Show HN: A Prompt-Injection Firewall for AI Agents and RAG Pipelines https://ift.tt/Uwo4b9N

Show HN: A Prompt-Injection Firewall for AI Agents and RAG Pipelines We built SafeBrowse — an open-source prompt-injection firewall for AI systems. Instead of relying on better prompts, SafeBrowse enforces a hard security boundary between untrusted web content and LLMs. It blocks hidden instructions, policy violations, and poisoned data before the AI ever sees it. Features: • Prompt injection detection (50+ patterns) • Policy engine (login/payment blocking) • Fail-closed by design • Audit logs & request IDs • Python SDK (sync + async) • RAG sanitization PyPI: pip install safebrowse Looking for feedback from AI infra, security, and agent builders. January 1, 2026 at 02:31AM

Show HN: A web-based lighting controller built because my old became a brick https://ift.tt/Yk5CMqf

Show HN: A web-based lighting controller built because my old became a brick I’m a student and I built this because my old lightning controller (DMX) became a brick after the vendor’s control software was deprecated in 2025. My focus was entirely on developing a robust backend architecture to guarantee maximum performance. Everything is released under GPLv3. The current frontend is just a "vibecoded" dashboard made with plain HTML and JavaScript to keep rendering latency as low as possible. In earlier versions Svelte was used. Svelte added too much complexity for an initial mvp. Video: https://ift.tt/w7dgpVs Repo: https://ift.tt/FIrgh1j Technical Details: The system uses a distributed architecture where a FastAPI server manages the state in a Redis. State changes are pushed via WebSockets to Raspberry Pi gateways, which then independently maintain the constant 44Hz binary stream to the lights. This "push model" saves massive amounts of bandwidth and ensures low latency. In a stress test, I processed 10 universes (5,120 channels) at 44Hz with zero packet loss (simulated). An OTP-based pairing makes the setup extremely simple (plug-and-play). I’m looking forward to your feedback on the architecture and the Redis approach! Happy New Year! https://ift.tt/FIrgh1j December 31, 2025 at 10:16PM

Show HN: Fleet / Event manager for Star Citizen MMO https://ift.tt/AGgqduZ

Show HN: Fleet / Event manager for Star Citizen MMO I built an open-source org management platform for Star Citizen, a space MMO where player orgs can have 50K+ members managing fleets worth millions. https://scorg.org The problem: SC's official tools won't launch until 2026, but players need to coordinate now - track 100+ ship fleets, schedule ops across timezones, manage alliances, and monitor voice activity during battles. Interesting challenges solved: 1. Multi-org data isolation - Users join multiple orgs, so every query needs scoping. 2. Canvas + Firebase Storage CORS - Couldn't export fleet layouts as PNG. Solution: fetch images as blobs, convert to base64 data URLs, then draw to canvas. No CORS config needed. 3. Discord bot - Built 4 microservices (VoiceActivityTracker, EventNotifier, ChannelManager, RoleSync) sharing Firebase state. Auto-creates channels for ops, cleans up when done. Features: role-based access, event calendar with RSVP, LFG matchmaking, drag-and-drop fleet builder, economy tools, alliance system, analytics dashboard, mobile-responsive. ~15 pages, fully functional. Custom military-inspired UI (monospace, gold accents). January 1, 2026 at 12:48AM

Show HN: Claude Cognitive – Working memory for Claude Code https://ift.tt/TfsdCY4

Show HN: Claude Cognitive – Working memory for Claude Code https://ift.tt/MBfUPm6 December 31, 2025 at 03:57AM

Show HN: Slide notes visible only to you during screen sharing https://ift.tt/uDLhYbw

Show HN: Slide notes visible only to you during screen sharing https://cuecard.dev December 30, 2025 at 11:48PM

Show HN: Replacing my OS process scheduler with an LLM https://ift.tt/8fpO7nD

Show HN: Replacing my OS process scheduler with an LLM https://ift.tt/w5jWSc0 December 30, 2025 at 10:17PM

Show HN: Aroma: Every TCP Proxy Is Detectable with RTT Fingerprinting https://ift.tt/IHaXDBv

Show HN: Aroma: Every TCP Proxy Is Detectable with RTT Fingerprinting TL;DR explanation (go to https://ift.tt/iIlpQJc... if you want the formatted version) This is done by measuring the minimum TCP RTT (client.socket.tcpi_min_rtt) seen and the smoothed TCP RTT (client.socket.tcpi_rtt). I am getting this data by using Fastly Custom VCL, they get this data from the Linux kernel (struct tcp_info -> tcpi_min_rtt and tcpi_rtt). I am using Fastly for the Demo since they have PoPs all around the world and they expose TCP socket data to me. The score is calculated by doing tcpi_min_rtt/tcpi_rtt. It's simple but it's what worked best for this with the data Fastly gives me. Based on my testing, 1-0.7 is normal, 0.7-0.3 is normal if the connection is somewhat unstable (WiFi, mobile data, satellite...), 0.3-0.1 is low and may be a proxy, anything lower than 0.1 is flagged as TCP proxy by the current code. https://ift.tt/HcNsPVl December 26, 2025 at 02:04AM

Show HN: A solar system simulation in the browser https://ift.tt/qxfW7eu

Show HN: A solar system simulation in the browser I didn't realize Universe Sandbox ran on MacOS, and I was in the mood to play around a bit. Some functions it's got: - Random system generation - Sonification is super fun too - Habitability Simulation (Just for fun, don't cite this please) - Replacing, spawning, deleting objects I've had tons of fun building this, so I hope someone else can share the joy. It's free and runs in the browser. I'd love to hear any feedback. I think this is at a state where I might leave it as it is, but if people are interested in other features, maybe I'll keep working on it. I've kept saying I'll stop working on this for a while now though. https://ift.tt/tiSewbz December 29, 2025 at 11:04PM

Show HN: Pion SCTP with RACK is 70% faster with 30% less latency https://ift.tt/AWOqGHm

Show HN: Pion SCTP with RACK is 70% faster with 30% less latency SCTP is a low level protocol focused on reliable packet transmission. Unlike hopelessly flinging packets from one device to another, it makes sure that the packets are correct using CRC, removes duplicate packets, and allows for packets to be sent in any order. Going into an established library, I thought that everything was already implemented and that there wasn't anything to do until I went through the existing issues and organized all the tasks and decided on an order. Sean DuBois ( https://ift.tt/bwz9Pt8 ), one of the co-creators and current maintainers of Pion, an open-source pure Go implementation of WebRTC (which uses SCTP), introduced me to a dissertation that was written about improving SCTP from 2021 ( https://ift.tt/vFrXkuq... ). To my surprise, the features in it weren't actually implemented yet, and generally went unused even though it depicted pretty big improvements. This came as a bit of a shock to me considering the countless companies and services that actively use Pion with millions of users on a daily basis. This led to two things: 1) implement the feature (done by me) and 2) measure the performance (done by Joe Turki https://ift.tt/AvWBu5z ). If you're interested in reading more, please check out the blog post where we go over what SCTP is used for, how I improved it, and the effort that went into making such a large improvement possible. This also marks a huge milestone for other companies and services that use SCTP as they can refer to the implementation in Pion for their own SCTP libraries including any real-time streaming platforms such as Microsoft Teams, Discord screen share, Twitch guest star, and many more! For my personal background, please take a look at a comment below about what it was like for me to get started with open-source and my career related journeys. Thanks for reading! https://ift.tt/1zXIYsP December 28, 2025 at 11:35PM

Show HN: AI 3D Model Generator https://ift.tt/nUq6vck

Show HN: AI 3D Model Generator https://ift.tt/hUC10sV December 28, 2025 at 11:21PM

Show HN: I'm 15. I built an offline AI Terminal Agent that fixes errors https://ift.tt/dXAmOnf

Show HN: I'm 15. I built an offline AI Terminal Agent that fixes errors https://ift.tt/VHnetGl December 27, 2025 at 10:27PM

Show HN: Jsonic – Python JSON serialization that works https://ift.tt/LsTDb5y

Show HN: Jsonic – Python JSON serialization that works https://ift.tt/Oy3eqB5 December 27, 2025 at 07:26PM

Show HN: AgentFuse – A local circuit breaker to prevent $500 OpenAI bills https://ift.tt/Z4B5uo6

Show HN: AgentFuse – A local circuit breaker to prevent $500 OpenAI bills Hey HN, I’ve been building agents recently, and I hit a problem: I fell asleep while a script was running, and my agent got stuck in a loop. I woke up to a drained OpenAI credit balance. I looked for a tool to prevent this, but most solutions were heavy enterprise proxies or cloud dashboards. I just wanted a simple "fuse" that runs on my laptop and stops the bleeding before it hits the API. So I built AgentFuse. It is a lightweight, local library that acts as a circuit breaker for LLM calls. Drop-in Shim: It wraps the openai client (and supports LangChain) so you don't have to rewrite your agent logic. Local State: It uses SQLite in WAL mode to track spend across multiple concurrent agents/terminal tabs. Hard Limits: It enforces a daily budget (e.g., stops execution at $5.00). It’s open source and available on PyPI (pip install agent-fuse). I’d love feedback on the implementation, specifically the SQLite concurrency logic! I tried to make it as robust as possible without needing a separate server process. https://ift.tt/3p4X1bt December 28, 2025 at 12:46AM

Show HN: Polibench – compare political bias across AI models https://ift.tt/ZS3Hj90

Show HN: Polibench – compare political bias across AI models Polibench runs the Political Compass questions across AI models so you can compare responses side by side. No signup. Built on top of work by @theo ( https://twitter.com/theo ) and @HolyCoward ( https://twitter.com/HolyCoward ). Question set is based on the Political Compass: https://ift.tt/Z9n5Rqy Early and rough. Feedback welcome on revealing questions, possible misuse, and ideas for extending it. Happy to answer questions. https://polibench.vercel.app/ December 27, 2025 at 12:23AM

Show HN: Web CLI – Browser-based terminal with multi-tab support https://ift.tt/zMtb95G

Show HN: Web CLI – Browser-based terminal with multi-tab support Hey HN! Web CLI, an open-source web-based command management tool just got an upgrade with Interactive Terminal support https://ift.tt/sWDEvim December 26, 2025 at 09:53PM

Show HN: Pivor, Open source self-hosted CRM https://ift.tt/oXdvQOh

Show HN: Pivor, Open source self-hosted CRM I built Pivor because I wanted a simple, self-hosted CRM without cloud lock-in or per-seat pricing. Features: Clients, Contacts, Communications tracking (emails, calls, meetings, tasks), dark mode. Stack: Laravel 12, Livewire 3, Tailwind CSS 4. Runs on SQLite by default, supports MySQL/PostgreSQL. Docker ready. AGPL-3.0 licensed. https://ift.tt/JmxPiEk Looking for feedback! https://ift.tt/JmxPiEk December 26, 2025 at 12:57AM

Show HN: I created a tool to generate handwritten signatures https://ift.tt/01SFPIk

Show HN: I created a tool to generate handwritten signatures At this time, I had to sign multiple documents (energy, gas, water, etc) for our new house. I'm using a Mac, and I have the option to create my own sign and reuse it multiple times, making it easy for me. I'm also exploring vibe coding, so I decided to try building a small web app to generate handwritten signatures, allowing me to have a cool-looking signature and for others to use it if they want. You can generate multiple signatures and only pay if you want to download your 7-signature pack. I decided to let the users pay for it (only $3), not to become rich obviously :D, but to maybe cover some operational costs, like the VPS and the domain. Since this is my first vibe-coded project, I'm also open to receiving feedback, so I can give some directions to my "virtual employee" :D Thanks in advance! https://signcraft.pro/ December 25, 2025 at 11:06PM

Show HN: Elfpeek – A tiny interactive ELF binary inspector in C https://ift.tt/fyl1kTo

Show HN: Elfpeek – A tiny interactive ELF binary inspector in C https://ift.tt/bBZv9jD December 24, 2025 at 11:08PM

Show HN: An open-source anonymizer tool to replace PII in PostgreSQL databases https://ift.tt/c8OtpDu

Show HN: An open-source anonymizer tool to replace PII in PostgreSQL databases https://ift.tt/PiHObZD December 24, 2025 at 09:45PM

Show HN: Full-text search engine for Epstein docs (OCR and OpenSearch) https://ift.tt/NEIwSLP

Show HN: Full-text search engine for Epstein docs (OCR and OpenSearch) Hi HN, Like many people, I was frustrated that the released Epstein/Maxwell court documents were mostly scanned images (PDFs) with no text layer. This made them impossible to Ctrl+F or analyze programmatically. I built a pipeline to fix this using Python, Tesseract, and OpenSearch. The Site: https://ift.tt/Uk38wWL The Stack: Ingestion: Python workers using ocrmypdf (Tesseract) to perform parallel OCR on raw files. Search: OpenSearch for indexing the extracted text. Frontend: Next.js (SSR) for the UI. Infrastructure: Self-hosted Docker swarm. Features: Sub-second full-text search across all files. Highlights search terms directly on the PDF page. Deep linking to specific pages/documents. This is a transparency tool, not a political one. I wanted to make the raw primary sources accessible to researchers and journalists. Feedback on the search relevance or indexing pipeline is welcome! December 24, 2025 at 01:27AM

Show HN: Openinary – Self-hosted image processing like Cloudinary https://ift.tt/bHwTrQL

Show HN: Openinary – Self-hosted image processing like Cloudinary Hi HN! I built Openinary because Cloudinary and Uploadcare lock your images and charge per request. Openinary lets you self-host a full image pipeline: transform, optimize, and cache images on your infra; S3, Cloudflare R2, or any S3-compatible storage. It’s the only self-hosted Cloudinary-like tool handling both transformations and delivery with a simple URL API (/t/w_800,h_800,f_avif/sample.jpg). Built with Node.js, Docker-ready. GitHub: https://ift.tt/7gpYukI Feedback welcome; especially from Cloudinary users wanting the same UX but on their own infra! https://ift.tt/7gpYukI December 23, 2025 at 09:31PM

Show HN: A kids book that introduces authorization and permissions concepts https://ift.tt/HItTaLG

Show HN: A kids book that introduces authorization and permissions concepts A colleague and I made a kids' picture book that introduces authorization concepts. We work at AuthZed and explain these concepts regularly. We thought it'd be fun to put them together in a format accessible and appealing to kids and grownups alike. It would also be helpful when explaining what we do for work and make a unique gift for our families. The goal was a fun story first and foremost. We aimed to present concepts accessibly but made conscious decisions to simplify, knowing we couldn't be comprehensive in a picture book format. We also wanted visually appealing illustrations, so we built a custom tool to streamline exploring ideas with AI. It does reference-weighted image generation (upload references, weight which ones matter most), git-like branching for asset organization, and feedback loops that improve subsequent generations. It was built with Claude Code. Here's a screenshot: https://ift.tt/vS72Dsg... We'd love feedback on where we chose to simplify. Did we get the tradeoffs right or did we oversimplify? And lastly, did you enjoy the story? You can read the book online: https://ift.tt/cEmtxXV https://ift.tt/cEmtxXV December 24, 2025 at 12:06AM

Show HN: Meds — High-performance firewall powered by NFQUEUE and Go https://ift.tt/WugtnQH

Show HN: Meds — High-performance firewall powered by NFQUEUE and Go Hi HN, I'm the author of Meds ( https://ift.tt/gUy7YMo ). Meds is a user-space firewall for Linux that uses NFQUEUE to inspect and filter traffic. In the latest v0.7.0 release, I’ve added ASN-based filtering using the Spamhaus DROP list (with IP-to-ASN mapping via IPLocate.io). Key highlights: Zero-lock core, ASN Filtering, Optimized Rate Limiting, TLS Inspection, Built-in Prometheus metrics and Swagger API. Any feedback is very welcome! https://ift.tt/gUy7YMo December 22, 2025 at 10:58PM

Show HN: Real-time SF 911 dispatch feed (open source) https://ift.tt/hz5D4pV

Show HN: Real-time SF 911 dispatch feed (open source) I built an open-source alternative to Citizen App's paid 911 feed for San Francisco. It streams live dispatch data from SF's official open data portal, uses an LLM to translate police codes into readable summaries, and auto-redacts sensitive locations (shelters, hospitals, etc.). Built it at a hack night after getting annoyed that Citizen is the only real-time option and they paywall it. Repo: https://ift.tt/ocCUsHG Discord: https://ift.tt/3VMSmtL Happy to discuss the technical approach or take feedback. https://ift.tt/GVxvRi4 December 22, 2025 at 06:29AM

Show HN: Mactop v2.0.0 https://ift.tt/F79sJVC

Show HN: Mactop v2.0.0 https://ift.tt/FYMeNxS December 22, 2025 at 06:14AM

Show HN: Pac-Man with Guns https://ift.tt/2gfTUHv

Show HN: Pac-Man with Guns Title really says it all on this https://pac-man-with-guns.netlify.app/ December 22, 2025 at 04:47AM

Show HN: I built a 1‑dollar feedback tool as a Sunday side project https://ift.tt/vrSeu8G

Show HN: I built a 1‑dollar feedback tool as a Sunday side project I’ve always found it funny how simple feedback widgets end up as $20–$30/month products. The tech is dead simple, infra is cheap, and most of us here could rebuild one in a weekend. So as a “principle experiment” I built my own today as a side project and priced it at 1 dollar. Just because if something is cheap to run and easy to replicate, it should be priced accordingly, and it’s also fun marketing. 1$ feedback tool. Shipped today, got the first users/moneys today, writing this post today. Side Sunday project, then back to the main product tomorrow. https://ift.tt/PhjGvuz December 22, 2025 at 03:22AM

Show HN: HN Wrapped 2025 - an LLM reviews your year on HN https://ift.tt/RanOutd

Show HN: HN Wrapped 2025 - an LLM reviews your year on HN I was looking for some fun project to play around with the latest Gemini models and ended up building this :) Enter your username and get: - Generated roasts and stats based on your HN activity 2025 - Your personalized HN front page from 2035 (inspired by a recent Show HN [0]) - An xkcd-style comic of your HN persona It uses the latest gemini-3-flash and gemini-3-pro-image (nano banana pro) models, which deliver pretty impressive and funny results. Give it a try and let me know what you think :) [0] https://ift.tt/oxtWj6T https://ift.tt/rJdNUuL December 20, 2025 at 07:09PM

Show HN: Music player for big local collections with mpd support https://ift.tt/gRcqW7l

Show HN: Music player for big local collections with mpd support mpz is a C++/Qt music player focused on UX, with derectory tree and playlists management. Version 2 got experimental https://musicpd.org support. https://ift.tt/Cw4l0MK December 20, 2025 at 02:25AM

Show HN: MCPShark Viewer (VS Code/Cursor extension)- view MCP traffic in-editor https://ift.tt/vwpdzic

Show HN: MCPShark Viewer (VS Code/Cursor extension)- view MCP traffic in-editor A few days ago I posted MCPShark (a traffic inspector for the Model Context Protocol). I just shipped a VS Code / Cursor extension that lets you view MCP traffic directly in the editor, so you’re not jumping between terminals, logs, and "I think this is what got sent". VS Code Marketplace: https://marketplace.visualstudio.com/items?itemName=MCPShark... Main repo: https://ift.tt/FRTnVZQ Feature requests / issues: https://ift.tt/IWP7ehK Site: https://mcpshark.sh/ If you’re building MCP agents/tools: what would make MCP debugging actually easy—timeline view, session grouping, diffing tool args, exporting traces, something else? I’d be thankful if you could open a feature request here: https://ift.tt/IWP7ehK December 17, 2025 at 11:49PM

Show HN: Stickerbox, a kid-safe, AI-powered voice to sticker printer https://ift.tt/bo1jR6F

Show HN: Stickerbox, a kid-safe, AI-powered voice to sticker printer Bob and Arun here, creators of Stickerbox. If AI were built for kids, what would it look like? Asking that question led us to creativity, and more specifically, the power of kids’ imaginations. We wanted to let kids combine the power of their ideas with AI tools but we needed to make sure we did it safely and in the right way. Enter Stickerbox, a voice powered sticker printer. By combining AI image generation with thermal sticker printing, we instantly turn kids' wildest ideas into real stickers they can color, stick, and share. What surprised us most is how the “AI” disappears behind the magic of the device. The moment that consistently amazes kids is when the printer finishes and they are holding their own idea as a real sticker. A ghost on a skateboard, a dragon doing its taxes, their dog as a superhero, anything they can dream of, they can hold in their hand. Their reactions are what pushed us to keep building, even though hardware can be really hard. Along the way the scope of the project grew more than we expected: navigating supply chains, sourcing safe BPA/BPS free thermal paper, passing safety testing for a children’s product, and designing an interface simple enough that a five year old can walk up and just talk to it. We also spent a lot of time thinking about kids’ data and privacy so that parents would feel comfortable having this in their home. Stickerbox is our attempt to make modern AI kid-safe, playful, and tangible. We’d love to hear what you think! P.S. If you’re interested in buying one for yourself or as a gift, use code FREE3PACK to get an extra free pack of paper refills. https://stickerbox.com/ December 20, 2025 at 01:14AM

Show HN: Linggen – A local-first memory layer for your AI (Cursor, Zed, Claude) https://ift.tt/YNAeqvr

Show HN: Linggen – A local-first memory layer for your AI (Cursor, Zed, Claude) Hi HN, Working with multiple projects, I got tired of re-explaining our complex multi-node system to LLMs. Documentation helped, but plain text is hard to search without indexing and doesn't work across projects. I built Linggen to solve this. My Workflow: I use the Linggen VS Code extension to "init my day." It calls the Linggen MCP to load memory instantly. Linggen indexes all my docs like it’s remembering them—it is awesome. One click loads the full architectural context, removing the "cold start" problem. The Tech: Local-First: Rust + LanceDB. Code and embeddings stay on your machine. No accounts required. Team Memory: Index knowledge so teammates' LLMs get context automatically. Visual Map: See file dependencies and refactor "blast radius." MCP-Native: Supports Cursor, Zed, and Claude Desktop. Linggen saves me hours. I’d love to hear how you manage complex system context! Repo: https://ift.tt/VoxNiQF Website: https://linggen.dev https://ift.tt/VoxNiQF December 19, 2025 at 11:24PM

Show HN: TinyPDF – 3KB PDF library (70x smaller than jsPDF) https://ift.tt/TuK7LC0

Show HN: TinyPDF – 3KB PDF library (70x smaller than jsPDF) I needed to generate invoices in a Node.js app. jsPDF is 229KB. I only needed text, rectangles, lines, and JPEG images. So I wrote tinypdf: <400 lines of TypeScript, zero dependencies, 3.3KB minified+gzipped. What it does: - Text (Helvetica, colors, alignment) - Rectangles and lines - JPEG images - Multiple pages, custom sizes What it doesn't do: - Custom fonts, PNG/SVG, forms, encryption, HTML-to-PDF That's it. The 95% use case for invoices, receipts, reports, tickets, and labels. GitHub: https://github.com/Lulzx/tinypdf npm: npm install tinypdf https://github.com/Lulzx/tinypdf December 19, 2025 at 12:29AM

Show HN: Explore Prometheus /metrics endpoints from your terminal https://ift.tt/tjzTVwb

Show HN: Explore Prometheus /metrics endpoints from your terminal https://ift.tt/a1obXJW December 18, 2025 at 11:40PM

Show HN: The feature gap "Chat with PDF" tuts and a regulated enterprise system https://ift.tt/5Gp93c4

Show HN: The feature gap "Chat with PDF" tuts and a regulated enterprise system I've spent the last few months architecting a RAG system for a regulated environment. I am not a developer by trade, but I approached this with a strict "systems engineering" and audit mindset. While most tutorials stop at "LangChain + VectorDB", I found that making this legally defensible and operationally stable required about 40+ additional components. We moved from a simple ingestion script to a "Multi-Lane Consensus Engine" (inspired by Six Sigma) because standard OCR/extraction was too hallucination-prone for our use case. We had to build extensive auditing, RBAC down to the document level, and a hybrid Graph+Vector retrieval to get acceptable accuracy The current architecture includes: Ingestion: 4 parallel extraction lanes (Vision, Layout, Text, Legal) with a Consensus Engine ("Solomon") that only indexes data confirmed by multiple sources Retrieval: Hybrid Neo4j (Graph) + ChromaDB (Vector) with Reciprocal Rank Fusion Performance: Semantic Caching (Redis) specifically for similar-meaning queries (40x speedup) Security: Full RBAC, Audit Logging of every prompt/retrieval, and PII masking. I documented the complete feature list and gap analysis https://gist.github.com/2dogsandanerd/2a3d54085b2daaccbb1125... My question to the community: Looking at this list – where is the line between "robust production engineering" and "over-engineering"? For those working in Fintech/Medtech RAG: what critical failure modes am I still missing in this list? https://gist.github.com/2dogsandanerd/2a3d54085b2daaccbb1125601945ceeb December 17, 2025 at 11:20PM

Show HN: Solving the ~95% legislative coverage gap using LLM's https://ift.tt/62x0PSF

Show HN: Solving the ~95% legislative coverage gap using LLM's Hi HN, I'm Jacek, the solo founder behind this project (Lustra). The Problem: 95% of legislation goes unnoticed because raw legal texts are unreadable. Media coverage is optimized for outrage, not insight. The Solution. I built a digital public infrastructure that: 1. Ingests & Sterilizes: Parses raw bills (PDF/XML) from US & PL APIs. Uses LLMs (Vertex AI, temp=0, strict JSON) to strip political spin. 2. Civic Algorithm: The main feed isn't sorted by an editorial board. It's sorted by user votes ("Shadow Parliament"). What the community cares about rises to the top. 3. Civic Projects: An incubator for citizen legislation. Users submit drafts (like our Human Preservation Act ), which are vetted by AI scoring and displayed with visual parity alongside government bills. Tech Stack: Frontend: Flutter (Web & Mobile Monorepo), Backend: Firebase + Google Cloud Run, AI: Vertex AI (Gemini 2.5 Flash), License: PolyForm Noncommercial — source is available for inspection, learning, and non-commercial civic use. Commercial use would require a separate agreement. I am looking for contributors. I have the US and Poland live. EU, UK, FR, DE in pipeline, partially available. I need help building Data Adapters for other parliaments (the core logic is country-agnostic). If you want to help audit the code or add a country, check the repo. The goal is to complete the database as much as possible with current funding. Live App: https://lustra.news Repo: https://ift.tt/M7t4lzf Dev Log: https://ift.tt/o9t6T5U https://lustra.news/ December 16, 2025 at 08:09PM

Show HN: Zenflow – orchestrate coding agents without "you're right" loops https://ift.tt/Fn8z4WY

Show HN: Zenflow – orchestrate coding agents without "you're right" loops Hi HN, I’m Andrew, Founder of Zencoder. While building our IDE extensions and cloud agents, we ran into the same issue many of you likely face when using coding agents in complex repos: agents getting stuck in loops, apologizing, and wasting time. We tried to manage this with scripts, but juggling terminal windows and copy-paste prompting was painful. So we built Zenflow, a free desktop tool to orchestrate AI coding workflows. It handles the things we were missing in standard chat interfaces: Cross-Model Verification: You can have Codex review Claude’s code, or run them in parallel to see which model handles the specific context better. Parallel Execution: Run five different approaches on a backlog item simultaneously—mix "Human-in-the-Loop" for hard problems with "YOLO" runs for simple tasks. Dynamic Workflows: Configured via simple .md files. Agents can actually "rewire" the next steps of the workflow dynamically based on the problem at hand. Project list/kanban views across all workload What we learned building this To tune Zenflow, we ran 100+ experiments across public benchmarks (SWE-Bench-*, T-Bench) and private datasets. Two major takeaways that might interest this community: Benchmark Saturation: Models are becoming progressively overtrained on all versions of SWE-Bench (even Pro). We found public results are diverging significantly from performance on private datasets. If you are building workflows, you can't rely on public benches. The "Goldilocks" Workflow: In autonomous mode, heavy multi-step processes often multiply errors rather than fix them. Massive, complex prompt templates look good on paper but fail in practice. The most reliable setups landed in a narrow “Goldilocks” zone of just enough structure without over-orchestration. The app is free to use and supports Claude Code, Codex, Gemini, and Zencoder. We’ve been dogfooding this heavily, but I'd love to hear your thoughts on the default workflows and if they fit your mental model for agentic coding. Download: https://ift.tt/X5WzNMV YT flyby: https://www.youtube.com/watch?v=67Ai-klT-B8 https://ift.tt/X5WzNMV December 16, 2025 at 10:02PM

Show HN: ModelGuessr: Can you tell which AI you're chatting with? https://ift.tt/YCs29wA

Show HN: ModelGuessr: Can you tell which AI you're chatting with? Hey HN - I built ModelGuessr, a game where you chat with a random AI model and try to guess which one it is. A big open question in AI is whether there's enough brand differentiation for AI companies to capture real profits. Will models end up commoditized like cloud compute, or differentiated like smartphones? I built ModelGuessr to test this. I think that people will struggle more than they expect. And the more model mix-ups there are, the more commodity-like these models probably are. If enough people play, I'll publish some follow-up analyses on confusion patterns (which models get mistaken for each other, what gives them away, etc.). Would love any feedback! https://ift.tt/DzhEb0I December 15, 2025 at 10:29PM

Show HN: A lightweight SaaS to reduce early-stage app friction https://ift.tt/CPFeZ81

Show HN: A lightweight SaaS to reduce early-stage app friction I recently shipped a small SaaS I built in roughly 24 hours, mostly during school breaks. This is my first project that I have taken from idea to deployment, onboarding, and real users. The product targets early-stage developers and focuses on reducing initial setup and preparation when building new apps. It abstracts away some of the repetitive early decisions and boilerplate that tend to slow down first-time builders, especially around project structure, configuration, and “what should exist on day one”. I have a small number of active users, but churn is relatively high, which suggests either: the problem is not painful enough the abstraction leaks too early the UX or onboarding fails to communicate value or the tool solves a problem that disappears after the first session I would really appreciate technical feedback on: whether the abstraction layer makes sense if the mental model aligns with how you bootstrap projects where the product feels opinionated vs restrictive what would make this something you would actually keep installed Thanks for reading. Direct, critical feedback is very welcome. https://simpl-labs.com/ December 16, 2025 at 12:21AM

Show HN: A Wordle-style game for SHA-256 hashes https://ift.tt/k1XLsFn

Show HN: A Wordle-style game for SHA-256 hashes i built a small wordle-style game where the target is a daily sha-256 hash. it’s intentionally not cryptographically realistic; the goal is to make avalanche effects and the meaninglessness of near-matches intuitive. this was a quick front-end experiment; the code isn’t published yet. everything runs client-side; no tracking; no accounts. https://hashle.app December 15, 2025 at 11:38PM

Show HN: 999 Penguins https://ift.tt/EYnP5IG

Show HN: 999 Penguins https://999penguins.com December 14, 2025 at 07:31PM

Show HN: Llmwalk – explore the answer-space of open LLMs https://ift.tt/TowvXrk

Show HN: Llmwalk – explore the answer-space of open LLMs https://ift.tt/A5YumVy December 14, 2025 at 10:14PM

Show HN: Open-source customizable AI voice dictation built on Pipecat https://ift.tt/PIVz51H

Show HN: Open-source customizable AI voice dictation built on Pipecat Tambourine is an open source, fully customizable voice dictation system that lets you control STT/ASR, LLM formatting, and prompts for inserting clean text into any app. I have been building this on the side for a few weeks. What motivated it was wanting a customizable version of Wispr Flow where I could fully control the models, formatting, and behavior of the system, rather than relying on a black box. Tambourine is built directly on top of Pipecat and relies on its modular voice agent framework. The back end is a local Python server that uses Pipecat to stitch together STT and LLM models into a single pipeline. This modularity is what makes it easy to swap providers, experiment with different setups, and maintain fine-grained control over the voice AI. I shared an early version with friends and recently presented it at my local Claude Code meetup. The response was overwhelmingly positive, and I was encouraged to share it more widely. The desktop app is built with Tauri. The front end is written in TypeScript, while the Tauri layer uses Rust to handle low level system integration. This enables the registration of global hotkeys, management of audio devices, and reliable text input at the cursor on both Windows and macOS. At a high level, Tambourine gives you a universal voice interface across your OS. You press a global hotkey, speak, and formatted text is typed directly at your cursor. It works across emails, documents, chat apps, code editors, and terminals. Under the hood, audio is streamed from the TypeScript front end to the Python server via WebRTC. The server runs real-time transcription with a configurable STT provider, then passes the transcript through an LLM that removes filler words, adds punctuation, and applies custom formatting rules and a personal dictionary. STT and LLM providers, as well as prompts, can be switched without restarting the app. The project is still under active development. I am working through edge cases and refining the UX, and there will likely be breaking changes, but most core functionality already works well and has become part of my daily workflow. I would really appreciate feedback, especially from anyone interested in the future of voice as an interface. https://ift.tt/KfiA6qN December 14, 2025 at 09:51PM

Show HN: Tic Tac Flip – A new strategic game based on Tic Tac Toe https://ift.tt/dxEM2cg

Show HN: Tic Tac Flip – A new strategic game based on Tic Tac Toe The biggest problem with Tic-Tac-Toe is that it almost always ends in a draw. Tic Tac Flip tries to fix that! Learn the rules in Learning Mode or below: - Winning Criteria: 3 Ghosts (Flipped O or X, which can be a mixture). It's not just 3 Os or 3 Xs anymore! - Flipping Mechanic: When one or more lines having only O and X are formed, the minority of either all Os or all Xs get flipped to a Ghost, and the majority gets removed from the board. E.g., A line of 2 Os and 1 X leads to 1 X ghost and the removal of 2 Os. - Active Flip: You can actively flip your O/X to a Ghost (or flip a ghost back) once per game. - Placing Ghost Directly: You can place a "Ghost" piece directly as a final winning move (only once, and only when there are two existing ghosts in a line). I'm looking for feedback on the game balance and learning curve. Specifically: - Is the "Ghost" and "Flip" mechanic intuitive? - Is the Learning Mode helpful? - Is the game fair? Any rule adjustments needed? - Any bugs or issues? Any suggestions or comments would be much appreciated. Thank you in advance! https://tic-tac-flip.web.app/ December 14, 2025 at 11:19AM

Show HN: Soup.lua: making Lua do what it shouldn't https://ift.tt/ORk8Z3e

Show HN: Soup.lua: making Lua do what it shouldn't https://ift.tt/kMADUx7 December 14, 2025 at 12:33AM

Show HN: PhenixCode – Added admin dashboard for multi-server management https://ift.tt/h012Xul

Show HN: PhenixCode – Added admin dashboard for multi-server management I built PhenixCode — an open-source, self-hosted and customizable alternative to GitHub Copilot Chat. Why: I wanted a coding assistant that runs locally, with full control over models and data. Copilot is great, but it’s subscription-only and cloud-only. PhenixCode gives you freedom: use local models (free) or plug in your own API keys. Use the new admin dashboard GUI to visually configure the RAG settings for multi-server management. https://ift.tt/3axOsvZ December 13, 2025 at 01:46AM

Show HN: I'm building an open-source Amazon https://ift.tt/3mWsX1e

Show HN: I'm building an open-source Amazon I'm building an open source Amazon. In other words, an open source decentralized marketplace. But like Carl Sagan said, to make an apple pie from scratch, you must first invent the universe. So first I had to make open source management systems for every vertical. I'm launching the first one today, Openfront e-commerce, an open source Shopify alternative. Next will be Openfront restaurant, Openfront grocery, and Openfront gym. And all of these Openfronts will connect to our decentralized marketplace, "the/marketplace", seamlessly. Once we launch other Openfronts, you'll be able to do everything from booking hotels to ordering groceries right from one place with no middle men. The marketplace simply connects to the Openfront just like its built-in storefront does. Together, we can use open source to disrupt marketplaces and make sure sellers, in every vertical, are never beholden to them. Marketplace: https://ift.tt/qVmj0fs Openfront platforms: https://ift.tt/BxkrAaT Source code: https://ift.tt/ET5Zgcx Demo - Openfront: https://youtu.be/jz0ZZmtBHgo Demo - Marketplace: https://youtu.be/LM6hRjZIDcs Part 1 - https://ift.tt/9pNRqmx https://openship.org December 12, 2025 at 11:49PM

Show HN: ESLint Plugin for styled-jsx https://ift.tt/N2vg3eL

Show HN: ESLint Plugin for styled-jsx https://ift.tt/hcTV3HG December 12, 2025 at 11:44PM

Show HN: I used Gemini 3 to turn 42 books into interactive webpages in 2 weeks https://ift.tt/OSkboK8

Show HN: I used Gemini 3 to turn 42 books into interactive webpages in 2 weeks https://ift.tt/L7O19oh December 12, 2025 at 12:15AM

Show HN: An endless scrolling word search game https://ift.tt/Ga3CVFI

Show HN: An endless scrolling word search game I built a procedurally generated word-search game where the puzzle never ends - as you scroll, the grid expands infinitely and new words appear. It’s designed to be quick to pick up, satisfying to play, and a little addictive. The core game works without an account using the pre-defined games, but signing up allows you to generate games using any topic you can think of. I’d love feedback on gameplay, performance, and whether the endless format feels engaging over time. If you try it, I’d really appreciate any bug reports or suggestions. Thanks in advance! https://ift.tt/TbIBkpO December 11, 2025 at 07:31PM

Show HN: SIM – Apache-2.0 n8n alternative https://ift.tt/vuDFfxW

Show HN: SIM – Apache-2.0 n8n alternative Hey HN, Waleed here. We're building Sim ( https://sim.ai/ ), an open-source visual editor to build agentic workflows. Repo here: https://ift.tt/2YaXb9s . Docs here: https://docs.sim.ai . You can run Sim locally using Docker, with no execution limits or other restrictions. We started building Sim almost a year ago after repeatedly troubleshooting why our agents failed in production. Code-first frameworks felt hard to debug because of implicit control flow, and workflow platforms added more overhead than they removed. We wanted granular control and easy observability without piecing everything together ourselves. We launched Sim [1][2] as a drag-and-drop canvas around 6 months ago. Since then, we've added: - 138 blocks: Slack, GitHub, Linear, Notion, Supabase, SSH, TTS, SFTP, MongoDB, S3, Pinecone, ... - Tool calling with granular control: forced, auto - Agent memory: conversation memory with sliding window support (by last n messages or tokens) - Trace spans: detailed logging and observability for nested workflows and tool calling - Native RAG: upload documents, we chunk, embed with pgvector, and expose vector search to agents - Workflow deployment versioning with rollbacks - MCP support, Human-in-the-loop block - Copilot to build workflows using natural language (just shipped a new version that also acts as a superagent and can call into any of your connected services directly, not just build workflows) Under the hood, the workflow is a DAG with concurrent execution by default. Nodes run as soon as their dependencies (upstream blocks) are satisfied. Loops (for, forEach, while, do-while) and parallel fan-out/join are also first-class primitives. Agent blocks are pass-through to the provider. You pick your model (OpenAI, Anthropic, Gemini, Ollama, vLLM), and and we pass through prompts, tools, and response format directly to the provider API. We normalize response shapes for block interoperability, but we're not adding layers that obscure what's happening. We're currently working on our own MCP server and the ability to deploy workflows as MCP servers. Would love to hear your thoughts and where we should take it next (: [1] https://ift.tt/xs8VpwB [2] https://ift.tt/HNrzdvM https://ift.tt/sjxM9IC December 11, 2025 at 10:50PM

Show HN: Cargo-rail: graph-aware monorepo tooling for Rust; 11 deps https://ift.tt/IRgvneA

Show HN: Cargo-rail: graph-aware monorepo tooling for Rust; 11 deps https://ift.tt/6cgJeyC December 11, 2025 at 02:19AM

Show HN: I launched a podcast to interview makers https://ift.tt/eUpjQsL

Show HN: I launched a podcast to interview makers For years I’ve wanted to start a podcast to interview curious and passionate makers in the depths of their creative pursuits. I would love any feedback, a rating, and if you know anyone would would make a great guest, please let me know! https://ift.tt/IJzFHjm December 11, 2025 at 12:40AM

Show HN: A 2-row, 16-key keyboard designed for smartphones https://ift.tt/H5gyrYI

Show HN: A 2-row, 16-key keyboard designed for smartphones Mobile keyboards today are almost entirely based on the 26-key, 3-row QWERTY layout. Here’s a new 2-row, 16-key alternative designed specifically for smartphones. https://ift.tt/0kW4bF2 December 10, 2025 at 11:19PM

Show HN: Gemini 3 imagines Hacker News as a HyperCard stack in 1994 https://ift.tt/IZ4OV6U

Show HN: Gemini 3 imagines Hacker News as a HyperCard stack in 1994 https://hyper-card-hacker-news.vercel.app/ December 10, 2025 at 04:34AM

Show HN: Advent of Back Ends https://ift.tt/tTuScQ8

Show HN: Advent of Back Ends Build AI Agents, Workflows, Backend systems live every day for 30 days. https://adventofbackends.vercel.app/ December 9, 2025 at 11:56PM

Show HN: Agentic Reliability Framework – Multi-agent AI self-heals failures https://ift.tt/w3emP86

Show HN: Agentic Reliability Framework – Multi-agent AI self-heals failures Hey HN! I'm Juan, former reliability engineer at NetApp where I handled 60+ critical incidents per month for Fortune 500 clients. I built ARF after seeing the same pattern repeatedly: production AI systems fail silently, humans wake up at 3 AM, take 30-60 minutes to recover, and companies lose \$50K-\$250K per incident. ARF uses 3 specialized AI agents: Detective: Anomaly detection via FAISS vector memory Diagnostician: Root cause analysis with causal reasoning Predictive: Forecasts failures before they happen Result: 2-minute MTTR (vs 45-minute manual), 15-30% revenue recovery. Tech stack: Python 3.12, FAISS, SentenceTransformers, Gradio Tests: 157/158 passing (99.4% coverage) Docs: 42,000 words across 8 comprehensive files Live demo: https://ift.tt/S1GEdPk... The interesting technical challenge was making agents coordinate without tight coupling. Each agent is independently testable but orchestrated for holistic analysis. Happy to answer questions about multi-agent systems, production reliability patterns, or FAISS for incident recall! GitHub: https://ift.tt/eQtMJcn (Also available for consulting if you need this deployed in your infrastructure: https://lgcylabs.vercel.app/ ) https://ift.tt/eQtMJcn December 9, 2025 at 10:25PM

Show HN: Fanfa – Interactive and animated Mermaid diagrams https://ift.tt/GYmpxDH

Show HN: Fanfa – Interactive and animated Mermaid diagrams https://fanfa.dev/ December 4, 2025 at 06:46PM

Show HN: Edge HTTP to S3 https://ift.tt/mO9R8lc

Show HN: Edge HTTP to S3 Hi HN, Edge.mq makes it very easy to ship data from the edge to S3. EdgeMQ is a managed HTTP to S3 edge ingest layer that takes events from services, devices, and partners on the public internet and lands them durably in your S3 bucket, ready for tools like Snowflake, Databricks, ClickHouse, DuckDB, and feature pipelines. Design focus on simplicity, performance and security. https://edge.mq/ December 8, 2025 at 11:35PM

Show HN: Diesel-guard – Lint Diesel migrations for unsafe PostgreSQL patterns https://ift.tt/OzwVfBd

Show HN: Diesel-guard – Lint Diesel migrations for unsafe PostgreSQL patterns https://ift.tt/3kYmL2s December 8, 2025 at 10:48PM

Show HN : WealthYogi - Net worth Tracker https://ift.tt/8yvoLau

Show HN : WealthYogi - Net worth Tracker Hey everyone I’ve been on my FIRE journey for a while and got tired of juggling spreadsheets, brokers, and bank apps — so I built WealthYogi, a privacy-first net worth tracker focused on clarity and peace of mind. Why Like many FIRE folks, I was juggling spreadsheets, bank apps, and broker dashboards — but never had one clear, connected view of my true net worth. Most apps required logins or shared data with third parties — not ideal if you care about privacy. So I built WealthYogi to be: Offline-first & private — all data stays 100% on your device Simple — focus purely on your wealth trajectory, not budgeting noise Multi-currency — 23 currencies, supporting GBP, USD, EUR, INR and more What it does now * Tracks your net worth and portfolio value in real time * Categorises assets (liquid, semi-liquid, illiquid) and liabilities (loans, mortgages, etc.) * Multi-currency support (GBP, USD, EUR, INR and more) * Privacy-first: all data stays 100% on your device * 10+ Financial Health Indicators and Personalised Finance Health Score and Suggestions to improve * Minimal, distraction-free design focused purely on your wealth trajectory Planned features (already in development) Real-time account sync Automatic FX updates Import/Export support More currency account types Debt tracking Net worth forecasting Pricing Free Trial for 3 days. One time deal currently running till 10th December. Monthly and Yearly Subscriptions available. Would love your feedback 1. Try the app and share honest feedback — what works, what feels clunky 2. Tell us what features you’d love to see next (especially FIRE-specific ideas!) 3. Share how you currently track your net worth — spreadsheet, app, or otherwise Here’s the link again: WealthYogi on the App Store ( https://ift.tt/dBIz8Q2 ) WealthYogi on the Android ( https://ift.tt/VDIzlpy... ) Demo ( https://youtu.be/KUiPEQiLyLY ) I am building this for the FIRE and personal finance enthusiasts, and your feedback genuinely guides our roadmap. — The WealthYogi Team hello@datayogi.io https://ift.tt/ifGM5AW December 8, 2025 at 05:43AM

Show HN: OpenFret – Guitar inventory, AI practice, and a note-detection RPG https://ift.tt/RbIuxdl

Show HN: OpenFret – Guitar inventory, AI practice, and a note-detection RPG I'm a solo dev and guitarist who got frustrated juggling separate apps for tracking gear, practicing, and collaborating. So I built OpenFret—one platform that handles all of it. What it does: 1) Smart inventory – Add your guitars, get auto-filled specs from ~1,000 models in the database. Track woods, pickups, tunings, string changes, photos. 2) AI practice sessions – Generate personalized tabs and lessons based on your practice history. Rendered with VexFlow notation. 3) Session Mode – Version-controlled music collaboration (think Git for audio). Fork tracks, add layers, see history, merge contributions. 4) Musical tools – Tuner, metronome, scale visualizer, chord progressions, fretboard maps. Last.fm integration for tracking what songs you're learning. 5) Guitar RPG – Fight monsters by playing real guitar notes. Web Audio API detects your playing. 300+ hand-crafted lessons from beginner to advanced. What you can try without signing up: 1) The RPG demo is completely free, no account needed: https://ift.tt/qEAMkwr — just click "Start Battle" and play. It's capped at level 10 but gives you a real feel for the note detection. The full platform (inventory, AI practice, sessions) requires Discord or magic link auth. Current state: Beta. Core features work, actively adding content. The RPG has 300+ lessons done with more coming. Full game is $10 one-time, everything else is free. Why I built it: I have a basement music setup and wanted one place to track when I last changed strings, get practice material that adapts to what I'm working on, and collaborate without DM'ing WAV/MP3 files. Tech: Next.js (T3), Web Audio API for pitch detection, VexFlow for notation, Strudel integration for algorithmic backing tracks, Last.fm API. Happy to answer questions about the AI tab generation, note detection, or the Git-style collaboration model. https://ift.tt/osA0Mwt December 8, 2025 at 02:49AM

Show HN: Minimal container-like sandbox built from scratch in C https://ift.tt/jKyFAwm

Show HN: Minimal container-like sandbox built from scratch in C Runbox recreates core container features without relying on existing runtimes or external libraries. It uses namespaces, cgroups v2, and seccomp to create an isolated process environment, with a simple shell for interaction. For future gonna work on adding an interface so external applications can be executed inside Runbox, similar to containers. Github: https://ift.tt/IBwSlrp Happy to hear feedback or suggestions. https://ift.tt/IBwSlrp December 7, 2025 at 06:23PM

Show HN: TapeHead – A CLI tool for stateful random access of file streams https://ift.tt/svqz0Ug

Show HN: TapeHead – A CLI tool for stateful random access of file streams I wrote this tool while debugging a driver because I couldn't find a tool that allowed me to open a file, seek randomly, and read and write. I thought it might one day be useful to someone too. https://ift.tt/8AZMTep December 7, 2025 at 01:53AM

Show HN: Manifesto – An AI-Native UI Framework Intent-to-State, Not Text-to-App https://ift.tt/iPaITjV

Show HN: Manifesto – An AI-Native UI Framework Intent-to-State, Not Text-to-App Hi HN, I'm the creator of Manifesto AI. I've noticed that while LLMs are getting smarter, their ability to interact with complex Web UIs is still fragile. Agents usually have to "guess" DOM selectors or rely on vision, which leads to hallucinations and broken workflows. I realized that for AI to be useful in SaaS/B2B software, we don't need "Generative UI" (Text-to-App); we need a deterministic "State Layer" that agents can understand and control directly. So I built Manifesto. It's a schema-first UI engine where: 1. You define the form/UI as a JSON Schema. 2. The engine renders it (React/Vue). 3. Crucially, it exports a "Semantic Snapshot" to the AI Agent. Instead of parsing pixels, the Agent receives a clean JSON state (values, validation rules, available actions) and dispatches "Intents" (e.g., `setValue`, `submit`) to the engine. Disclaimer: I built the core engine and this demo in just 4 days. It is currently in a very early Alpha (v0.1) stage. I’m sharing this early because I want to validate if this "Intent-to-State" architecture makes sense to other developers. I'd love to hear your feedback on the approach. Roast my code or the concept! Demo: https://ift.tt/jNdplFw Repo: https://ift.tt/UOtCkG5 https://ift.tt/4EhIVKl December 6, 2025 at 11:24PM

Show HN: AgentPG – Stateful AI Agents in Go with PostgreSQL Persistence https://ift.tt/XByrudY

Show HN: AgentPG – Stateful AI Agents in Go with PostgreSQL Persistence https://ift.tt/Kw5VPJU December 6, 2025 at 11:07PM

Show HN: Bible Note Journal – AI transcription and study tools for sermons (iOS) https://ift.tt/CgnsGio

Show HN: Bible Note Journal – AI transcription and study tools for sermons (iOS) I got back into church a couple years ago and would try taking notes with Apple Notes. It was a struggle trying to type notes while focusing on the sermon. Honestly, it would have been easier to write it in a notebook but in the end I built this iOS app to solve that problem. You can record audio during a sermon (or upload files), and it transcribes using Whisper, then generates summaries, flashcards, and reflection questions tailored to Christian content. The backend is Spring Boot + Kotlin calling OpenAI's API. Instead of deploying the backend through one of the cloud providers directly I decided to go with Railway. Users are notified with push notifications when their transcription and summary are completed. The iOS app uses SwiftUI and out-of-the-box SwiftUI components. I worked with Spring Boot + Java a few years back when in fintech so it was cool to try writing something in Kotlin. I'm also a full-time Flutter dev that has been trying to get into Native iOS development and felt like I found a good use case for an app. Currently only available in the US/Canada App Store. There is a free 3-day trial that you can use to give the app a go. The goal was helping Christians retain more from sermons and build stronger biblical literacy. Happy to answer questions about the architecture, AI prompting approach for Christian content, or anything else. App Store link: https://ift.tt/cdD9gCm... https://ift.tt/qg7IhHP December 6, 2025 at 02:13AM

Show HN: HCB Mobile – financial app built by 17 y/o, processing $6M/month https://ift.tt/aVGYoXq

Show HN: HCB Mobile – financial app built by 17 y/o, processing $6M/month Hey everyone! I just built a mobile app using Expo (React Native) for a platform that moves $6M/month. It’s a neobank used by 6,500+ nonprofit organizations across the world. One of my biggest challenges, while juggling being a full-time student, was getting permission from Apple/Google to use advanced native features such as Tap to Pay (for in-person donations) and Push Provisioning (for adding your card to your digital wallet). It was months of back-and-forth emails, test case recordings, and also compliance checks. Even after securing Apple/Google’s permission, any minor fix required publishing a new build, which was time-consuming. After dealing with this for a while, I adopted the idea of “over the air updates” using Expo’s EAS update service. This allowed me to remotely trigger updates without needing a new app build. The 250 hours I spent building this app were an INSANE learning experience, but it was also a whole lot of fun. Give the app a try, and I’d love any feedback you have on it! btw, back in March, we open-sourced this nonprofit neobank on GitHub. https://ift.tt/KCJskIj https://ift.tt/PemiSdq December 3, 2025 at 09:50AM

Show HN: SerpApi MCP Server https://ift.tt/VfuXc12

Show HN: SerpApi MCP Server https://ift.tt/MqRcKSj December 6, 2025 at 12:00AM

Show HN: Playwright for Windows Computer Use https://ift.tt/bmYOn0V

Show HN: Playwright for Windows Computer Use https://ift.tt/vNfFcSr December 5, 2025 at 04:15AM

Show HN: I Built an UI Library that lets you create beautiful UIs in Minutes https://ift.tt/tx2lwLV

Show HN: I Built an UI Library that lets you create beautiful UIs in Minutes Hello Everyone, My name is Karan, and I'm a Frontend Developer, but I feel like I'm more of a Design Engineer because of my love for creating UIs When I started my development journey, I fell for frontend development and stuck with it ever since But I noticed that many of my friends hated writing CSS because creating UIs is a very tedious and time-consuming process, and you have to be pixel-perfect But at the same time, they also wanted their project to look premium with beautiful animations and a world-class user experience That's when I thought "What if anyone could integrate beautiful animated components into their website regardless of their CSS skills?" And after six months of pain and restless nights, I finally built ogBlocks to solve this problem. It is an Animated UI Library for React that contains all the cool animations that will make it look premium and production-grade ogBlocks has navbars, modals, buttons, feature sections, text animations, carousels, and much more. I hope you'll love it Best Karan https://ogblocks.dev/ December 5, 2025 at 02:29AM

Show HN: Cheap OpenTelemetry lakehouses with Parquet, DuckDB, and Iceberg https://ift.tt/LX5WDBc

Show HN: Cheap OpenTelemetry lakehouses with Parquet, DuckDB, and Iceberg Side project: exploring storing and querying OpenTelemetry data with duckdb, open table formats, and cheap object storage with some rust glue code. Yesterday, AWS made this exact sort of data architecture lot easier with new CloudWatch features: https://ift.tt/n6DGpea... https://ift.tt/lQE0qzX December 5, 2025 at 02:12AM

Show HN: Fresh – A new terminal editor built in Rust https://ift.tt/kIPSvRH

Show HN: Fresh – A new terminal editor built in Rust I built Fresh to challenge the status quo that terminal editing must require a steep learning curve or endless configuration. My goal was to create a fast, resource-efficient TUI editor with the usability and features of a modern GUI editor (like a command palette, mouse support, and LSP integration). Core Philosophy: - Ease-of-Use: Fundamentally non-modal. Prioritizes standard keybindings and a minimal learning curve. - Efficiency: Uses a lazy-loading piece tree to avoid loading huge files into RAM - reads only what's needed for user interactions. Coded in Rust. - Extensibility: Uses TypeScript (via Deno) for plugins, making it accessible to a large developer base. The Performance Challenge: I focused on resource consumption and speed with large file support as a core feature. I did a quick benchmark loading a 2GB log file with ANSI color codes. Here is the comparison against other popular editors: - Fresh: Load Time: *~600ms* | Memory: *~36 MB* - Neovim: Load Time: ~6.5 seconds | Memory: ~2 GB - Emacs: Load Time: ~10 seconds | Memory: ~2 GB - VS Code: Load Time: ~20 seconds | Memory: OOM Killed (~4.3 GB available) (Only Fresh rendered the ansi colors.) Development process: I embraced Claude Code and made an effort to get good mileage out of it. I gave it strong specific directions, especially in architecture / code structure / UX-sensitive areas. It required constant supervision and re-alignment, especially in the performance critical areas. Added very extensive tests (compared to my normal standards) to keep it aligned as the code grows. Especially, focused on end-to-end testing where I could easily enforce a specific behavior or user flow. Fresh is an open-source project (GPL-2) seeking early adopters. You're welcome to send feedback, feature requests, and bug reports. Website: https://sinelaw.github.io/fresh/ GitHub Repository: https://ift.tt/s06E2k3 https://sinelaw.github.io/fresh/ December 3, 2025 at 08:15PM

Show HN: Golang Client Library for Gradium.ai TTS/STT API https://ift.tt/GmTxptF

Show HN: Golang Client Library for Gradium.ai TTS/STT API https://ift.tt/DowhegG December 3, 2025 at 01:22AM

Show HN: Meeting Detection – a small Rust engine that detects meetings on macOS https://ift.tt/bSJKux6

Show HN: Meeting Detection – a small Rust engine that detects meetings on macOS I built a small open-source meeting detection engine for macOS. The goal is to provide a simple and accurate way for apps to know when a user is in a Zoom/Meet/Teams/Webex meeting. A lot of meeting recorders, productivity tools, and focus apps try to detect meetings, but the results are often unreliable. Some apps pop up “You’re in a meeting” suggestions even when nothing is happening. I wanted something that works consistently and is easy for developers to integrate. The engine is written in Rust and exposed to Node/Electron via napi-rs. It runs a lightweight background loop and uses two tiers: 1. Native app detection (Zoom, Teams, Webex) • process detection • meeting-related network activity 2. Browser meeting detection (Google Meet, Teams Web, Zoom Web, Webex Web) • reads browser tabs via AppleScript • validates meeting URL patterns • supports Chrome, Safari, and Edge It exposes a very simple JS API: init(); onMeetingStart((_, d) => console.log("Meeting started:", d.appName)); onMeetingEnd(() => console.log("Meeting ended")); console.log(isMeetingActive()); Would love feedback, especially from anyone building recorders, focus apps, calendar tools, etc. Windows + Linux support coming next. https://ift.tt/xVZwIjq December 3, 2025 at 01:47AM

Show HN: SMART report viewer – Simple tool to analyze smartctl outputs https://ift.tt/Vc1EKZg

Show HN: SMART report viewer – Simple tool to analyze smartctl outputs https://ift.tt/DoR3dPe December 3, 2025 at 12:29AM

Show HN: Valknut – static analysis to tame agent tech debt https://ift.tt/9ajBimK

Show HN: Valknut – static analysis to tame agent tech debt Hi y'all, In my work to reduce the amount of time I spend in the agentic development loop, I observed that code structure was one of the biggest determinants in agent task success. Ironically, agents aren't good at structuring code for their own consumption, so left to their own devices purely vibe-coded projects will tend towards dumpster fire status. Agents aren't great at refactoring out of the box either, so rather than resign myself to babysitting refactors to maintain agent performance, I wrote a tool to put agents on rails while refactoring. Another big problem I encountered trying to remove myself from the loop was knowing where to spend my time efficiently when I did dive into the codebase. To combat this I implemented a html report that simplifies identifying high level problem. In many cases you can click from an issue in the report directly to the code via VS Code links. I hope you find this tool as useful as I have, I'm working on it actively so I'm happy to field feature requests. https://ift.tt/cd6pMzO December 2, 2025 at 11:14PM

Show HN: RFC Hub https://ift.tt/6rG0utF

Show HN: RFC Hub I've worked at several companies during the past two decades and I kept encountering the same issues with internal technical proposals: - Authors would change a spec after I started writing code - It's hard to find what proposals would benefit from my review - It's hard to find the right person to review my proposals - It's not always obvious if a proposal has reached consensus (e.g. buried comments) - I'm not notified if a proposal I approved is now ready to be worked on And that's just scratching the surface. The most popular solutions (like Notion or Google Drive + Docs) mostly lack semantics. For example it's easy as a human to see a table in a document with rows representing reviewers and a checkbox representing review acceptance but it's hard to formally extract meaning and prevent a document from "being published" when criteria isn't met. RFC Hub aims to solve these issues by building an easy to use interface around all the metadata associated with technical proposals instead of containing it textually within the document itself. The project is still under heavy development as I work on it most nights and weekends. The next big feature I'm planning is proposal templates and the ability to refer to documents as something other than RFCs (Request for Comments). E.g. a company might have a UIRFC for GUI work (User Interface RFCs), a DBADR (Database Architecture Decision Record), etc. And while there's a built-in notification system I'm still working on a Slack integration. Auth works by sending tokens via email but of course RFC Hub needs Google auth. Please let me know what you think! https://rfchub.app/ December 1, 2025 at 10:34PM

Show HN: An AI zettelkasten that extracts ideas from articles, videos, and PDFs https://ift.tt/BJ349PV

Show HN: An AI zettelkasten that extracts ideas from articles, videos, and PDFs Hey HN! Over the weekend (leaning heavily on Opus 4.5) I wrote Jargon - an AI-managed zettelkasten that reads articles, papers, and YouTube videos, extracts the key ideas, and automatically links related concepts together. Demo video: https://youtu.be/W7ejMqZ6EUQ Repo: https://ift.tt/XLsjmTJ You can paste an article, PDF link, or YouTube video to parse, or ask questions directly and it'll find its own content. Sources get summarized, broken into insight cards, and embedded for semantic search. Similar ideas automatically cluster together. Each insight can spawn research threads - questions that trigger web searches to pull in related content, which flows through the same pipeline. You can explore the graph of linked ideas directly, or ask questions and it'll RAG over your whole library plus fresh web results. Jargon uses Rails + Hotwire with Falcon for async processing, pgvector for embeddings, Exa for neural web search, crawl4ai as a fallback scraper, and pdftotext for academic papers. https://ift.tt/XLsjmTJ December 1, 2025 at 11:50PM