Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
Hi HN :) really excited to share this with you.The one thing AI reliably does is generate noise. Half the tools I see launch are just machines for producing more noise across more channels. And people are starting to see this in the form of emails in their inboxes as spam filters are struggling.There used to be a useful signal in email: the effort a sender put into customizing a message was a rough proxy for how relevant it actually was. AI killed that. Now it's customized slop with the appearance of effort with none of the cost. It is painful that the open internet / open channels have been abused like this.Captchainbox applies the idea of proof-of-work to email. If a sender is willing to do a bit of work to reach you, the message is more likely to be worth your time and the sender more likely to be real. The work is a traditional captcha. You can also set a pay-to-deliver amount if you want more friction. The proceeds of the delivery payment after transaction costs go to the Internet Archive and the EFF. The tool currently works by authing with your Gmail or Outlook and during launch time I make this completely free as a lifetime deal (with optional payment if you wanna support).How it works: Captchainbox builds a whitelist automatically from the metadata of your past correspondence. If you've emailed an individual address, that sender can reach you. If you talk to several people at the same domain, we whitelist the whole domain. If one transactional-looking sender has sent you more than 10 emails, we treat it as a transactional domain and let it through. This whitelist is for you to change whenever you want. It continues to build organically as you converse with more addresses.Incoming mail is checked against that whitelist. Senders already on it land in your inbox as normal. Anyone else gets archived (never deleted) and is sent a challenge. This can be the captcha or the payment link. Once they solve it, their email is pulled out of the archive an
Hacker News2mo agoToolAI
Hi HN, we're Kiran and Vijay!Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability.Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS Lambda.Since we process each span of every trace, instead of running LLM-based evals on each, we first analyze them using deterministic techniques. We detect tool failures, retries, loops, abnormal token usage, latency regressions, schema violations, sentiment, and other production signals. We've written more about the approach here: https://blog.oodle.ai/you-cant-sample-your-way-to-reliable-a...The combination of our own engine, no sampling, and deterministic processing before LLM-for-evals allows us to price at $10 per million traces, provide sub-second p99 query latency, and have healthy margins. Before building this, we used Langfuse for our own agent observability, which was 6x more expensive.Still super early, and rough around some edges, we would love your questions and feedback!
Hacker News2mo agoToolAI
I created an app that compares real-time prices and wait times across Uber, Lyft, Waymo, Tesla Robotaxi, Curb, and Empower. It shows you all ride options in one list, then once you’re ready to book, it deeplinks you to the provider’s app with the route pre-filled.Edit: Here's a demo video: https://www.youtube.com/watch?v=VV8PEAjxwQII reverse-engineered ride-hailing mobile apps to understand how they fetch prices from their servers. You sign in to my app with your ride-hailing accounts, and then my app requests live prices from the same APIs that ride-hailing apps use. Importantly, my app is built using an on-device approach: the app on your phone stores authentication tokens locally and sends network requests directly to each ride-hailing company’s servers. This keeps your accounts private. I wrote a blog post showing network requests sent by my app, which you can verify yourself: https://blog.hackney.app/p/how-hackney-worksThis seems like an obvious app. Why doesn’t it already exist? That’s because most ride-hailing companies don’t offer public APIs for prices and wait times. Uber does offer one, but they prohibit using it for price comparison. When someone built a comparison app using the official API, Uber terminated their API access (https://www.benedelman.org/news-053116). There are apps today that don’t use official APIs, but they run your account tokens through their servers and send price requests server-side.To integrate a ride-hailing provider, my app sends network requests for sign-in, token refresh, ride prices, and ride history (to power a feature that shows you unified ride history across apps and how much you’ve saved on each ride). Some ride-hailing apps implement certificate pinning to prevent you from viewing their network requests, and some communicate with their server using Protobuf, a data format that doesn’t include the original field names. Building an app using this approach is technical
Hacker News2mo agoToolAI
Hi all, author here. SX started as a CLI to let developers share skills across AI clients without having to rely on git for storage. This allowed sharing at the Repo/Team/Org and Personal level.However, the more we spoke to users the more we realized that non-technical users were actually using skills more and more but they had no way to share. And there was no way you were going to get your legal team to install and learn git.SX 2.0 is targeting non-technical teams by adding a native Mac, Windows and Linux app. Our vault format was reworked so it can be used directly as a claude or codex plugin. And by storing your vault in Dropbox, Google Drive, iCloud or others you can be up and sharing in under a minute.2.0 also adds an extension system with extensions that manage Skill Evals, LLM de-duping, metics and much more https://github.com/sleuth-io/sx-extensions.It's Apache-2.0 and you can download it here https://github.com/sleuth-io/sx.
Hacker News2mo agoToolAI
I built FixBugs, an agent that ingests the rich context surrounding production bugs to reproduce them in a sandbox and generate verified fixes. It's available in the form of a self-hosted VSCode extension and as a Github app:VSCode Extension: https://fixbugs.ai/go/vscode-extension - full code and data privacy. - zero data retention models opted out of training. GitHub App: https://fixbugs.ai/go/github-app - we do access your code temporarily. - pick a repo to install FixBugs on. What motivated me to build FixBugs were my years being on-call at Google and VMware. How many hours did I spend gathering logs, traces, reviewing metrics, and reading code only to find that,* Some context was missing.* The bug wasn't reproducible.* The alert was caused by a transient infrastructure issue.Too many. Inefficiency in investigating staging/production bugs has a real cost, and it's paid both by developers and customers.Current capabilities: - Reproduce the bug. - Identify the root cause. - Generate a fix. - Verify the fix. - Review the generated code using multiple AI models to help catch potential regressions. Do try it and let me know what you think!I'd especially love feedback from engineers who work with distributed systems or handle high-volume production bug triage.
Hacker News2mo agoToolAI
I created a simple CLI that turns a YouTube guitar-lesson video into a PDF of the guitar tab.There are services that transcribe music from Youtube videos into tabs, but they never work well enough for me. Instead I'm taking a simpler approach. It downloads the video, samples frames, uses Claude vision to locate the tab region, crops every frame to that region, de-duplicates the crops by the bar number printed on each line of the score, and stitches the distinct tab lines vertically into a PDF.I didn't test it on a lot of different Youtube videos yet, so problem will arise for sure.
Hacker News2mo agoToolAI
Hey HN! I made Orbit, an iOS app that allows you to see the satellites, planets, and constellations above you in AR, on a 2D map, and on a 3D globe. The app includes more than 15,000 objects tracked by CelesTrack, together with their pass predictions, descriptions, and detailed orbital data. A searchable catalog of all objects is also available, as well as a built-in chatbot designed to answer any space-related questions you might have.This is my first published iOS app, so any feedback is greatly appreciated! App Store: https://apps.apple.com/app/id6772174570
Hacker News2mo agoToolAI
Hey HN, we’re Shubham & Parth, childhood friends building Agnost AI (https://agnost.ai), product analytics for teams building chat and voice agents.We read production conversations and find behavioral failures like users rageprompting (cursing at the agent), repeatedly rephrasing the same request, correcting the agent, asking for missing features, or leaving after an answer that was technically successful.We have an interactive demo with no signup here: https://app.agnost.ai?demo=trueHere's a demo video: https://www.tella.tv/video/agnost-ai-launch-hn-demo-9haaThe core problem is that chat and voice products do not have the same metrics as web apps. When the product interface is language, clicks and funnels become much less useful. Users also rarely give explicit feedback, and when they do it's usually sugarcoated. I barely type /feedback in Claude or Codex myself. Most users just curse, ask again, correct the agent, or leave. So product engineers get technical visibility from latency, errors, and traces, but still have to guess whether users got what they wanted.We got here after building around agents for the last year and got a couple of founders asking for something like a PostHog for conversations for the AI assistants they were building.We are not trying to be in the observability or evals space. Observability tells you what happened technically. Evals validate cases you already know. We're more on the discovery side like what users wanted, where they got frustrated, what they asked for repeatedly, and what new evals should exist.Teams send us agent conversation messages through SDKs or OTel, optionally with metadata like account, plan, source, organization, etc. We cluster conversations into product-specific intents. Feature requests and bugs are default categories; most other clusters are created dynamically from the customer’s data and evolve over time. You can create your own cluster in plain E
Hacker News2mo agoToolAI
Hi guys,I've been using Claude Code for almost everything lately. Have given one an email account so it can research business leads, draft emails, fact-check them and clear them with me before sending (works really well by the way). I also tend to have a few Claude Code agents running at any one time for coding.I used to create a split terminal to manage them from there, but found working in the terminal all day pretty depressing and, more importantly, found it hard to follow Claude Code's process and see which agents needed my immediate attention.I tried Anthropic's VS Code Claude Code extension and it had a great UI (more info on Claude Code's process and easier to read), but it crashed my PC when I ran more than 3 and I couldn't watch multiple agents in parallel (had to constantly switch between them).So I built a lightweight Tauri desktop app which lets you run multiple Claude Code agents in one window alongside each other. It's easier to read the output and see which agents need your attention than a terminal.Have been using this all day everyday instead of an IDE and have obsessed over every detail to make sure it's easy-to-use, but also lightweight and fast (so you can manage multiple agents without your PC crashing).There are some nice features like better usage alerts for when you're going to hit your 5-hour and weekly limits (with sparklines to show when usage peaked, and which agents are the most token-intensive).It's free to use (you just need to log in with your existing Claude Code account) for up to 4 agents simultaneously. This app doesn't store your Claude Code account details and doesn't store any of your interactions with Claude Code. They remain between you and Anthropic. It's compatible with Windows, MacOS and 64-bit Linux.Would really appreciate any feedback, so if you have any thoughts, issues or suggestions please let me know.Thanks, Chris
Hacker News2mo agoToolAI
Existing STT models struggle with accurate diarization and chunking after initial use, making it difficult to create reliable searchable memories from conversations or recordings.
X2mo agoToolAI
AI agents require a shared platform (like a 'waterpark') where they can post in-progress projects, connect with other agents, and exchange help or feedback during development.
X2mo agoToolAI
I started leaning in on AI heavily this year, as I wanted to get more done autonomously, but then my token usage climbed dramatically to the point where my weekly quota would run out before the end of the week, sometimes a couple of days into the week.I realised I had to do something about it else I'd have to double my spend. So I decided to start tracking my cost per task type. This revealed that a lot of my spend went to searches/scans or simple things like scouting tasks.I then decided to turn this into a simple CLI tool that can be used to read your OpenAI-style logs locally, and analyze the cost and compare this spend to other models, then show you how much you could potentially save by switching those calls to a cheaper model.When you run analyze you get an offline estimate priced against LiteLLM and gated by LMArena tiers. The general savings bands come from the research published by RouteLLM; but you can confirm this yourself using 2 commands --measure (shows the prompt-response output side by side) and --judge (a model chosen to do the comparisons). These send a sample of the prompts from the logs to the candidate models - either the default choice or set by you. This call goes directly to the model provider (never through me) as any normal LLM call would, and the response is shown and judged to either be better or worse or a tie.It's deliberately small, because I tend to over complicate/think things sometimes: analyze + capture + a few commands, doing three jobs. Cost, quality visibility, routing recommendation.Nothing is hosted. capture is an optional local proxy on your own machine, and there's no endpoint in the path of your data. You can confirm this by checking the source.I included a demo so you can check out the output. It has a synthetic 56k call log (a month's worth) showing how costs can drop from $549.46 to $343.91 a month. A 37.4% saving.Try it: uvx frugon analyze --demo or uv tool install frugon Then point it
Hacker News2mo agoToolAI
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't seen elsewhere.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/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.Details for each page:- 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.- 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/move history and related files that often change together (useful for a coding agent).- 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.- Relationships: A graph of interactions between contributors, weighted
Hacker News2mo agoToolAI
There is a mobile game called DragonBox. It sort of tricks you into learning algebra by starting with very abstract manipulations of a puzzle that must follow rules... gradually the game teaches you more and more rules and also strips out the more abstract elements until on the last levels you are finally solving real equations. I loved it, it taught my kids algebra.... and it was just fun.Over the years I often thought that there should be a calculator for Algebra that works this way... something where you can drag terms around and cancel & distribute with gestures, but most importantly enter your own problems. It should also do more kinds of problems than DragonBox allowed. So I finally decided to build it.https://dicroce.github.io/wyrm/home.htmlHere's a video showing it: https://www.youtube.com/watch?v=_STbS4zvIlU. If you'd rather just play with it: there's a limited in-browser demo (real engine, a few example equations, no download) on the landing page — https://dicroce.github.io/wyrm/home.html.The app can be found on iOS (https://apps.apple.com/us/app/wyrm-math/id6782342042) and as of this week on Google Play (https://play.google.com/store/apps/details?id=com.dicroce.wy...).I also decided to open source the underlying math engine so others could build on it: https://github.com/dicroce/wyrm_math. My goal for the engine btw is to build it all the way up to Calculus.Monetization is deliberately boring: the engine is free (MIT), and the polished gesture app is $4.99 once. No subscriptions, ads, accounts, or analytics.I'd love feedback on the engine design — especially from anyone who's worked on CAS or proof-assistant-adjacent problems. And if you played DragonBox as a kid and wished it went further: this is for you!
Hacker News2mo agoToolAI
Hey HN! We built a browser-based agent that runs inside an authenticated web app, watches how the app calls its own APIs, and automatically turns those into agent tools. You can think of it as an auto-generated MCP server that self-updates as the host app changes.The result is a skilled AI assistant that actually integrates deeply with any product (not just chat and RAG) with minimal effort.Check out these short demos below that show the agent in software you're probably familiar with:- Jira: https://demo.frigade.com/hn?skill=jira- Spotify: https://demo.frigade.com/hn?skill=spotify- Hacker News (lol): https://demo.frigade.com/hn?skill=hackernews- Full Demo: https://demo.frigade.com/hn?skill=full-demoAs you can see in the examples, you can do way more (and faster) than what you normally would be able to via point and click. And we never even touched the source code of these products!Why do this?In an ideal world, every application has an MCP server or an easily-digestible API available for AI agents to feed from. In practice, we found that even very modern software tends to have a spider web of confusing APIs and services that AI agents simply cannot use out of the box. Security also becomes a huge issue as applications have different (often homebrewed) standards for how endpoints are secured (JWTs/cookies/mix of both). Finally, having an actual browser agent go in and use the application on behalf of the user (i.e. computer-use), is simply too brittle, slow, and burns a lot of tokens.We took our existing browser agent that’s already trained to use and learn authenticated applications, and added an extra step that automatically turns the app’s authenticated APIs into "recipes". A recipe is a mix of the following:- API endpoint + method- Authentication method (and how to retrieve refresh auth tokens/cookies)- Response schema- Input schema (for POST/PUT)- Human readable descr
Hacker News2mo agoToolAI
Hacker News2mo agoToolAI
Need simple, user-friendly hosting options for setting up personal AI agents, prioritizing ease of use over complex setups.
X2mo agoToolAI
I've been slowly adding some new free tools to Moxie Docs (partly for SEO, partly to illustrate some of our feature sets before any commitment) for some reason this mermaid editor one blew up on Google rankings so I figured I'd share in case people find it useful! We also have ADR, AGENTS.md, LLMs, and a few other free tools.
Hacker News2mo agoToolAI
When I read papers, I have to jump between multiple tabs to find the dataset, code, videos, peer reviews, and so on. I tried to fix this with this project.It started as a project just for papers on arXiv, but after its initial success on Twitter (got like 1.9k views: the most I have gotten for a post), I have now expanded it to include other openly available papers from PubMed Central, bioRxiv, medRxiv, and eLife. These papers have been linked with their genes, proteins, diseases, drugs, clinical trials, 3D protein structures, code, and cited and similar papers.This project now has four parts:First, a map. I embedded nearly 8.5M papers (with SPECTER2), ran UMAP for 2D representation, and rendered them as a scatterplot. The dots can be clicked to see brief information about the papers, like an LLM TLDR, key findings, peer reviews, linked entities, and more. The clusters are also labeled, though you might have to zoom in.Second, I built a detailed paper page for each paper. They give you the paper's full text, images, videos, peer reviews (from OpenReview), GitHub links, Hugging Face dataset/model links, clinical trials, genes, diseases, 3D protein structures, cited papers, and similar papers. You can also copy the whole page, including the full paper text and image URLs, as markdown for your LLM.Third, I have released an extension so you can read all this information in your sidebar by clicking "open in Tomesphere" that shows up in arXiv, PMC, bioRxiv, Google Scholar, or medRxiv. I have tried to provide as much information as possible in the extension, though for things like viewing all the images or a 3D protein structure, you might still have to go to the paper page using the link provided in the extension.Fourth, all this data is available for your LLM via MCP. The MCP does have a 50-query free limit (this jumps 10x with signup).Note: this project is still in beta, so papers might have some mismatched information. I am rolling out feedback form
Hacker News2mo agoToolAI
Hi Hacker News, I’m Yahia. I built Context.dev (https://www.context.dev/) to make it really easy to integrate web data into your products and agents.Here’s a demo video: https://www.tella.tv/video/build-faster-with-context-dev-api...Since it’s an API, here are the docs: https://docs.context.dev/quickstart.You can send us a URL and get back clean Markdown, rendered HTML, screenshots, extracted images, etc.. You can also send us a domain and get company or brand context: name, description, logos, colors, fonts, social links, screenshots, style information, and related metadata. For more custom use cases, you can send a URL plus a JSON Schema and ask us to extract structured data from the site into that shape. For example, you might ask for pricing plans, product categories, office locations, support links, integration partners, or anything else that is visible on the public site.The goal is to give developers the output they actually want. Raw HTML is rarely the useful thing; the useful thing is usually Markdown for a model, JSON for an application, a logo for a UI, or a structured company profile for an agent.Before, I worked at Amazon and Sunrun, and co-founded StockAlarm.io & essense.io, both of which were acquired. Also, I built knifegeek.io, which scraped pocket knives from across the internet and listed them easily. The project is outdated now (coming back soon) but back then it hit the frontpage of hacker news and people seemed to like it: https://news.ycombinator.com/item?id=34604281.Just before Context.dev, I built Brand.dev. The idea was that your software product should automatically know about your customer if they sign up with a corporate email. The API pulled brand data such as logos, backdrops, name, description, industry, and more from the public web and surfaced it to your product to integrate as part of their onboarding experience. That’s worth doing because conversion rates on onbo
Hacker News2mo agoToolAI