Show HN: Context7 – LLM Code Snippets from Docs in Minutes https://ift.tt/d0qfuMA

Show HN: Context7 – LLM Code Snippets from Docs in Minutes https://context7.com/ March 28, 2025 at 11:00PM

Show HN: A FlashAttention backwards-over-backwards pass https://ift.tt/nxh6LSU

Show HN: A FlashAttention backwards-over-backwards pass https://ift.tt/X0GWNZp March 29, 2025 at 12:43AM

Show HN: Hexi, modern header-only network binary serialisation for C++ hackers https://ift.tt/L7KbyTE

Show HN: Hexi, modern header-only network binary serialisation for C++ hackers Over the last few years, I've needed an easy way to quickly serialise and deserialise various network protocols safely and efficiently. Most of the libraries that existed at the time were either quite heavy, had less than stellar performance, or were an abstraction level above what I was looking for. I decided to put together my own class to do the job, starting with an easy, low-overhead way to move bytes in and out of arbitrary buffers. Along the way, it picked up useful bits and pieces, such as buffer structures and allocators that made the byte shuffling faster, often being able to do it with zero allocations and zero copies. Safety features came along to make sure that malicious packet data or mistakes in the code wouldn't result in segfaults or vulnerabilities. It's become useful enough to me that I've packaged it up in its own standalone library on the chance that it might be useful to others. It has zero dependencies other than the standard library and has been designed for quick integration into any project within minutes, or seconds with a copy paste of the amalgamated header. It can be used in production code but it's also ideal for for those that want to quickly hack away at binary data with minimal fuss. https://ift.tt/z6aRG3g March 28, 2025 at 11:07PM

Show HN: FancyLock – Linux screenlock with videos. Wayland support coming soon https://ift.tt/latgx1V

Show HN: FancyLock – Linux screenlock with videos. Wayland support coming soon I've been wanting a fancy screen locker for linux, so I built FancyLock, a screen lock solution for Linux with X11 (and soon wayland) support. Key Features - Dynamic media playback during lock screen - Multi-monitor support - PAM-based authentication - Intelligent idle timeout - Highly configurable FancyLock aims to solve several pain points with existing screen lockers: - Boring, static lock screens - Poor multi-monitor support Technical Highlights - Written in Go - Uses X11 extensions for low-level window and input management - Flexible media playback with mpv - Configurable via JSON Current version is v0.0.1 and supports X11. Wayland support is planned. GitHub: https://ift.tt/QHgoRPf Would love to hear your thoughts and feedback! Edit: Happy to answer any questions about the implementation or design choices. https://ift.tt/QHgoRPf March 28, 2025 at 03:03AM

Show HN: My tiny web shell on my local PC https://ift.tt/s3FB9fa

Show HN: My tiny web shell on my local PC https://ift.tt/Nepd4Zs March 28, 2025 at 01:34AM

Show HN: Xorq – open-source Python-first Pandas-style pipelines https://ift.tt/o1PW3Rz

Show HN: Xorq – open-source Python-first Pandas-style pipelines Hi HN, Dan, Hussain and Daniel here… After years of struggling with data pipelines that worked in notebooks but failed in production, we decided to do something about it. We created xorq to eliminate the constant headaches of SQL/pandas impedance mismatch, runtime debugging, wasteful recomputations and unreliable research-to-production deployments that plague traditional pandas-style pipeline workflows. xorq is built on Ibis and DataFusion. We’d love your feedback and contributions. xorq is [Apache 2.0 licensed]( https://ift.tt/1AJrRNS ) to encourage open collaboration. Repo : https://ift.tt/ZTY5gEh Docs : https://docs.xorq.dev Roadmap Issues : https://ift.tt/ZTY5gEh You can get started `pip install xorq`. Or, if you use nix, you can simply run `nix run github:xorq-labs/xorq` and drop into an IPython shell. Demo video: https://youtu.be/jUk8vrR6bCw Here are some vignettes to look into next: 1. MCP Server + Flight + XGBoost: https://ift.tt/1g9DCvZ 2. 1 DuckDB + 2 Writers + 1 Reader: https://ift.tt/y3B2DeK 3. OpenAI UDF: https://ift.tt/ZYJMBAC Some features to note: - Ibis-based multi-engine expression system: effortless engine-to-engine streaming - Cache expressions with `.cache` operator - Portable DataFusion-backed UDF engine with first class support for pandas dataframes - Serialize Expressions to and from YAML - Easily build Flight end-points by composing UDFs thanks for checking this out, and we’re here to answer any questions! https://ift.tt/t1Ya7SK March 27, 2025 at 10:57PM

Show HN: Taildrops – Free Tailwind CSS 4 code snippets https://ift.tt/w4MJ1OF

Show HN: Taildrops – Free Tailwind CSS 4 code snippets Free Tailwind CSS 4 Components — and this is just the beginning! I’ve been sharing a bunch of free Tailwind CSS components on X, but honestly, they just keep getting buried in the timeline. It’s super frustrating when something you put effort into disappears so quickly. That’s why I decided to put everything on a website. Now you can easily find all the components I’ve shared in one place, and I’ll keep adding any new ones I create. It feels good to have a space where they won’t get lost. Check them out if you’re interested — I’d love to hear what you think! https://taildrops.com/ March 27, 2025 at 02:59AM

Show HN: I made a browser tab management tool called TabTab https://ift.tt/DKBmE1t

Show HN: I made a browser tab management tool called TabTab https://www.tabtab.xyz March 27, 2025 at 07:20AM

Show HN: Prompteus – Visual workflow builder for shipping better AI features https://ift.tt/A2LrSYX

Show HN: Prompteus – Visual workflow builder for shipping better AI features We built Prompteus to help devs build and manage AI features without the mess — no more prompt spaghetti or scattered "hardcoded" AI API calls. Design workflows visually, deploy as APIs, and get built-in caching, logging, rate limits, and model orchestration (OpenAI, Anthropic, Mistral, etc.). It’s like Zapier for LLMs — but dev-friendly. Free up to 50k requests/month. https://prompteus.com March 26, 2025 at 11:20PM

Show HN: I built a chatbot that lets you talk to any GitHub repository https://ift.tt/hQJKjkP

Show HN: I built a chatbot that lets you talk to any GitHub repository https://ift.tt/THLB7JV March 26, 2025 at 12:43AM

Show HN: Fingernotes – handwritten notes which become their own preview image https://ift.tt/gRQnsIT

Show HN: Fingernotes – handwritten notes which become their own preview image Hi HN, I've lurked here for ages and decided to come out of the shadows for my latest side project which reached the point where it’s sort of fun to use and hopefully not totally embarrassing to share. Hacking fingernotes.com together over a couple of weeks was a creative outlet when work got stressful. I think of it as digital sticky notes. The goal was to make notes with a personal touch that are easy to write and share. I also wanted them to appear as their own link preview image on supported platforms. That way when you send the link to a note, the person sees the message without following the link. Let me know what you think! I drew inspiration from Apple's quick notes: low latency made scribbling a pleasure, and sending notes to friends felt warm and original compared to a typical exchange. It was also intriguing to see my handwriting printed in a message chat. In a time of rising artificial generation, spreading my clumsy handwriting feels like an act of rebellion. But I dislike the light background in Apple notes, which I don't think you can change when sharing. More importantly, no one sent a note back. With fingernotes the low-friction interaction is meant to make creating notes simple. I also find the image previews aesthetically more pleasing. For implementation, fingernotes are publicly accessible links to collections of strokes that have been persisted to a Cloudflare D1 database and rendered in SVG. Like pen on a sticky note, each stroke is immutable but anyone can add to a note if they have the link. You can't undo strokes, so if you mess up your note just throw it out and start a new one. Having append-only collections avoids handling order of operations when multiple people edit the same note. Hosting it as a Cloudflare worker made it easy to get up and running. There's some latency in Safari on iOS which is absent on desktop. It's noticeable compared to Apple notes and I'm afraid it's a limitation of the browser. https://ift.tt/q30spOH March 23, 2025 at 12:02PM

Show HN: X DMs suck so we built a better one https://ift.tt/yWXSRkv

Show HN: X DMs suck so we built a better one https://tweetdm.com/crm March 24, 2025 at 11:52PM

Show HN: Prefix any URL with `pure.md/` to get unblocked Markdown https://ift.tt/zvEWVRM

Show HN: Prefix any URL with `pure.md/` to get unblocked Markdown https://pure.md March 24, 2025 at 10:06PM

Show HN: XYMake – Turn Your Posts into LLM-Ready Data https://ift.tt/jfpohUW

Show HN: XYMake – Turn Your Posts into LLM-Ready Data I just built XYMake ( https://xymake.com ), a tool that lets you convert any X (Twitter) thread into clean markdown, making your conversations accessible for LLMs, MCPs, or any API. ## What it does: - Transforms any X thread URL into markdown by simply changing "x.com" to "xymake.com" in the URL - OAuth2 login to "free your data" and make your threads available - Auto-generates OG images with token counts and participant info for easy sharing - Serves different content types based on whether the request is from a crawler, browser, or agent ## Why I built it: I believe people should have the right to own and use their own data. While X/Twitter uses our content to train Grok, we should be able to leverage our own conversations for similar purposes. I built this as a proof of concept in one day (what started as a 30-minute experiment turned into a 10-hour flow state). It's built entirely on Cloudflare Workers and uses some interesting techniques to serve different content types to different consumers. ## Technical highlights: - Request identification to serve HTML+OG images to crawlers while providing raw markdown to agents - Preloading OG image generation using ctx.waitUntil for near-instant loading when shared - Optimized OG image rendering across platforms using workers-og Try it out with any X thread - just replace "x.com" with "xymake.com"! Example: https://ift.tt/S7A4Kvj Feedback welcome! This is just the beginning of what's possible when we reclaim our conversational data. https://xymake.com March 25, 2025 at 12:32AM

Show HN: Tascli, a simple CLI task and record manager https://ift.tt/qWJhE76

Show HN: Tascli, a simple CLI task and record manager https://ift.tt/U8efh7T March 25, 2025 at 12:02AM

Show HN: Search and chat with millions of court cases using AI. https://ift.tt/MoLj9QS

Show HN: Search and chat with millions of court cases using AI. https://ift.tt/YyrU9jt March 24, 2025 at 12:51AM

Show HN: Cocommit – A copilot for git commit https://ift.tt/yZXC28u

Show HN: Cocommit – A copilot for git commit I've built a lightweight copilot that integrates with Git commits, leveraging LangChain to support multiple LLM providers. I currently use it with Claude 3.7 (via Bedrock) and OpenAI’s GPT-4o, but I’d love to see how it performs with other LLMs. If you have access to any LangChain-supported LLMs, I’d really appreciate a quick test! Your feedback via GitHub Issues would be invaluable in improving the project. Thanks in advance! https://ift.tt/bxDzohu March 23, 2025 at 11:46PM

Show HN: DAPS – Prime-Adaptive Search for Discontinuous Optimization Problems https://ift.tt/KLqZpz2

Show HN: DAPS – Prime-Adaptive Search for Discontinuous Optimization Problems I've been working on a global optimization algorithm that uses prime number-based adaptive grid search. It dynamically adjusts resolution by increasing or decreasing prime numbers as "resolution knobs" — allowing it to handle discontinuities, sharp valleys, and chaotic landscapes better than naive grid search. The repo includes Python and PyTorch-compatible versions, benchmarks against grid search, and a research paper. Would love feedback from optimization, ML, or numerical analysis folks. Curious if anyone sees potential applications or improvements. GitHub: https://ift.tt/TNvy8bD Paper: https://ift.tt/v45D91e.... https://ift.tt/TNvy8bD March 23, 2025 at 11:19AM

Show HN: I build a tool that will tell you what to respond in negotations https://ift.tt/ScHALrB

Show HN: I build a tool that will tell you what to respond in negotations After reading the book Getting to Yes, I really want some tool to help me negotiate more efficiently without having to memorize everything principle. You start by putting in interests of each party, then you can explore different functions: how to respond to the other party, explore objective criteria out there or brainstorm more negotiation options. Still working on it! Leave me feedback if you have any suggestions! https://ift.tt/v8BxFsS March 23, 2025 at 03:31AM

Show HN: I Made a Language to Be JavaScript's Nanny https://ift.tt/1Bhgvom

Show HN: I Made a Language to Be JavaScript's Nanny I'm working on a language called Chicory. It's yet-another compiles to JS(X) language. I'd value any feedback. See also https://ift.tt/jDZlvrm https://ift.tt/HncbE3x March 23, 2025 at 01:39AM