Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
Hi HN. My name is Andrey. On a regular business day, I'm a software engineer working at AWS. Outside of work hours, I spend time on my hobby - writing code.I was once building a pet project that allowed customers to spin up fully synchronized blockchain nodes within just a few minutes. The backend was split into a control plane and a data plane, each with its own AWS account. Later I added two more AWS accounts. One for shared RPC nodes. One for the Analytics Service.Since I love to visualize things, I used drawio to visualize the architecture.With time, I noticed a pattern. I'd write some code, add a few lambda functions, update my drawio diagram, write more code, introduce a few more resources, test things, see that everything works fine and go to sleep with a smile on my face. Next week I'd check my diagram, and shockingly, it's missing some of the resources! This kept happening for a few more weeks until I decided to fully abandon the project until my infrastructure diagrams could stay in sync with my cloud account.That's how Atlasphere.io was born. I've been working on it for the past 6 months and I think the product is ready for some feedback :)A few notes:- Atlasphere uses a ReadOnly IAM role to scan your AWS account (my account reaches your account through a trust relationship).- The number of services is currently limited (WIP)- It's a macOS app- It's NOT an Electron app, i use Rust + WebviewWhat am I looking for? All I really need is for someone to try the app and tell me what they like about it and what they absolutely hate about it, haha!The website is https://atlasphere.io/
Hacker News3mo agoToolAI
At Deno we've been using OpenClaw and other agents increasingly for addressing production problems in Deno Deploy - when a PagerDuty alert fires, the agent starts researching the cause and making fixes.In order to do this, the agent needs access to real production systems - postgres, kubernetes, gcp, clickhouse, github, etc. But this is dangerous to say the least - we want destructive actions to be reviewed by other LLMs, approved by humans, and logged appropriately.Claw Patrol terminates TCP connections over WireGuard or Tailscale, then parses application protocols (eg http, postgres, ssh) to apply rules that allow you to deny/allow requests.There are a few projects that sit as a proxy in front of agents to do secret injection or apply various guardrails, but none met our needs (LLM gateways, MCP proxies, sandboxes), particularly the need to handle low-level protocols, or handle complex real world situations like tunneling postgres through k8s.Written in Go, configured in HCL, MIT licensed. Happy to answer any questions.https://clawpatrol.dev/
Hacker News3mo agoToolAI
Using AI for startup tasks fails when the core problem isn't fully understood first, resulting in wasted effort and irrelevant suggestions.
X6mo agoPromptAI
Hey HN, it’s been just over a year since we launched HelixDB (https://news.ycombinator.com/item?id=43975423), a project a friend and I started in college. It’s an OLTP graph database built on object-storage, with native vector search and full-text search (FTS).Why graph, vector and FTS? Graph databases provide a natural cognitive model for data, vectors allow for a semantic understanding of the entities and relationships in the graph, and FTS provides more specific filtering. Many AI-driven applications attempt to combine all of these functionalities by stitching together multiple disconnected systems, but even then there’s no native way to perform joins or queries that span all systems. You still need to handle this logic at the application level.Helix started as a graph DB, but we moved to a hybrid graph/vector approach after attempting to build an AI memory system, which led us down the GraphRAG and HybridRAG rabbit hole, where we would need separate graph and vector databases.We knew scalability would be a challenge at each stage of our product's development, however our initial focus this past year was to prove out the product through local deployments and was only meant to be run on a single node. Scaling graph DBs remained a difficult and expensive problem we’d have to solve later. Some common ways other graph DBs solve scaling is by duplicating entire datasets across distributed machines (extremely expensive per node), or by sharding the data.Sharding databases is effective and affordable, however, graph data doesn’t have explicit partitions like relational databases do. For example, sharding a relational DB involves splitting up tables. When it comes to graph DBs, the edges can span across any of the partitions, and hopping across multiple machines when traversing nodes is ineffective and computationally expensive.Replicating graph DBs for high availability and better throughput drastically increases the operational cost of the db a
Hacker News3mo agoToolAI
Hi HN, I've been building Nucleus, a lightweight Linux container runtime focused on two workloads: ephemeral AI-agent sandboxes and declarative NixOS services. It's a single Rust binary, no daemon.It is not a Docker replacement and not a strict subset of Docker either. I dropped the entire image-and-distribution half (no Dockerfile, no layers, no registry, no pull/push, no persistent storage layer) in exchange for going deeper on isolation and reproducibility. The rootfs is either a directory copied into tmpfs (agent mode) or a Nix-built closure mounted read-only (production mode). If your mental model is "run my image instead of docker run," this won't fit. If it's "run untrusted or ephemeral workloads with stronger, auditable isolation on a single host," that's the target.Things that I think are interesting: - Defense-in-depth defaults. All capabilities dropped, ~100-syscall seccomp allowlist (vs Docker's ~300), up to 8 namespaces including time/cgroup, Landlock LSM path ACLs per service. - Deny-by-default egress. Outbound traffic is denied unless you allow specific CIDRs or DNS-resolved domains. Enforced with namespace-local iptables rules. - Externalized, hash-pinned security policies. seccomp (JSON), capabilities (TOML), and Landlock (TOML) live as separate SHA-256-verified files, decoupled from the rootfs build. There's a nucleus seccomp generate that records syscalls in trace mode and emits a minimal profile. - gVisor as a first-class integrated runtime, not an add-on. Explicit network modes including a gvisor-host mode that's intentionally separate from native host networking. - Nix-native production path. nucleus.lib.mkRootfs builds locked-down closures; rootfs attestation verifies a per-file SHA-256 manifest at startup; first-class NixOS module. - Formal verification. TLA+ specs for the isolation/resource/filesystem/security/gVisor subsystems, checked with
Hacker News3mo agoToolAI
What works now: user signups, org creations, private/public repos, and importing GitHub repositories (both as read-only mirrors and full migrations). So basically, you can create, push and pull to a repo, but we don't have many features quite yet (issues, PRs, CI).What is a bit unique is: 1) we built it in Rust and 2) the website is a little odd. Its design is inspired by CLIs (e.g., fzf, broot, vim) instead of web apps, and as such, lacks some affordances that you might typically expect in favor of keyboard-driven instant navigations (we have the very ambitious goal of an FCP of 100ms). In case you're curious, here's how we we built it: https://gitdot.io/designsWe recognize that we're making some bold claims here and are also well aware that we have much to learn. Building software is still hard, and that's a fact we seem to relearn everyday.But we wanted to share what we built so far nonetheless.Cheers, thank y'all for reading, and till the next —paul & mikkel.
Hacker News3mo agoToolAI
Hello HN, I am the founder of Agora Cosmica.This started about three years ago. On a walk I asked a chatbot to interpret the cave dream from Cormac McCarthy's book "The Road" as C.G. Jung. It gave me a perspective I had not thought of. But for my own dreams the policies of the big providers felt wrong for so personal conversations, as zero data retention is not available. So I started building.The project evolved to a German nonprofit and we published the code (AGPL-3.0) last month. The content is still copyright, but will be opened to CC-BY 4.0 in the next 6 to 12 months.Agora Cosmica is a library to learn from 30 historical figures. Each one has 12 narrated stories about their teachings / life wisdom, speech to speech conversation. Four learning modes and a council where you can gather the figures to discuss or reflect on a topic. Each figure is an AI Echo, an interpretation grounded in primary works, historical context, with a factcheck per figure to show what's verified versus recreated. On privacy: The speech is self hosted on Hetzner GPU servers, Qwen3-TTS for German, Kokoro TTS for English, Faster-Whisper for transcription. 30 free messages per day (EU-hosted for GDPR), BYOK, or you can run it in a full local self-hosted mode.No conversation is stored, no tracking cookies, no profiling, no signup.The app is slow on purpose. Cosmic, no dopamine rush.The mission is to be a doorway, a first step, an introduction to get people interested and outgrow the app to move to primary texts and human teachers.Live at: https://agoracosmica.org
Hacker News3mo agoToolAI
We're open-sourcing 14 components & examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It's MIT licensed and fully customizable.Demo video here: https://share.extend.ai/kRmSGKRFWhen we started, we tried every file viewer and document component library we could find. Unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for https://extend.ai/. It was only ever meant to be internal, but enough customers kept asking for it that we decided to open source it.It's useful for building document processing agents, real-time user facing document intake flows, or all kinds of internal tooling.We naively thought this would be a solved problem. Turns out, making PDF/XLSX/DOCX viewers that work at scale is not trivial...we use and maintain it for Extend ourselves, so we've fixed a lot of edge cases that came up while running millions of pages / day through our own system. Our hope is that with our resources + community support, it'll keep getting better over time.
Hacker News3mo agoToolAI
Hi HN — we’re Julius, Jago, and Nils, and we’re building transload (transload.io).transload helps LTL trucking companies measure freight dimensions using the security cameras already installed in their terminals. Instead of sending shipments through a dedicated dimensioning station, we measure them automatically as they move through the normal dock workflow.We’ve put together a small HN-specific demo site here: https://hn.transload.io/In LTL trucking, dimensions matter because they affect pricing, freight classification, and trailer utilization. If a shipment is larger than the shipper reported, the carrier may undercharge for it while still giving up the same amount of trailer space. The obvious fix is to measure every shipment, but that is surprisingly hard in a busy freight terminal. Dedicated dimensioning systems work for freight that passes through them, but they can add forklift travel, create dock congestion, and change the normal flow of work. In practice, many terminals only measure a sample of their shipments.Jago grew up close to this industry through his family’s LTL trucking and cross-docking business. We did not start out building freight dimensioning. Our first idea was an AI system for optimizing forklift routes inside cross-dock terminals. After spending time with customers and talking to more than 50 trucking companies, we realized that forklift routing was not the pain people kept bringing up. Freight dimensions were.At the same time, we saw that spatial AI was advancing quickly. Monocular metric depth estimation has become dramatically better, making it possible to recover accurate 3D structure from ordinary camera footage without expensive LiDAR sensors. MapAnything (https://github.com/facebookresearch/map-anything) and MoGe (https://github.com/microsoft/moge) are two examples.Freight terminals also have helpful structure: fixed cameras, repeated workflows, barcode scan timestamps, and known
Hacker News3mo agoToolAI
I submit an extension (an adblocker) to Google Chrome's web store.Google keeps rejecting it for dubious reasons. The first rejection was claim it was "spam". When I appealed, the review came back that it contained "additional functionality" because it uses "modifies network traffic". Well of course it does! When I asked the reviewer how I could achieve the stated functionality of blocking ads without the use of "declarativeNetRequest" I simply received the same canned response.I submit a totally new update that simplified the code and included comments, and references to other open source projecs that use the exact same mechanisms. Again it was rejected. On this appeal I asked if it could be escalated to a senior reviewer who could possibly reply with more context. Same canned response and rejection.I can't help but think Google has some internal policy to give adblockers a runaround. It is obvious to me the stated rejections are not valid (Note that I'm also not new to this - I have several extensions that have been published for years with thousands of users) but have never encountered such gate-keeping before.It's a sad state of affairs even if not totally unpredictable. To be honest I'm surprised Google hasn't made it an official policy to prohibit adblockers. But they haven't - obviously there are other adblockers published to the store, and that's what makes this so frustrating.Anyway, fellow developers. Anyone run into a similar situation? And how did you resolve it? Thanks!
Hacker News3mo agoToolAI
Users lack a tool to record Claude AI sessions to prove they were completed in one shot and enable others to learn from the interactions.
X3mo agoToolAI
Local LLMs like Qwen or Gemma have poor user interfaces and harness issues, making them unproductive and hard to use effectively for mainstream users.
X3mo agoToolAI
Hi HN! We’re Jimmy and Ray. Jimmy is a Thiel Fellow with a Ph. D. from MIT who has worked on programming tools for 15 years; Ray became VP of Sales at a $2B company when he was 19 and has built side-businesses vibe-coding.Last year, we set to answer the question “If AI can write code 100x faster, then why aren’t you shipping 100x faster?” What we learned shocked us — even fairly nontechnical people and solo founders told us they were spending more than half of their development time reading the AI-written code. And much of the rest of the time was spent either de-slop-ping it, or wishing they had done so.As luck turns out, our last two products were a tool that quickly onboards people to large codebases ( https://x.com/0xjimmyk/status/1873357324229984677 ) and trainings that taught deep concepts of code quality to CEOs, YC founders, and engineers at top companies ( mirdin.com ), so we were extremely well-positioned to solve these problems.Command Center is an agentic coding environment focused on quality. With a few keypresses, you can start building 3 features at once and soon have 3 diffs ready, each consisting of 2000 changed lines across 50 files….This is normally the point where you think “Crap, what now?”With Command Center, at this point you simply click “Refactor,” and watch the vibed slop turn into readable robustness. Then you click “Generate Walkthrough,” and then suddenly, to read a 2000 line diff, instead of scrolling up and down trying to make sense of it, you just press the right arrow key 200 times. See something you don’t like? Click on line 37, type “Do this and all other network fetches in the background Cmd+Enter,” and you have a few more agents getting your code into final shape. Click or type “Commit,” “Push,” “Create PR” — you just shipped a high quality, non-slop featureWe’re striving to be the best at every step of the pipeline, but can just try Command Center in pieces wherever you feel your current workflow is wea
Hacker News3mo agoToolAI
Hey HN, we're Faisal and Ahmad from Intuned (https://intunedhq.com). We’re building a platform for building, deploying, and maintaining browser automations.Customers primarily use the Intuned AI agent to automate websites that don't expose APIs. Common use-cases include scraping data, pulling reports, and submitting forms. As the website changes, our agent also helps automatically heal the automation.On Intuned, browser automations are created by an AI agent and run as code. Our infra captures the context of every run, allowing our agent to debug and maintain the underlying code - to keep the automations working over time. This way, we’re able to offer the predictability, speed, and cost of code, without the painful parts of writing and maintaining it.Here’s a demo of building a scraper on Intuned: https://youtu.be/ruZP73bK4FUHere’s a demo of using AI to maintain a project: https://youtu.be/e4R4hLdHBroBackstory: we were accepted into YC for a completely different idea. During the batch, because of Faisal's background at UiPath, several batchmates asked us whether RPA tools could fill API gaps in their products by automating websites without APIs. When it was time to pivot, we went back to those founders to dig deeper. (RPA in this context is referring to using UI automation to do complete non-testing tasks)We discovered that the actual hard problem in browser automation is maintenance. Websites change, selectors break, and failures can be painful to reproduce and fix. So in early 2024, we decided to take a crack at this problem with a handful of customers. It needed a fair number of iterations before we landed on our current code-first approach.How it works: Intuned is infra + agent, deeply integrated.On the infrastructure side, Intuned is a managed runtime for browser automation code. Projects are usually Playwright-based TypeScript or Python. Users can write them directly in our online IDE, or hand the work of
Hacker News3mo agoToolAI
Users with ADHD need AI to automatically mark unread messages or chats until action is taken, as standard summarization features fail to prompt follow-through.
X3mo agoToolAI
Builders using AI coding agents struggle with benchmarking skills, lack of telemetry/hooks, prompt versioning, recommendations based on coding patterns, and managing natural language agent infrastructure like plugins and context, leading to anecdotal management and need for custom wikis.
X3mo agoToolAI
Hey HN!Lathe is an experiment in using LLMs to teach me something new, instead of doing the work for me. It generates a hands-on, source-backed tutorial for any technical topic you want to learn. Then you work through it yourself by reading and typing the code by hand (gasp) in a local UI built for exactly that.It's a Go CLI plus LLM agent skills (Claude Code / Cursor / Codex). You prompt something like "/lathe build a 3D slicer in Erlang", run `lathe serve` to spin up a local webapp, and read it in your browser. Every tutorial comes with the things that have made self-learning a pleasant experience for me in the past:- table of contents that follows along as you scroll - side-notes that nudge you to think - exercises for the reader - sources backing up the content that you can use to take you deeperTo help make up for the lack of human brainpower behind the tutorial, you can also ask questions about the content, have another LLM verify the tutorial actually compiles and runs, or extend it with another part (no more "Part 4 of 6" that hasn't seen an update since 2021).I didn't build lathe to replace human-written tutorials. I built lathe because I _love_ human-written tutorials, but wanted to learn technical domains where no good human-written tutorial exists yet (building a 3D slicer from scratch, making embedded Zig approachable, etc). There's a longer story in the README about how I got started with programming through PSP homebrew tutorials, and why losing that to LLMs bugged me enough to build this.I'm not here to sell you anything (there's nothing close to a VC-backed startup here :D). It's an LLM, and its output is usually good but not perfect by any means. So far, my experience is that because you're the one typing and actually engaged, you catch the weird stuff (and I'm finding that pushing back on it is its own kind of learning). And yes, it's vibecoded, because it's
Hacker News3mo agoToolAI
NoSuggest is a quiet act of resistance against YouTube algorithms always trying to pull you into a loop of unlimited videos in turn into unlimited screen time. With unending side cards of videos, auto-play, what's next suggestions, YouTube shorts and notifications, users will be doom scrolling for many hours in a day.I faced the same problem. Acknowledging that, not all content in YouTube is bad. There are educational videos, genuine news contents without political bias which is very hard to find outside YouTube and many other good relaxing, entertainment stuff.NoSuggest lets you only follow the YouTube channels you like and removes all types of recommendation YouTube has. So you don't waste time on watching things which you never wanted to watch anyways.UI is very simple. You add your favourite channels in "Channels" tab and latest 5 videos per channel excluding shorts would appear in "Feed" tab. "Search" tab is to search for specific videos to watch and "Saved" tab is to bookmark any video you want to watch later. Intention of NoSuggest is to provide whatever is necessary to extract whats good from YouTube all inside NoSuggest and leave out bad parts.NoSuggest works in any devices. Install it as an app (PWA) in android and iPhone, or simply open in browser in laptops. No sign-in, no account creation or no card details. NoSuggest won't even ask your name. Total privacy for the users.Parents can add the channels and save some educational videos and lock it with the pin for kids mode. Kids won't be able access unwanted additive contents inside NoSuggest.Completely free, no string attached. Source available in Github through NoSuggest website.I would love genuine feedback. Thank you very much for your attention on this matter.
Hacker News3mo agoToolAI
Hi HN, not sure if anyone would be interested, but just wanted to share that I've been maintaining my small tool called 'lowfat' that helps me filters some of my verbose CLI output. It's a single binary, works as an agent hook or a shell wrapper. It has a plugin system to customize filters per command.The idea is pretty simple: agents don't need the full kubectl get -o yaml or any 10k-line dump to make decisions. So that lowfat sits in between, strips the noise, and passes through what matters. Here's my real report after 2 months of personal use: lowfat history --all lowfat plugin candidates ───────────────────────────────────────────────────────── # command runs avg raw cost savings source status 1 kubectl get 101x 14.4K 1.5M 93.9% plugin good 2 grep 103x 13.5K 1.4M 96.2% plugin good 3 git diff 81x 995 80.6K 57.9% built-in good 4 kubectl 90x 485 43.6K 33.6% plugin good 5 docker 127x 5.5K 693.6K 96.1% built-in good 6 ls 489x 117 57.3K 56.2% built-in good 7 find 30x 16.5K 495.0K 95.5% plugin good 8 git show 63x 490 30.9K 38.0% built-in good 9 git 177x 368 65.2K 76.1% built-in good 10 git log 86x 556 47.8K 78.5% built-in good 11 kubectl logs 5x 3.6K 17.8K 43.0% plugin good 12 git status 86x 152 13.1K 58.0% built-in good 13 docker ps 20x 467 9.3K 52.8% plugin good 14 kubectl describe 6x 656 3.9K
Hacker News3mo agoToolAI
Hi!This is an infinite canvas note-taking tool where notes are laid out in a non-Euclidean, hyperbolic geometric space. As you drag and navigate through the view, you’ll experience a unique fluid distortion that naturally leverages your brain's spatial memory.I’ve been obsessed with the concept of space in HCI for years. Many modern UI patterns are essentially workarounds for the lack of screen real estate. While researching zoom-based UIs a while back, I stumbled upon old HCI papers that used the Poincaré disk model of the hyperbolic plane to organize data. It elegantly projects an infinite space into a finite disk, keeping everything contextually visible.I wanted to build an experimental app around this concept years ago, but the non-Euclidean math was a significant roadblock. Recently, I decided to give it a shot with the help of LLMs. It turns out that LLMs can handle the mathematical heavy lifting quite well, specifically in designing the coordinate systems and optimization algorithms, provided that you guide them with a solid architectural design.This is still an experimental demo, but I hope it leaves an impression. I’d love to know if you find this paradigm practical for organizing your thoughts.
Hacker News3mo agoToolAI