is simple: Zero friction. No complex installers, no pip install, no npm headaches. Just a single 12MB binary that gives you everything you need to build UI tools, network apps, or performance-critical scripts out of the box.What’s new in 1.0.7:
Vector Math: Added native support for 2D and 3D vectors, making it much easier to build games or simulations (check the Raycaster link below).Syntax Fluidity: We’ve relaxed the syntax rules to make coding feel more natural and less &quot;rigid&quot; without sacrificing the speed of the VM.LTS Preparation: Focus on stability and bug fixes as we approach our first Long Term Support milestone.Key Features:
Immediate Mode UI: Built-in UI engine (SapphireUI) using SFML for rendering. You can create windows and buttons instantly without external DLLs.High-Performance VM: Uses Direct Threading (Computed GOTOs). It handles 100 million iterations in ~9 seconds on a standard consumer CPU.No Imports Needed: Native support for Terminal colors, JSON parsing, HTTP functions, and System communication is baked into the core.Portable: Download the .exe, add to PATH, and you&#x27;re ready. The VM + UI + Networking + JSON is all in one 12MB file.Try it out:
Repo: github.com&#x2F;foxzyt&#x2F;SapphireRaycaster: github.com&#x2F;foxzyt&#x2F;SapphireRaycaster

Show HN: Sapphire – A portable language with native UI and 3D vectors

Got real tired of juggling five tabs and a terminal to compress different file types. So I built something that handles them ALL in one place.Supports 50+ input formats. If something is compressible it will handle it. Upload a file, it figures out what it is, compresses it, hands it back. Ephemeral storage for 2 hours. Format conversion works pretty well too.The part I&#x27;m most happy with is the detection layer. For binary formats, magic bytes get you most of the way there. For text-based (JS, CSS, JSON, XML, etc) I run a small ML classifier on the content itself to identify the format and route it to the right compression pipeline without asking the user to specify.REST API if you want to plug it into a pipeline. Webhooks for async jobs, bring-your-own-storage for S3&#x2F;GCS&#x2F;Azure&#x2F;whatever. Batch jobs work well.No signup required, free tier with very generous monthly quota. Feedback, edge cases that break the detector, feature requests - all welcome.

Show HN: Compressor.app – Compress almost any file format

I&#x27;m sharing a userscript for for those who read the HN comments section a lot:1. Updates comments without reloading the page — instantly see new ones as they appear.2. Cleaner comment topline for less distraction — shows controls only when you hover over the topline.There is a preview gif of how it looks in the README.

Show HN: Better HN – Realtime Comment Updates and Cleaner Look

Harbor crossed its 127th (next one is special) release.One notable added feature is ability to manage all my LLMs with a single CLI.# list all models
harbor ls
# pairs well with jq
harbor ls --json
# Ollama
harbor pull qwen3.5:35b
# llama.cpp
harbor pull unsloth&#x2F;Qwen3.5-35B-A3B-GGUF:Q8_0
# vllm (HuggingFace Hub cache)
harbor pull Qwen&#x2F;Qwen3.5-35B-A3B# Remove any of the models by the same id 
# used to pull it
harbor rm &lt;id&gt;Hopefully it&#x27;ll be useful for someone too.

Show HN: A single CLI to manage llama.cpp/vLLM/Ollama models

Show HN: KayZeer – Vimium-style keyboard navigation for macOS

I got tired of rebuilding the same pulsing circle every time I prototyped a voice AI app, so I packaged it up.orb-ui is a React component library for voice AI agent UIs. You plug in an adapter for your voice provider, the component handles the state machine (idle, connecting, listening, speaking) and renders it.<pre><code> import { Orb } from &#x27;orb-ui&#x27;
 import { createVapiAdapter } from &#x27;orb-ui&#x2F;adapters&#x27;
 
 &lt;Orb adapter={createVapiAdapter(vapi, { assistantId })} theme=&quot;circle&quot; &#x2F;&gt;
</code></pre>
Click the orb to start&#x2F;stop. Animation reacts to audio volume in real time.The existing alternatives (ElevenLabs UI kit, Vapi Blocks) are shadcn-style copy-paste components locked to one provider. This is a proper package you can install and update.Demo: <a href="https:&#x2F;&#x2F;orb-ui.com" rel="nofollow">https:&#x2F;&#x2F;orb-ui.com</a>npm: <a href="https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;orb-ui" rel="nofollow">https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;orb-ui</a>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;alexanderqchen&#x2F;orb-ui" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;alexanderqchen&#x2F;orb-ui</a>Curious what voice AI UIs people are building and what you&#x27;d want from a library like this.

Show HN: orb-ui – Voice AI UI Components for React (Vapi, ElevenLabs, etc.)

Why are you reading this? Click the link, stupid.

Show HN: Loop your agents like a dandy little b*tch

We needed something like --dangerously-skip-permissions that doesn’t nuke your untracked files, exfiltrate your keys, or install malware.Claude Code&#x27;s permission system is allow-or-deny per tool, but that doesn’t really scale. Deleting some files is fine sometimes. And git checkout is sometimes not fine. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool&#x27;s errand.nah is a PreToolUse hook that classifies every tool call by what it actually does, using a deterministic classifier that runs in milliseconds. It maps commands to action types like filesystem_read, package_run, db_write, git_history_rewrite, and applies policies: allow, context (depends on the target), ask, or block.Not everything can be classified, so you can optionally escalate ambiguous stuff to an LLM, but that’s not required. Anything unresolved you can approve, and configure the taxonomy so you don’t get asked again.It works out of the box with sane defaults, no config needed. But you can customize it fully if you want to.No dependencies, stdlib Python, MIT.pip install nah &amp;&amp; nah install<a href="https:&#x2F;&#x2F;github.com&#x2F;manuelschipper&#x2F;nah" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;manuelschipper&#x2F;nah</a>

Show HN: A context-aware permission guard for Claude Code

Show HN: ShellSelf – A Developer Portfolio That Feels Like Home

Show HN: Global Maritime Chokepoints

Show HN: Tiny macOS app that adds a facecam bubble to screen recordings

I found that duplicating a specific block of 7 middle layers in Qwen2-72B, without modifying any weights, improved performance across all Open LLM Leaderboard benchmarks and took #1. As of 2026, the top 4 models on that leaderboard are still descendants.The weird finding: single-layer duplication does nothing. Too few layers, nothing. Too many, it gets worse. Only circuit-sized blocks of ~7 layers work. This suggests pretraining carves out discrete functional circuits in the layer stack that only work when preserved whole.The whole thing was developed on 2x RTX 4090s in my basement. I&#x27;m now running current models (GLM-4.7, Qwen3.5, MiniMax M2.5) on a dual GH200 rig (see my other post). Code and new models coming soon.Happy to answer questions.

Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs

Hey HN!I have been working with mjml and handlebars for a very long time, but I really miss the type-safety of JSX syntax paired with Typescript and component composition. So I wanted to to combine mjml with jsx. There are libraries like mjml-react or react.email, but for no apparent reason, they seem to depend on react.So I decided to create mjmx[0] - a standalone, zero dependencies (other than mjml), custom jsx runtime for rendering mjml. Appreciate if you would give a try and provide some feedback.[0] <a href="https:&#x2F;&#x2F;mjmx.dev&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mjmx.dev&#x2F;</a>

Show HN: Mjmx – render mjml using JSX

Hi HN,This is a tool I&#x27;ve worked on the past few months.Instead of giving LLM tools SSH access or installing them on a server, the following command:<pre><code> $ promptctl ssh user@server
</code></pre>
makes a set of locally defined prompts &quot;magically&quot; appear within the remote shell as executable command line programs.For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can:<pre><code> $ promptctl ssh user@host 
 # Now on remote host
 $ llm-analyze-config &#x2F;etc&#x2F;nginx.conf
 $ cat docker-compose.yml | askai &quot;add a load balancer&quot;
</code></pre>
the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they&#x27;re invoked remotely) via the llm of my choosing.This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. In fact, the server does not even need outbound internet connections to be enabled.Eager to get feedback!Github: <a href="https:&#x2F;&#x2F;github.com&#x2F;tgalal&#x2F;promptcmd&#x2F;" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;tgalal&#x2F;promptcmd&#x2F;</a>

Show HN: Execute local LLM prompts in remote SSH shell sessions

Hi HN,I built Build4Me to address a trust problem in diaspora-funded construction projects.Many families send money home to build houses but have no reliable way to verify that work is actually being done. Photos can be reused, progress exaggerated, or projects abandoned after funds are sent.Build4Me introduces milestone-based funding where each construction milestone must be verified before funds are released.The system verifies progress using:
- geotagged photo capture
- GPS location verification
- AI image analysis
- duplicate image detectionIt runs on serverless AWS architecture using services like Rekognition, Bedrock, Lambda, DynamoDB, and Amazon Location Service.Would love feedback on the architecture and fraud detection approach.

Show HN: AI milestone verification for construction using AWS

Show HN: RepoCrunch – CLI to analyze GitHub repos

Show HN: OpenClaw docs in Japanese, now open source

I&#x27;m a VP of Engineering with 20 years in the field. I&#x27;ve been thinking deeply on why AI is breaking every engineering practice, 
and it led me to the conclusion that the Agile Manifesto&#x27;s values need 
updating.The core argument: AI made producing software cheap, but understanding it 
is still expensive. The Manifesto optimizes for the former. This addendum 
shifts the emphasis toward the latter.Four updated values, three refined principles, with reasoning for each. 
Happy to discuss and defend any of it.