The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Math2Tex – Convert handwritten math and complex notes to LaTeX text
Hi HN,<p>I’m the creator of Math2Tex. I was a PhD student, I spend a huge amount of my time working with LaTeX, especially when dealing with lecture notes, academic papers, and homework. I built *Math2Tex*, a lightweight tool that converts handwritten or printed academic content — especially math formulas — into LaTeX or text<p>The Problem:<p>I've always found it incredibly tedious to manually type out mathematical formulas, especially complex, multi-line equations from my handwritten notes or from a textbook. It's slow, boring, and I always make syntax errors. I tried some existing tools, but they often struggled with my handwriting or couldn't handle mixed content (text and formulas together).<p>The Solution:<p>So, I built Math2Tex to solve my own problem. It’s a straightforward, single-page web app: you upload an image (a photo of your notebook, a screenshot of a PDF, etc.), and it converts the academic content into clean LaTeX code or plain text. You get a real-time preview and can copy the result with one click. My goal was to make the workflow as fast as possible: Snap. Convert. Done.<p>You can try it here: [<a href="https://math2tex.com" rel="nofollow">https://math2tex.com</a>](<a href="https://math2tex.com/" rel="nofollow">https://math2tex.com/</a>)<p>How is it different from general AI tools like GPT, Claude, etc?<p>This is a fair question. While large models can handle this, they are often slow for such a specific task. I wanted something faster and more specialized. Math2Tex uses a lightweight model fine-tuned specifically for academic content recognition.<p>In short, think of it as a specialized scalpel versus a Swiss Army knife. For this particular job, it's generally 3-5x faster and, in my experience, more reliable for complex notations.<p>Tech Stack:<p>The core OCR engine is a custom-trained model based on a transformer architecture, fine-tuned on a large dataset of both printed and handwritten academic material. It's all deployed on Vercel.<p>*It's free to use.* This is still an early version, and I'm sure there are plenty of bugs and areas for improvement. The recognition might not be perfect, especially with very messy handwriting or some obscure symbols.<p>I would be incredibly grateful for your feedback. Whether you’re a student, researcher, or someone who’s fought with LaTeX input. Feedback on both the tool and the approach would be really helpful.<p>Thanks!
Show HN: Math2Tex – Convert handwritten math and complex notes to LaTeX text
Hi HN,<p>I’m the creator of Math2Tex. I was a PhD student, I spend a huge amount of my time working with LaTeX, especially when dealing with lecture notes, academic papers, and homework. I built *Math2Tex*, a lightweight tool that converts handwritten or printed academic content — especially math formulas — into LaTeX or text<p>The Problem:<p>I've always found it incredibly tedious to manually type out mathematical formulas, especially complex, multi-line equations from my handwritten notes or from a textbook. It's slow, boring, and I always make syntax errors. I tried some existing tools, but they often struggled with my handwriting or couldn't handle mixed content (text and formulas together).<p>The Solution:<p>So, I built Math2Tex to solve my own problem. It’s a straightforward, single-page web app: you upload an image (a photo of your notebook, a screenshot of a PDF, etc.), and it converts the academic content into clean LaTeX code or plain text. You get a real-time preview and can copy the result with one click. My goal was to make the workflow as fast as possible: Snap. Convert. Done.<p>You can try it here: [<a href="https://math2tex.com" rel="nofollow">https://math2tex.com</a>](<a href="https://math2tex.com/" rel="nofollow">https://math2tex.com/</a>)<p>How is it different from general AI tools like GPT, Claude, etc?<p>This is a fair question. While large models can handle this, they are often slow for such a specific task. I wanted something faster and more specialized. Math2Tex uses a lightweight model fine-tuned specifically for academic content recognition.<p>In short, think of it as a specialized scalpel versus a Swiss Army knife. For this particular job, it's generally 3-5x faster and, in my experience, more reliable for complex notations.<p>Tech Stack:<p>The core OCR engine is a custom-trained model based on a transformer architecture, fine-tuned on a large dataset of both printed and handwritten academic material. It's all deployed on Vercel.<p>*It's free to use.* This is still an early version, and I'm sure there are plenty of bugs and areas for improvement. The recognition might not be perfect, especially with very messy handwriting or some obscure symbols.<p>I would be incredibly grateful for your feedback. Whether you’re a student, researcher, or someone who’s fought with LaTeX input. Feedback on both the tool and the approach would be really helpful.<p>Thanks!
Were RNNs all we needed? A GPU programming perspective
Were RNNs all we needed? A GPU programming perspective
Show HN: FocusStream – Focused, distraction-free YouTube for learners
I built FocusStream because I was tired of going to YouTube to learn one thing, then getting lost in recommendations and distractions.<p>With FocusStream, just enter your topic and get only the relevant YouTube videos—no unrelated suggestions or autoplay.<p>It’s free, minimal.
Would love your feedback!<p>Try it: <a href="https://focusstream.media" rel="nofollow">https://focusstream.media</a>
Demo video: <a href="https://drive.google.com/file/d/1fCvOJ6kRs9jn7O_hIGgP6wBuq4fzFAOT/view?usp=drive_link" rel="nofollow">https://drive.google.com/file/d/1fCvOJ6kRs9jn7O_hIGgP6wBuq4f...</a>
Show HN: FocusStream – Focused, distraction-free YouTube for learners
I built FocusStream because I was tired of going to YouTube to learn one thing, then getting lost in recommendations and distractions.<p>With FocusStream, just enter your topic and get only the relevant YouTube videos—no unrelated suggestions or autoplay.<p>It’s free, minimal.
Would love your feedback!<p>Try it: <a href="https://focusstream.media" rel="nofollow">https://focusstream.media</a>
Demo video: <a href="https://drive.google.com/file/d/1fCvOJ6kRs9jn7O_hIGgP6wBuq4fzFAOT/view?usp=drive_link" rel="nofollow">https://drive.google.com/file/d/1fCvOJ6kRs9jn7O_hIGgP6wBuq4f...</a>
Show HN: FocusStream – Focused, distraction-free YouTube for learners
I built FocusStream because I was tired of going to YouTube to learn one thing, then getting lost in recommendations and distractions.<p>With FocusStream, just enter your topic and get only the relevant YouTube videos—no unrelated suggestions or autoplay.<p>It’s free, minimal.
Would love your feedback!<p>Try it: <a href="https://focusstream.media" rel="nofollow">https://focusstream.media</a>
Demo video: <a href="https://drive.google.com/file/d/1fCvOJ6kRs9jn7O_hIGgP6wBuq4fzFAOT/view?usp=drive_link" rel="nofollow">https://drive.google.com/file/d/1fCvOJ6kRs9jn7O_hIGgP6wBuq4f...</a>
Show HN: Nanobot – Turn MCP servers into full AI agents
Today we're releasing Nanobot an open-source framework for building AI agents on top of the Model Context Protocol (MCP).<p>MCP servers are a great way to expose structured tools, but they’re usually just that—collections of functions. Nanobot makes it simple to wrap any MCP server with reasoning, a system prompt, and orchestration so it behaves like a real agent. Even better, Nanobot fully supports MCP-UI, so agents can pass rich interactive components (forms, dashboards, even mini-apps) directly into chat.<p>A simple example: if you had a Blackjack MCP server with tools like deal, bet, and hit, you could wrap it with Nanobot to create a dealer agent that knows how to explain the game, guide a player, and render an interactive Blackjack table inside chat.<p>We built this because we wanted agents that go beyond text and function calls, into actual interactive experiences—something useful for everything from games to e-commerce to developer tools.<p>Code is on GitHub: <a href="https://github.com/nanobot-ai/nanobot" rel="nofollow">https://github.com/nanobot-ai/nanobot</a><p>Live demo (Blackjack): <a href="https://blackjack.nanobot.ai" rel="nofollow">https://blackjack.nanobot.ai</a><p>We’d love feedback from this community—on the framework, the design, and what you’d like to see next.
Show HN: Dyad, local, open-source Lovable alternative (Electron desktop app)
Hi HN!<p>I left Google earlier this year and created Dyad, a local, open-source AI app builder made with Electron.<p>The motivation: I tried one of the popular cloud-based AI app builders, but when I pulled down the app to run locally and debug in Cursor, it just didn’t work. So I created Dyad, an app builder that runs fully on your computer, making it easy to switch between Dyad and coding tools like Cursor or Claude Code.<p>Source code: <a href="https://github.com/dyad-sh/dyad/" rel="nofollow">https://github.com/dyad-sh/dyad/</a><p>Download (free, no sign-up): <a href="https://www.dyad.sh/" rel="nofollow">https://www.dyad.sh/</a><p>I've gotten questions about how it works under the hood so I wrote an architecture doc explaining how it does tool calling using XML tags, etc:
<a href="https://github.com/dyad-sh/dyad/blob/main/docs/architecture.md" rel="nofollow">https://github.com/dyad-sh/dyad/blob/main/docs/architecture....</a><p>Let me know what you think and happy to answer questions about building an Electron app, etc!
Show HN: Zedis – A Redis clone I'm writing in Zig
Writing Redis from scratch in Zig.
Show HN: Zedis – A Redis clone I'm writing in Zig
Writing Redis from scratch in Zig.
Show HN: Zedis – A Redis clone I'm writing in Zig
Writing Redis from scratch in Zig.
Show HN: WeUseElixir - Elixir project directory
Show HN: WeUseElixir - Elixir project directory
Show HN: WeUseElixir - Elixir project directory
Show HN: WeUseElixir - Elixir project directory
Show HN: KSON, a love-letter to the humans maintaining computer configuration
Hi friends, I'm really excited to introduce KSON, which just entered public beta!<p>Anywhere a human is reading or editing YAML/JSON/TOML, KSON may be used as a more effective interface on that data. If you are such a human, we invite you to participate in this beta.<p><i>tl;dr</i> Check out the website [1], play with the online playground [2], install the library for your programming language [3], edit in your favorite editor [4], discuss and give feedback [5], contribute to the project [6].<p>(A personal note about this project: I love software. Machines made of words! Such a wonder. KSON itself, as a collection of words that both make a machine <i>and</i> explain that machine, is an expression of a lot ideas I feel really passionately about around software and our relationship to it. I've put a lot of love into trying to make that expression eloquent and reliable. I hope some of that comes through clearly, and I look forward to discussing this more over time with anyone who's interested)<p>One of the key things KSON wants to say is: let's keep everything that's great about YAML and JSON as "Configuration User Interfaces", and let's make those interfaces more toolable, robust, and fun. Here's some of the ways we do that:<p>- KSON is a verified superset of JSON, has native JSON Schema support, transpiles cleanly to YAML (with comments preserved!), and is likely available wherever you want it—current supported platforms: JS/TS, Python, Rust, JVM, and Kotlin Multiplatform.<p>- KSON is also widely available in developer tools, with support for VS Code, Jetbrains IDEs, and anywhere you can plug in an LSP.<p>- KSON is fully open source, licensed under Apache-2.0, and you are invited to meet its words and tinker with how they make its machine. A lot of care, craft, attention and joy went into making the KSON project understandable and approachable for developers. We hope to see you around.<p>PS. This is an HN-friendly version of the official announcement at <<a href="https://kson.org/docs/blog/2025/09/17/introducing-kson/" rel="nofollow">https://kson.org/docs/blog/2025/09/17/introducing-kson/</a>>.<p>[1]: <a href="https://kson.org/" rel="nofollow">https://kson.org/</a><p>[2]: <a href="https://kson.org/playground/" rel="nofollow">https://kson.org/playground/</a><p>[3]: <a href="https://kson.org/docs/install/#languages" rel="nofollow">https://kson.org/docs/install/#languages</a><p>[4]: <a href="https://kson.org/docs/install/#editor-support" rel="nofollow">https://kson.org/docs/install/#editor-support</a><p>[5]: <a href="https://kson-org.zulipchat.com/" rel="nofollow">https://kson-org.zulipchat.com/</a><p>[6]: <a href="https://github.com/kson-org/kson" rel="nofollow">https://github.com/kson-org/kson</a>
Show HN: KSON, a love-letter to the humans maintaining computer configuration
Hi friends, I'm really excited to introduce KSON, which just entered public beta!<p>Anywhere a human is reading or editing YAML/JSON/TOML, KSON may be used as a more effective interface on that data. If you are such a human, we invite you to participate in this beta.<p><i>tl;dr</i> Check out the website [1], play with the online playground [2], install the library for your programming language [3], edit in your favorite editor [4], discuss and give feedback [5], contribute to the project [6].<p>(A personal note about this project: I love software. Machines made of words! Such a wonder. KSON itself, as a collection of words that both make a machine <i>and</i> explain that machine, is an expression of a lot ideas I feel really passionately about around software and our relationship to it. I've put a lot of love into trying to make that expression eloquent and reliable. I hope some of that comes through clearly, and I look forward to discussing this more over time with anyone who's interested)<p>One of the key things KSON wants to say is: let's keep everything that's great about YAML and JSON as "Configuration User Interfaces", and let's make those interfaces more toolable, robust, and fun. Here's some of the ways we do that:<p>- KSON is a verified superset of JSON, has native JSON Schema support, transpiles cleanly to YAML (with comments preserved!), and is likely available wherever you want it—current supported platforms: JS/TS, Python, Rust, JVM, and Kotlin Multiplatform.<p>- KSON is also widely available in developer tools, with support for VS Code, Jetbrains IDEs, and anywhere you can plug in an LSP.<p>- KSON is fully open source, licensed under Apache-2.0, and you are invited to meet its words and tinker with how they make its machine. A lot of care, craft, attention and joy went into making the KSON project understandable and approachable for developers. We hope to see you around.<p>PS. This is an HN-friendly version of the official announcement at <<a href="https://kson.org/docs/blog/2025/09/17/introducing-kson/" rel="nofollow">https://kson.org/docs/blog/2025/09/17/introducing-kson/</a>>.<p>[1]: <a href="https://kson.org/" rel="nofollow">https://kson.org/</a><p>[2]: <a href="https://kson.org/playground/" rel="nofollow">https://kson.org/playground/</a><p>[3]: <a href="https://kson.org/docs/install/#languages" rel="nofollow">https://kson.org/docs/install/#languages</a><p>[4]: <a href="https://kson.org/docs/install/#editor-support" rel="nofollow">https://kson.org/docs/install/#editor-support</a><p>[5]: <a href="https://kson-org.zulipchat.com/" rel="nofollow">https://kson-org.zulipchat.com/</a><p>[6]: <a href="https://github.com/kson-org/kson" rel="nofollow">https://github.com/kson-org/kson</a>
Show HN: 47jobs – A Fiverr/Upwork for AI Agents
Hi HN,<p>I’ve been working on something I’d love to share: 47jobs (<a href="https://47jobs.com" rel="nofollow">https://47jobs.com</a>
) – a marketplace where you can hire AI agents to do tasks instead of human freelancers.<p>Why?
I kept noticing that many tasks on Upwork/Fiverr—coding, content generation, data analysis, automation—can now be handled by AI in minutes, not hours. But there wasn’t a platform built around hiring AI directly.<p>So I built 47jobs:<p>100% AI agents doing the work (no humans in the loop).<p>Jobs get delivered 10x faster, at transparent prices.<p>You can “hire” an agent for coding, automation, research, etc.<p>I’d love your thoughts:<p>Does a pure AI-agent marketplace make sense?<p>What types of jobs would you want AI agents to handle first?<p>Any UX or trust issues you’d expect with this model?<p>This is an early version, and I’m here to learn from your feedback.
Thanks!
Show HN: 47jobs – A Fiverr/Upwork for AI Agents
Hi HN,<p>I’ve been working on something I’d love to share: 47jobs (<a href="https://47jobs.com" rel="nofollow">https://47jobs.com</a>
) – a marketplace where you can hire AI agents to do tasks instead of human freelancers.<p>Why?
I kept noticing that many tasks on Upwork/Fiverr—coding, content generation, data analysis, automation—can now be handled by AI in minutes, not hours. But there wasn’t a platform built around hiring AI directly.<p>So I built 47jobs:<p>100% AI agents doing the work (no humans in the loop).<p>Jobs get delivered 10x faster, at transparent prices.<p>You can “hire” an agent for coding, automation, research, etc.<p>I’d love your thoughts:<p>Does a pure AI-agent marketplace make sense?<p>What types of jobs would you want AI agents to handle first?<p>Any UX or trust issues you’d expect with this model?<p>This is an early version, and I’m here to learn from your feedback.
Thanks!