Open-weight OCR got so cheap I had to share it
This was not supposed to become a product. When PaddleOCR-VL-1.6 dropped, independent benchmarks put it at the top of document parsing models. I had to try it. I needed a provider, but there simply isn't one ready for production that I would trust. So i set one up myself. I assumed that even after getting it running, serving a vision-language model would be expensive. It turns out the opposite is true. Once I had it running properly, the cost was absurdly low. At proper GPU utilization, the cost is only around $1 per 1,000 pages. The nearest competitors are either much lower quality (Azure Read) or absurdly expensive (Extend or Reducto). Even Mistral OCR 4 which is really good and pretty cheap is still 4x more expensive. So I had to share it. I made the endpoitns public, and vibe-coded a simple dashboard. Let me know what you think!
Leet Robotics: Learn robotics and ROS2 with hands-on courses
Hi all, I've just launched Leet Robotics: a platform to learn robotics hands-on, with a full ROS2 workspace that runs in the browser (Jazzy, Gazebo Harmonic, Foxglove, VS Code) - no install required. The platform also has room for sharing projects and simulation assets as it grows. Our first course is live now: Intro to ROS2 (free to read). The course teaches skills ranging from building your first node to a capstone project of a robot touring a museum world, with every lesson runnable in the online workspace (free accounts get an hour of workspace time daily - enough to follow the course). Would love feedback from this community: on the course, the workspace experience, and what courses to build next.
Agnost
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=true Here's a demo video: https://www.tella.tv/video/agnost-ai-launch-hn-demo-9haa The 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 English. If a cluster gets too broad, we split it. If a new pattern appears, we suggest it. One AI video editor company used Agnost AI to find feature requests hidden inside chat. The biggest one was that around 70 users wanted auto-subtitles, but users said it as “add this text in this frame” 12x in a single session, “can you caption it”, “give me transcript of audio” and variations across languages. The team later built the feature. Doing this over millions of messages without sending everything to an LLM was the hard part initially. In ClickHouse, “fetch the last 50 events by time across conversations” and “fetch all events in this conversation” want different sort orders, so we had to iterate a lot on sorting keys, partitions, materialized views, and projections. For finding new clusters, sending everything through an LLM was too slow and expensive. HDBSCAN-style embedding clustering also gets painful at scale because of pairwise comparisons. We first split conversations into segments based on cosine drift, run BIRCH to compress the candidate space, and then use HDBSCAN-like clustering on the smaller set. For matching existing clusters, we use embeddings, smaller classifiers/BERT-style models, and LLMs only as fallback for ambiguous cases. We’re live with multiple companies and ingesting ~1M chat and voice messages per day. Pricing is public: Starter is free, Pro is $499/month, and Enterprise is for higher volume, security, retention needs. We use each customer’s data only for that customer. We are SOC 2 Type 1 compliant, Type 2 is in progress, and our SDKs are on PyPI and npm. We’d love feedback from the HN community and people building chat or voice agents: how do you detect these signals today, what feedback methods have worked, and what would block you from trying this? Happy to answer questions and take criticism.
I built a one-prompt hackathon platform, free entry, sponsored prizes
Show HN: I built a one-prompt hackathon platform, free entry, sponsored prizes
Bitboard
We’re Connor and Ambar from BitBoard (https://bitboard.work). BitBoard is an agentic analytics workspace. We give you the infrastructure and visualization layer to analyze data with AI. Today, we’re launching dashboards that you and your agents can work on together. You can connect your coding agent or AI chat to BitBoard and build live reporting. Here’s a demo: https://www.youtube.com/watch?v=HPl0K565a7c. AI tools treat data analysis as ephemeral, making it hard to report or collaborate. Legacy BI tools weren’t intended for AI users, so they bolt on chatbots and can’t offer meaningful control to your agents. Software can now make far more of a business legible than BI ever could, but neither legacy BI nor chat bots are built to handle it. Our original product was AI agents for administrative tasks in healthcare (https://news.ycombinator.com/item?id=44237769), but customers kept pulling us toward their data analysis problems: queries scattered across disparate sources, spreadsheets floating everywhere. We kept building tooling for addressing that, and at a certain point those tools were becoming our product. We ran into several problems. Agents made bad inferences because they had no context on the business. They couldn't be trusted to make decisions because nothing checked their work. And anything one agent or one person figured out was invisible to everyone else. In BitBoard, humans and agents interact with the same data primitives but get tools designed for their own work. We’re building dashboards to make the human reading experience better. These dashboards progressively use intelligence - starting from code or SQL queries and leading to full embedded apps. Humans and agents will need to agree on methods to interpret data, so we’re letting both contribute to canonical sources, entities, and measures (using your favorite semantic model or ours). Every answer comes with provenance, and the same call with the same parameters returns the same number. Looking ahead, these shared primitives let long-running agents operate inside a business, and we're building those agents too. An agent needs a measurable goal and a way to verify its work. BitBoard gives it both. The agent takes a problem like a metric drifting or a funnel leaking and figures out what to do next. Its work becomes datasets, dashboards, and traces that the team can observe and sign off on. Technically, we’re building a collaboration engine with isomorphic updates for humans and AI, columnar analysis (we use DuckDB and Apache Arrow), grounding and verification infrastructure, and enabling long running tasks with agent containers and traces. For agentic work we’re big fans of applying LLM judgement to discover problems, and then generating deterministic software to automate them. Try it out at https://app.bitboard.work. (We require an email so we can set up your account). We’re excited about how data analysis and science can change in the age of LLMs, and welcome all your thoughts!
StackScope
Hey all, I built StackScope, a crawler/catalogue that looks at new product launches and shows what they were built with. It watches launches from Product Hunt, Show HN, and PeerPush, then crawls the public site behind each one. The goal is to show what people actually launched with: hosting, frameworks, analytics, DNS, security headers, legal pages, AI-builder signals, and other public clues. I started building it because most stack-detection sites look at the web as a whole. I was more interested in the current indie launch scene: what people are choosing right now, at the point they first put something in public. A few implementation details: it runs on .NET, uses Playwright for rendered pages, and has a first-party fingerprint catalogue rather than one copied from Wappalyzer/etc. robots.txt is honoured, and the bot identifies itself. Frustratingly, I am still waiting for verified bot status from Cloudflare and currently that knocks out about 10% of all sites. There is also a private readiness check: paste a URL, get the same style of report, fix things, and recrawl. No account or email needed. I'd be interested in feedback on the usefulness of this, the methodology, and any obvious false positives. Jonathan.
GrayCloud
I miss Dark Sky, so I built my own weather app. Here's how GrayCloud works: * Raincast: minute-by-minute rain prediction and accumulation tracking for your exact location * Forecasts: 10 day forecasts use multiple high resolution sources and correct for bias at your location. * Alerts: rain starting, stopping, severe weather, daily summary and more * Widgets: home and lock screen widgets * Multi-platform: apple watch and mac apps I use NOAA and ECMWF models for core weather data and a custom model to compute rain accumulation and the next 60 minute radar movements. I also offer Apple WeatherKit as an alternative weather source.
500 years of Joseon court omens as an observability dashboard
Show HN: 500 years of Joseon court omens as an observability dashboard
Superlog (YC P26)
Hey HN, we’re Nico and Arseniy, co-founders of Superlog (https://superlog.sh). We're building a self-installing, self healing observability tool meant not to be opened. It has a wizard that daily sets up proper logging and an agent that investigates errors and opens PRs. Super short demo: https://www.youtube.com/watch?v=xFhU9Mk247M. In our earlier startups, we tried Sentry, Datadog, Grafana, Dash0, and nothing was good enough. Proper telemetry and alerting still requires a ton of manual setup. We struggled with adding good logs, so debugging was tough, especially as codebases grow at a faster pace. Meanwhile, the Datadog/Dash0 bill kept climbing, and we still spent engineering hours to learn, configure, and maintain our observability tooling. With Sentry, we found ourselves flooded by a stream of alerts into our Slack channel, most were duplicates or lacked context, so alert fatigue/constant interrupts were a real pain. The #ops notification is consistently the worst feeling on a Saturday morning We’ve seen too many times servers run out of memory and disk, and three AWS metrics giving us three different values. Half of the graphs on dashboards are normally empty or outdated, and manually clicking through UIs, especially when the team is small, seems like a huge waste of time. At some point we realized that solving this problem would be more valuable than the things we had been working on, and we had the expertise to do it, since Arseniy had spent years at Datadog, getting paged during the night to debug production incidents. So we decided to build a platform that would just work: agent-first, MCP-native, zero-setup. Here’s how Superlog works: we have a wizard that scans your repo, and automatically instruments it with well-structured logs, traces and metrics via OpenTelemetry. We make sure to highlight main failure modes, endpoint performance, usage per tenant, and LLM/upstream cost (by callsite, tenant and model). Errors get fingerprinted and grouped into incidents, so you see one issue, not a thousand duplicates. When you get a notification from Superlog, you see a clear failure summary, its inferred severity and impact upfront. Then the agent investigates and tries to solve the issue. If it has enough context, it produces a concise and tested PR. If it doesn't, it posts its findings for the investigating team, and automatically pulls in the engineers that could contribute more context based on documentation, previous investigations and Slack threads. Either way the output is one clean PR per incident, posted in Slack, that you can merge, ignore, or open as a Claude Code session and modify. Three things we think are different from other observability vendors: (1) We solve the setup pain. The wizard will instrument everything with native OTel SDKs, respecting the semantic conventions, with proper service and environment tagging. We’re also working on native automatic dashboards and alerts, so that you can see what’s going on in a glance and don’t miss subtle failure modes. (2) Our telemetry doesn’t decay. The wizard runs daily, and keeps adding logs, alerts and dashboards where it’s needed. You don't have to remember to instrument new features. The next time something breaks, the data you need to debug it is already there. (3) Our goal is to solve alert fatigue. We use agents to merge similar errors and refine the summaries, giving you relevant information upfront. We have a custom evaluation setup that makes sure that our summaries are dense and correct, and severity and impact is on point. We also give you confidence scores for every LLM-enhanced metric so that wrong guesses don’t get boosted. Important: superlog telemetry is vendor-neutral, so you keep all the logs/metrics/traces we install. Pricing is on the site. We're early, so expect rough edges and please tell us when you find them. You can try it at https://superlog.sh. We'd love to hear what you're using today, what's broken about it, and whether the "one mergeable PR per incident" model sounds useful or terrifying. Especially keen to hear from folks running integration-heavy products, anyone who's rolled their own observability, and anyone who has tried Sentry / Datadog MCPs and given up. Comments and feedback welcome!
Vibe Coding a $20k /Year Enterprise Logistics Platform
Show HN: Vibe Coding a $20k /Year Enterprise Logistics Platform
Live Sun and Moon Dashboard with NASA Footage
Show HN: Live Sun and Moon Dashboard with NASA Footage
CatchAll
Hey HN, Artem and Maksym from NewsCatcher here. Some of you know us as we started six years ago as two freshly graduated economics students who decided to build the best news API product. We started NewsCatcher thinking the market for news APIs was so big that we could build a self-serve platform and get millions of $29 users. Obviously, it was a wrong assumption. We pivoted to serve enterprises and had success with it. But we are hackers at heart, and we want to serve hackers. We haven't used our Launch HN yet, so consider this our smoke test. We're looking for feedback and power users rather than revenue. So, happy to provide enough credits for any HN user who finds CatchAll useful. CatchAll is built for one thing: retrieving every matching event from the web. The use cases that fit it are ones where missing events have real consequences — funding and M&A monitoring, regulatory and compliance feeds (FDA approvals, SEC filings, policy changes), cybersecurity incident tracking, supply chain signals. If your pipeline consumes structured records and the answer to your query is "find all of them," that's where it works. It's not the right tool for small, bounded queries that return 5 high-precision results. The 15-minute job time is a direct consequence of the pipeline depth: analyze, fetch, cluster, validate, extract, deduplicate. You're not getting a ranked list of links; you're getting a verified record set. Our latest benchmark run: https://newscatcherapi.com/blog-posts/web-search-api-benchma...