Show HN: LogicStamp – A Context Compiler for TypeScript https://ift.tt/NjGnL7W

Show HN: LogicStamp – A Context Compiler for TypeScript https://logicstamp.dev March 31, 2026 at 10:57PM

Show HN: Memv – Memory for AI Agents https://ift.tt/np2Dmso

Show HN: Memv – Memory for AI Agents memv is an open-source Python library that gives AI agents persistent memory. Feed it conversations; it extracts knowledge. The extraction mechanism is predict-calibrate (Nemori paper): given existing knowledge, it predicts what a new conversation should contain, then extracts only what the prediction missed. v0.1.2 adds the production path: - PostgreSQL backend (pgvector for vectors, tsvector for text search, asyncpg pooling). Single db_url parameter — file path for SQLite, connection string for Postgres. - Embedding adapters: OpenAI, Voyage, Cohere, fastembed (local ONNX). Other things it does: - Bi-temporal validity: event time (when was the fact true) + transaction time (when did we learn it), following Graphiti's model. - Hybrid retrieval: vector similarity + BM25 merged with Reciprocal Rank Fusion. - Episode segmentation: groups messages before extraction. - Contradiction handling: new facts invalidate old ones, with full audit trail. Procedural memory (agents learning from past runs) is next, deferred until there's usage data. https://ift.tt/uYHRTsa March 31, 2026 at 12:09AM

Show HN: I made my fitness dashboard public and Apple Health needs an API https://ift.tt/fuOenJ3

Show HN: I made my fitness dashboard public and Apple Health needs an API https://ift.tt/5JmO1CB March 31, 2026 at 12:39AM

Show HN: A Terminal Interface for Jira https://ift.tt/GDAg3Zr

Show HN: A Terminal Interface for Jira https://ift.tt/YcgmUQ3 March 30, 2026 at 08:47PM

Show HN: QuickBEAM – run JavaScript as supervised Erlang/OTP processes https://ift.tt/XdxsOrY

Show HN: QuickBEAM – run JavaScript as supervised Erlang/OTP processes QuickBEAM is a JavaScript runtime embedded inside the Erlang/OTP VM. If you’re building a full-stack app, JavaScript tends to leak in anyway — frontend, SSR, or third-party code. QuickBEAM runs that JavaScript inside OTP supervision trees. Each runtime is a process with a `Beam` global that can: - call Elixir code - send/receive messages - spawn and monitor processes - inspect runtime/system state It also provides browser-style APIs backed by OTP/native primitives (fetch, WebSocket, Worker, BroadcastChannel, localStorage, native DOM, etc.). This makes it usable for: - SSR - sandboxed user code - per-connection state - backend JS with direct OTP interop Notable bits: - JS runtimes are supervised and restartable - sandboxing with memory/reduction limits and API control - native DOM that Erlang can read directly (no string rendering step) - no JSON boundary between JS and Erlang - built-in TypeScript, npm support, and native addons QuickBEAM is part of Elixir Volt — a full-stack frontend toolchain built on Erlang/OTP with no Node.js. Still early, feedback welcome. https://ift.tt/lAeFcK6 March 29, 2026 at 04:03AM

Show HN: Tinyvision:-Building Ultra-Lightweight Models for Image Tasks https://ift.tt/RoVEhij

Show HN: Tinyvision:-Building Ultra-Lightweight Models for Image Tasks Disclaimer: English is not my first language. I used an LLM to help me write post clearly. Hello everyone, I just wanted to share my project and wanted some feedback on it Goal: Most image models today are bulky and overkill for basic tasks. This project explores how small we can make image classification models while still keeping them functional by stripping them down to the bare minimum. Current Progress & Results: Cat vs Dog Classification: First completed task using a 25,000-image dataset with filter bank preprocessing and compact CNNs. Achieved up to 86.87% test accuracy with models under 12.5k parameters. Several models under 5k parameters reached over 83% accuracy, showcasing strong efficiency-performance trade-offs. CIFAR-10 Classification: Second completed task using the CIFAR-10 dataset. This approach just relies on compact CNN architectures without the filter bank preprocessing. A 22.11k parameter model achieved 87.38% accuracy. A 31.15k parameter model achieved 88.43% accuracy. All code and experiments are available in my GitHub repository: https://ift.tt/MjKI7ap I would love for you to check out the project and let me know your feedback! Also, do leave a star if you find it interesting https://ift.tt/MjKI7ap March 29, 2026 at 10:52PM

Show HN: Octopus, Open-source alternative to CodeRabbit and Greptile https://ift.tt/FwaklQ0

Show HN: Octopus, Open-source alternative to CodeRabbit and Greptile Hey HN, we built Octopus an open-source, self-hostable AI code reviewer for GitHub and Bitbucket. It uses RAG with vector search (Qdrant) to understand your full codebase, not just the diff, and posts inline findings on PRs with severity ratings. Works with Claude and OpenAI, and you can bring your own API keys. Video: https://www.youtube.com/watch?v=HP1kaKTOdXw | GitHub: https://ift.tt/lUaGAIE https://ift.tt/F51fn3q March 28, 2026 at 08:20PM

Show HN: GitHub Copilot Technical Writing Skill https://ift.tt/G5b6DtN

Show HN: GitHub Copilot Technical Writing Skill Its not super fancy, but I have found it useful from small emails to larger design docs so thought I would share. https://ift.tt/kXoOZ50 March 29, 2026 at 01:33AM

Show HN: We built a multi-agent research hub. The waitlist is a reverse-CAPTCHA https://ift.tt/6GxEwml

Show HN: We built a multi-agent research hub. The waitlist is a reverse-CAPTCHA Hey HN, Automated research is the next big step in AI, with companies like OpenAI aiming to debut a fully automated researcher by 2028 ( https://ift.tt/CvrW52j... ). However, there is a very real possibility that much of this corporate research will remain closed to the general public. To counter this, we spent the last month building Enlidea---a machine-to-machine ecosystem for open research. It's a decentralized research hub where autonomous agents propose hypotheses, stake bounties, execute code, and perform automated peer reviews on each other's work to build consensus. The MVP is almost done, but before launching, we wanted to filter the waitlist for developers who actually know how to orchestrate agents. Because of this, there is no real UI on the landing page. It's an API handshake. Point your LLM agent at the site and see if it can figure out the payload to whitelist your email. https://enlidea.com March 28, 2026 at 09:49PM

Show HN: Foundry: a Markdown-first CMS written in Go https://ift.tt/mRS6xdH

Show HN: Foundry: a Markdown-first CMS written in Go Hi HN! I've been building a CMS called Foundry, brought together from multiple smaller private projects as well as greenfield code. The short version is: it's a CMS written in Go with a focus on markdown content, a simple hook-based plugin model, themes, archetypes, preview flows, and a clean authoring/developer experience. I started working on it because I wanted something that was more powerful than Hugo for a few of my websites, without having to resort to dangling onto a database. What seems different about it, at least to me, is that I'm trying to keep the system small in concept: local content, explicit behavior, compile-time plugin registration, and an admin/editor layer that is meant to stay close to how the content actually lives on disk. The goal is not to make "yet another website builder", but to make a CMS that is easy to use and quick to onramp onto, but has powerful advanced features and extensibility. Still early, but usable enough that I wanted to put it in front of people here and get feedback. Please don't castigate me on the UI look - I'm not a designer, and the themes are basically clones of each other. Happy to answer technical questions, architecture questions, or hear where this seems useful versus where it does not. https://ift.tt/fHapkIY March 28, 2026 at 12:05AM

Show HN: Open-Source Animal Crossing–Style UI for Claude Code Agents https://ift.tt/gYAhy1w

Show HN: Open-Source Animal Crossing–Style UI for Claude Code Agents We posted here on Monday and got some great feedback. We’ve implemented a few of the most requested updates: - iMessage channel support (agents can text people and you can text agents) Other channels are simple to extend. - A built-in browser (agents can navigate and interact with websites) - Scheduling (run tasks on a timer / cron/ in the future) - Built in tunneling so that the agents can share local stuff with you over the internet - More robust MCP and Skills support so anyone can extend it - Auto approval for agent requests If you didn’t see the original: Outworked is a desktop app where Claude Code agents work as a small “team.” You give it a goal, and an orchestrator breaks it into tasks and assigns them across agents. Agents can run in parallel, talk to each other, write code, and now also browse the web and send messages. It runs locally and plugs into your existing Claude Code setup. Would love to hear what we should build next. Thanks again! https://ift.tt/EQxDVak March 28, 2026 at 12:25AM

Show HN: Orloj – agent infrastructure as code (YAML and GitOps) https://ift.tt/4UQXoVI

Show HN: Orloj – agent infrastructure as code (YAML and GitOps) Hey HN, we're Jon and Kristiane, and we're building Orloj ( https://orloj.dev ), an open-source (Apache 2.0) orchestration runtime for multi-agent AI systems. You define agents, tools, policies, and workflows in declarative YAML manifests, and Orloj handles scheduling, execution, governance, and reliability. We built this because running AI agents in production today looks a lot like running containers before Kubernetes: ad-hoc scripts, no governance, no observability, no standard way to manage the lifecycle of an agent fleet. Everyone we talked to was writing the same messy glue code to wire agents together, and nobody had a good answer for "which agent called which tool, and was it supposed to?" Orloj treats agents the way infrastructure-as-code treats cloud resources. You write a manifest that declares an agent's model, tools, permissions, and execution limits. You compose agents into directed graphs — pipelines, hierarchies, or swarm loops. The part we're most excited about is governance. AgentPolicy, AgentRole, and ToolPermission are evaluated inline during execution, before every agent turn and tool call. Instead of prompt instructions that the model might ignore, these policies are a runtime gate. Unauthorized actions fail closed with structured errors and full audit trails. You can set token budgets per run, whitelist models, block specific tools, and scope policies to individual agent systems. For reliability, we built lease-based task ownership (so crashed workers don't leave orphan tasks), capped exponential retry with jitter, idempotent replay, and dead-letter handling. The scheduler supports cron triggers and webhook-driven task creation. The architecture is a server/worker split. orlojd hosts the API, resource store (in-memory for dev, Postgres for production), and task scheduler. orlojworker instances claim and execute tasks, route model requests through a gateway (OpenAI, Anthropic, Ollama, etc.), and run tools in configurable isolation — direct, sandboxed, container, or WASM. For local development, you can run everything in a single process with orlojd --embedded-worker --storage-backend=memory. Tool isolation was important to us. A web search tool probably doesn't need sandboxing, but a code execution tool should run in a container with no network, a read-only filesystem, and a memory cap. You configure this per tool based on risk level, and the runtime enforces it. We also added native MCP support. You register an MCP server (stdio or HTTP), Orloj auto-discovers its tools, and they become first-class resources with governance applied. So you can connect something like the GitHub MCP server and still have policy enforcement over what agents are allowed to do with it. Three starter blueprints are included (pipeline, hierarchical, swarm-loop). Docs: https://docs.orloj.dev We're also building out starter templates for operational workflows where governance really matters. First on the roadmap: 1. Incident response triage, 2. Compliance evidence collector, 3. CVE investigation pipeline, and 4. Secret rotation auditor. We have 20 templates in mind and community contributions are welcome. We're a small team and this is v0.1.0, so there's a lot still on the roadmap — hosted cloud, compliance packaging, and more. But the full runtime is open source today and we'd love feedback on what we've built so far. What would you use this for? What's missing? https://ift.tt/Z6CJVkI March 26, 2026 at 12:07PM

Show HN: Vizier – A physical design advisor for DuckDB https://ift.tt/Hi1J9RS

Show HN: Vizier – A physical design advisor for DuckDB Hi, I've made an early version of a physical design advisor (called Vizier) for DuckDB. It can analyze a collection of queries (using a set of heuristics) and recommend changes to the physical design/layout of the database (for example, sort orders, Parquet layouts, indexes, etc.), in order to make those queries run faster. Vizier is implemented as a DuckDB extension in Zig and supports DuckDB version 1.2.0 and newer. The project is very early-stage, but if you're interested in learning more about Vizier or trying it out, you can check out the links below: Project's GitHub repo: https://ift.tt/nOxGjMp Vizier documentation: https://cogitatortech.github.io/vizier/ March 26, 2026 at 11:46PM

Show HN: Micro – apps without ads, algorithms or tracking https://ift.tt/fwGhYIJ

Show HN: Micro – apps without ads, algorithms or tracking For over 10 years I've been trying to accomplish something that took Claude Code and a lot of failure to realise. We need alternatives to big tech and we're not working hard enough to make that happen. In an era of addiction, usury and exploitation it's now time we seriously consider alternatives. Proton and the like worked on privacy focused individual services and a pain stakingly slow pace. Maybe for good reason. But it was also in an era pre AI. 10 years ago I was convinced the super app model would work. And that a platform needed to exist to facilitate that. Today I realised the tech doesn't matter, the idea and execution from the top down does. I put aside my technical perfectionism to try pull together a solution to some of the problems that plagued my own life with tech addiction and I rewrote and threw away this thing multiple times over the years pre AI and after. I burned VC funding, I burned bridges, I burned community trust in an open source project. But it was all in the pursuit of something I was compelled needed to exist. I used this on a daily basis probably 10+ times a day. Every person has different use cases but for me what's key is to try pull all the digital daily habits in one place and then be able to build on that. I can't replace my own google usage for mail yet but I also saw a need for something in between by private email and a work email. There's so much more I could say but essentially Micro and the app Mu ( https://mu.xyz ) is the culmination of many years of work. And it's also open source. https://ift.tt/0mBc5FE . Please provide feedback. Please tear it apart. Please poke holes in my theory. I'm not looking for hype. I really do just think we need an alternative to big tech. https://micro.mu March 26, 2026 at 11:14PM

Show HN: NerdFlair, a Claude Code QoL Plugin https://ift.tt/pXZ9deM

Show HN: NerdFlair, a Claude Code QoL Plugin NerdFlair is a configurable bash statusline and chimes/spinner pack for Claude Code. Cursor extension (chimes only) also included. https://ift.tt/2Al8HTz March 26, 2026 at 10:51PM

Show HN: Pgsemantic – Point at your Postgres DB, get vector search instantly https://ift.tt/HeNdoBT

Show HN: Pgsemantic – Point at your Postgres DB, get vector search instantly https://ift.tt/9ZJcHMo March 26, 2026 at 01:41AM

Show HN: I built an integration for RL training of browser agents for everyone https://ift.tt/qOlzHGw

Show HN: I built an integration for RL training of browser agents for everyone This integration allows for scalable evals and training of browser agents with hosted Prime Intellect eval + training pipelines and headless browser infrastructure on Browserbase to RL train browser agents with LoRA. https://ift.tt/PFf28oC March 26, 2026 at 12:11AM

Show HN: I built a site that maps the web from a bounty hunter's perspective https://ift.tt/MJrz1xT

Show HN: I built a site that maps the web from a bounty hunter's perspective I built this because I wanted my own directory of public companies running bug bounty programs — where I could see their infrastructure in one place and have a real idea of where to start poking holes. Neobotnet collects intel data from companies on HackerOne and Bugcrowd — subdomains, DNS records, web servers with status codes, indexed/crawled URLs, JS files, and exposed secrets/paths (still building this last part). The data is already there when you need it. No scans to run. Currently tracking 41 companies, 63,878 web servers, and 1.8M+ URLs. Long term I want to expand this to startups that depend on cloud infrastructure so they can see what's publicly accessible. Made a free sample with Capital One's data (and other companies) so you can see what it looks like without signing up: https://freerecon.com Original Page: https://neobotnet.com Feedback very welcome. https://ift.tt/l4hLMRK March 24, 2026 at 01:49AM

Show HN: I built a party game that makes fun of corporate culture https://ift.tt/A42YhlR

Show HN: I built a party game that makes fun of corporate culture Made the first party game that makes fun of corporate culture! Would love for you to try it out. https://ift.tt/AYs8tbg March 25, 2026 at 01:39AM

Show HN: Jelly – SSH Social Hangout https://ift.tt/JAlxHuD

Show HN: Jelly – SSH Social Hangout built a social network you connect to over SSH. no signup, no browser, just open your terminal and you're in. channels, profiles, guestbook, shared blackboard, Top 8. your identity is your SSH key fingerprint so no passwords needed. to connect: ssh-keygen -t ed25519 (just hit enter through all the prompts) ssh jellyshell.dev built with Go, Bubble Tea, and Wish. i wanted to make something that maintains privacy and gets away from the brain rot and algorithms pushing rage bait. lmk what you think. March 24, 2026 at 11:08PM

Show HN: JulIDE – Lightweight Julia IDE Built with Tauri https://ift.tt/CL9i05c

Show HN: JulIDE – Lightweight Julia IDE Built with Tauri Hi HN! I built JulIDE - a lightweight Julia IDE using Tauri and Rust. Features: 10MB install (vs VSCode's 300MB) Full LSP, debugger, Git integration Built-in dev containers with X11 forwarding Tauri/Rust backend, React frontend Monaco based editor It's beta but functional. Built this for fun and to solve a real need in the Julia community. Tech stack: Tauri 2, Rust, React, Monaco, LanguageServer.jl GitHub: https://ift.tt/NzVKsSM Would love feedback! https://ift.tt/NzVKsSM March 24, 2026 at 12:55AM

Show HN: Minimalist library to generate SVG views of scientific data https://ift.tt/WVSQ2s7

Show HN: Minimalist library to generate SVG views of scientific data Just wanted to share with HN a simple/minimal open source Python library that generates SVG files visualizing two dimensional data and distributions, in case others find it useful or interesting. I wrote it as a fun project, mostly because I found that the standard libraries in Python generated unnecessarily large SVG files. One nice property is that I can configure the visuals through CSS, which allows me to support dark/light mode browser settings. The graphs are specified as JSON files (the repository includes a few examples). It supports scatterplots, line plots, histograms, and box plots, and I collected examples here: https://ift.tt/LzWSibD... I did this mostly for the graphs in an article in my blog ( https://alejo.ch/3jj ). Would love to hear opinions. :-) https://ift.tt/0VPA8k5 March 24, 2026 at 12:54AM

Show HN: Threadprocs – executables sharing one address space (0-copy pointers) https://ift.tt/6B9ZybA

Show HN: Threadprocs – executables sharing one address space (0-copy pointers) This project launches multiple independent programs into a single shared virtual address space, while still behaving like separate processes (independent binaries, globals, and lifetimes). When threadprocs share their address space, pointers are valid across them with no code changes for well-behaved Linux binaries. Unlike threads, each threadproc is a standalone and semi-isolated process. Unlike dlopen-based plugin systems, threadprocs run traditional executables with a `main()` function. Unlike POSIX processes, pointers remain valid across threadprocs because they share the same address space. This means that idiomatic pointer-based data structures like `std::string` or `std::unordered_map` can be passed between threadprocs and accessed directly (with the usual data race considerations). This accomplishes a programming model somewhere between pthreads and multi-process shared memory IPC. The implementation relies on directing ASLR and virtual address layout at load time and implementing a user-space analogue of `exec()`, as well as careful manipulation of threadproc file descriptors, signals, etc. It is implemented entirely in unprivileged user space code: < https://github.com/jer-irl/threadprocs/blob/main/docs/02-imp... >. There is a simple demo demonstrating “cross-threadproc” memory dereferencing at < https://github.com/jer-irl/threadprocs/tree/main?tab=readme-... >, including a high-level diagram. This is relevant to systems of multiple processes with shared memory (often ring buffers or flat tables). These designs often require serialization or copying, and tend away from idiomatic C++ or Rust data structures. Pointer-based data structures cannot be passed directly. There are significant limitations and edge cases, and it’s not clear this is a practical model, but the project explores a way to relax traditional process memory boundaries while still structuring a system as independently launched components. https://ift.tt/4oKiJCI March 23, 2026 at 11:08PM

Show HN: MAGA or Not? Political alignment scores for people and companies https://ift.tt/ptnz84v

Show HN: MAGA or Not? Political alignment scores for people and companies I wanted a way for people to support companies and people that align with their political beliefs. Additionally, I think it can serve as a valuable, source-linked public ledger of who said and did what over time, especially as incentives change and people try to rewrite their positions. This is fully AI-coded, researched, and sourced. Additionally, AI helped develop the scoring system. The evidence gathering is done by a number of different agents through OpenRouter that gather and classify source-backed claims. The point of that is not to pretend bias disappears, but to avoid me manually selecting the evidence myself. I intend for it to remain current and grow. The system is close to fully automated, though ongoing evidence collection at scale is still limited mostly by cost. The name is an homage to the early days of Web 1.0 and Hot or Not, which was a main competitor of mine as the creator of FaceTheJury.com, but I think it works well here. The backend and frontend are running on Cloudflare Workers with D1. It's coded in vanilla JavaScript. https://magaornot.ai March 23, 2026 at 12:55AM

Show HN: Revise – An AI Editor for Documents https://ift.tt/Vy8AdOX

Show HN: Revise – An AI Editor for Documents I started building this 10 months ago, largely using agentic coding tools. I've stayed very involved in the code base and architecture, and have never moved faster in my life as a dev. The word processor engine and rendering layer are all built from scratch - the only 3rd party library I used was the excellent Y.js for the CRDT stack. Would love some feedback! https://revise.io March 22, 2026 at 08:28PM

Show HN: Brand Toolkit – Claude Code plugin for framework-driven brand building https://ift.tt/zxFJA0E

Show HN: Brand Toolkit – Claude Code plugin for framework-driven brand building https://ift.tt/akKSuYp March 22, 2026 at 11:56PM

Show HN: AI SDLC Scaffold, repo template for AI-assisted software development https://ift.tt/PqKaAGV

Show HN: An open-source safety net for home hemodialysis https://ift.tt/y0kftMx

Show HN: An open-source safety net for home hemodialysis https://safehemo.com/ March 17, 2026 at 07:48AM

Show HN: Fossilware – a community archive of retro hardware, software, and games https://ift.tt/MAyFrbS

Show HN: Fossilware – a community archive of retro hardware, software, and games i built a small site to collect memories of the things we grew up with: floppy drives, Game Boys, cassette tapes, forgotten software, classic games. the tech stack is React, Supabase and Vercel. fair warning: the items on there right now were seeded by AI to get things started. the goal is for it to grow through community submission. there's a submit form, no account needed. i'd love to gather some early feedback and get some more ideas. something i was thinking about in the future is having users create accounts to favorite items and comment their own personal experiences with items. right now everything requires manual approval but in the future i'd like to push that towards the community. thanks for looking! https://ift.tt/GoRYJX5 March 21, 2026 at 12:33AM

Show HN: I Built a MTA Subway Display So I'd Stop Checking My Phone https://ift.tt/zQikrFo

Show HN: I Built a MTA Subway Display So I'd Stop Checking My Phone https://twitter.com/pirosb3/status/2034370959977619513 March 20, 2026 at 11:13PM

Show HN: Mavera – Predict audience response with GANs, not LLM sentiment https://ift.tt/wiceRkB

Show HN: Mavera – Predict audience response with GANs, not LLM sentiment Mavera is an audience intelligence API. Give it a message, product prototype, or creative asset and it returns a predicted distribution of emotional and behavioral responses across your target stakeholder population. This is the best way to test your assumptions before you spend or push anything live. To show this in practice, we ran all 101 Super Bowl LX ads through Mavera on game night: https://ift.tt/BUVGQ7T. We simulated how audiences would emotionally and behaviorally respond by platform and segment. We returned a distribution rather than a single score as part of a full analysis of each ad in under 4 hours. The model is a GAN adapted for language, emotion, and cognition. A generator produces synthetic audience responses and a discriminator validates them against human benchmarks. Scoring follows a feel-think-act framework: emotional activation, cognitive framing, behavioral prediction. We validated scoring against the Harvard/Illinois OASIS benchmark. MAE on emotional response is 0.02-0.15 versus 1.0-2.5+ for GPT and Claude. Every response includes a confidence score and a hallucination risk score. You can also build-in spread of opinion, response stability, and impact of news/market context scores to your outputs. The API is OpenAI-compatible. Change the base URL to app.mavera.io/api/v1, add a persona_id, and you are running against 50+ pre-built personas or you can customize your own. Sub-100ms latency at P99. Free API key and docs at https://ift.tt/IjyuPTR. https://ift.tt/IjyuPTR March 17, 2026 at 03:54AM

Show HN: Tmux-IDE, OSS agent-first terminal IDE https://ift.tt/TRx8US2

Show HN: Tmux-IDE, OSS agent-first terminal IDE Hey HN, Small OSS project that i created for myself and want to share with the community. It's a declarative, scriptable, terminal-based IDE focussed on agentic engineering. That's a lot of jargon, but essentially its a multi-agent IDE that you start in your terminal. Why is that relevant? Thanks to tmux and SSH, it means that you have a really simple and efficient way to create your own always-on coding setup. Boot into your IDE through ssh, give a prompt to claude and close off your machine. In tmux-ide claude will keep working. The tool is intentionally really lightweight, because I think the power should come from the harnesses that you are working with. I'm hoping to share this with the community and get feedback and suggestions to shape this project! I think that "remote work" is directionally correct, because we can now have extremely long-running coding tasks. But I also think we should be able to control and orchstrate that experience according to what we need. The project is 100% open-source, and i hope to shape it together with others who like to work in this way too! Github: https://ift.tt/U1tz0Ve Docs: https://ift.tt/5U8Jp7Q https://ift.tt/pxiOY3r March 19, 2026 at 12:46AM

Show HN: Will my flight have Starlink? https://ift.tt/ODoARaE

Show HN: Will my flight have Starlink? Hey HN, If you’ve been lucky enough to be on a flight with Starlink, you understand the hype. It actually works! However, its availability on flights is patchy and hard to predict. So we built a database of all airlines that have rolled out Starlink (beyond just a trial), and a flight search tool to predict it. Plug in a flight number and date, and we'll estimate the likelihood of Starlink on-board based on aircraft type and tail number. If you don’t have any trips coming up, you can also look up specific routes to see what flights offer Starlink. You can find it here: https://ift.tt/CKLPpdl . - I wanted to add a few notes on how this works too. There are three things we check, in order, when we answer a query: - Does this airline have Starlink? - Does this aircraft body have Starlink? - Does this specific aircraft have Starlink? Only a few airlines at all have Starlink right now: United, Hawaiian, Alaskan, Air France, Qatar, JSX, and a handful of others. So if an aircraft is operated by any other airline, we can issue a blanket no immediately. Then, we check the actual body that's flying on the plane. Airlines usually publish equipment assignments in advance, and they're also rolling out Starlink body-by-body. So we know, for instance, that all JSX E145s have Starlink and that none of Air France's A320s have Starlink. (You can see a summary of our data at https://ift.tt/YWQftID , though the live logic has a few rules not encoded there.) If there's a complete match at the body type level, we can confidently tell you your flight will have Starlink. However, in most cases, the airline has only rolled out a partial upgrade to that aircraft type. In that case, we need to drill down a little more and figure out exactly which plane is flying on your route. We can do this by looking up the 'tail number' (think of it as a license plate for the plane). Unfortunately , the tail number is usually only assigned a few days before a flight. So, before that, the best we can do is calculate the probability that your plane will be assigned an aircraft with Starlink enabled. To do this, we had to build a mapping of aircraft tails to Starlink status. Here, I have to thank online airline enthusiasts who maintain meticulous spreadsheets and forum threads to track this data! As I understand it, they usually get this data from airline staff who are enthusiastic about Starlink rollouts, so it's a reliable, frequently updated source. Most of our work was finding each source, normalizing their formats, building a reliable & responsible system to pull them in, and then tying them together with our other data sources. Basically, it's a data normalization problem! I used to work on financial data systems and I was surprised how similar this problem was. - Starlink itself is also a pretty cool technology. I also wrote a blog post ( https://ift.tt/5kOUvhP ) on why it's so much better than all the other aircraft wifi options out there. At a high level, it's only possible because rocket launches are so cheap nowadays, which is incredibly cool. The performance is great, so it's well worth planning your flights around it where possible. Right now, your best bet in the US is on United regional flights and JSX/Hawaiian. Internationally, Qatar is the best option (though obviously not right now), with Air France a distance second. This will change throughout the year as more airlines roll it out though, and we'll keep our database updated! March 19, 2026 at 12:29AM

Show HN: Hanoi-CLI – simulate and optimize pod placement in Kubernetes https://ift.tt/ecx7VfQ

Show HN: Hanoi-CLI – simulate and optimize pod placement in Kubernetes Hi HN, I built hanoi-cli, a small CLI tool that analyzes how pods are distributed across Kubernetes nodes and suggests a better placement. The idea came from a recurring issue: clusters often end up imbalanced even when requests/limits are set properly. Some nodes get overloaded while others stay underutilized. Would love feedback. https://ift.tt/hwMq8ct March 18, 2026 at 11:14PM

Show HN: Crust – A CLI framework for TypeScript and Bun https://ift.tt/6ZEhd59

Show HN: Crust – A CLI framework for TypeScript and Bun We've been building Crust ( https://crustjs.com/ ), a TypeScript-first, Bun-native CLI framework with zero dependencies. It's been powering our core product internally for a while, and we're now open-sourcing it. The problem we kept running into: existing CLI frameworks in the JS ecosystem are either minimal arg parsers where you wire everything yourself, or heavyweight frameworks with large dependency trees and Node-era assumptions. We wanted something in between. What Crust does differently: - Full type inference from definitions — args and flags are inferred automatically. No manual type annotations, no generics to wrangle. You define a flag as type: "string" and it flows through to your handler. - Compile-time validation — catches flag alias collisions and variadic arg mistakes before your code runs, not at runtime. - Zero runtime dependencies — @crustjs/core is ~3.6kB gzipped (21kB install). For comparison: yargs is 509kB, oclif is 411kB. - Composable modules — core, plugins, prompts, styling, validation, and build tooling are all separate packages. Install only what you need. - Plugin system — middleware-based with lifecycle hooks (preRun/postRun). Official plugins for help, version, and shell autocompletion. - Built for Bun — no Node compatibility layers, no legacy baggage. Quick example: import { Crust } from "@crustjs/core"; import { helpPlugin, versionPlugin } from "@crustjs/plugins"; const main = new Crust("greet") .args([{ name: "name", type: "string", default: "world" }]) .flags({ shout: { type: "boolean", short: "s" } }) .use(helpPlugin()) .use(versionPlugin("1.0.0")) .run(({ args, flags }) => { const msg = `Hello, ${args.name}!`; console.log(flags.shout ? msg.toUpperCase() : msg); }); await main.execute(); Scaffold a new project: bun create crust my-cli Site: https://crustjs.com GitHub: https://ift.tt/thosJWV Happy to answer any questions about the design decisions or internals. https://ift.tt/s0Wvt3T March 17, 2026 at 11:43AM

Show HN: FireClaw – Open-source proxy defending AI agents from prompt injection https://ift.tt/8W1i5FV

Show HN: FireClaw – Open-source proxy defending AI agents from prompt injection Hey HN, We built FireClaw because we kept watching AI agents get owned by prompt injection through web content. The agent fetches a page, the page says "ignore previous instructions," and suddenly your agent is leaking data or running commands it shouldn't. The existing solutions detect injection after the fact. We wanted to prevent it. FireClaw is a security proxy that sits between your AI agent and the web. Every fetch passes through a 4-stage pipeline: 1. DNS blocklist check (URLhaus, PhishTank, community feed) 2. Structural sanitization (strip hidden CSS, zero-width Unicode, encoding tricks) 3. Isolated LLM summarization (hardened sub-process with no tools or memory) 4. Output scanning with canary tokens (detect if content bypassed summarization) The key insight: even if Stage 3's LLM gets injected, it has no tools, no memory, and no access to your data. It can only return text — which still gets scanned in Stage 4. The attacker hits a dead end. Other design decisions: - No bypass mode. The pipeline is fixed. If your agent gets compromised, it can't disable FireClaw. - Community threat feed — instances anonymously share detection metadata (domain, severity, detection count) to build a shared blocklist. No page content is ever sent. - Runs on a Raspberry Pi as a physical appliance with an OLED display that shows real-time stats and lights up with animated flames when it catches a threat. We searched the literature and open source extensively — no one else is doing proxy-based defense for agent prompt injection. Detection exists, sandboxing exists, but an inline proxy that sanitizes before content reaches the agent's context? We couldn't find it. 200+ detection patterns, JSONL audit logging, domain trust tiers, rate limiting, and cost controls. AGPLv3 licensed. Website: https://fireclaw.app Would love feedback from anyone working on AI agent security. What are we missing? What attack vectors should we add to the pattern database? https://ift.tt/sLEPgdc March 17, 2026 at 11:28PM

Show HN: F0lkl0r3.dev – a searchable, interlinked map of computing history https://ift.tt/g9SKXyI

Show HN: F0lkl0r3.dev – a searchable, interlinked map of computing history I love reading about the early days of computing, but finding the alpha in raw historical archives can be tough. I built f0lkl0r3.dev over the weekend to fix that. It takes nearly 1,000 oral histories from the Computer History Museum and makes them explorable, searchable, interconnected, and multimodal. To build it, I used the Gemini APIs (via ai.dev) to process the massive volume of unstructured interview text, pulling out the timelines, machines, and people so they could be cross-referenced. The app itself was built with Antigravity, next steps will be to add images and videos. You can search by specific mainframes, browse by era in the timeline, or just read the Apocrypha section for weird historical anecdotes. Enjoy the rabbit hole! I hope it distracts and inspires at least a few more people than me today. :) https://f0lkl0r3.dev March 17, 2026 at 11:00PM

Show HN: March Madness Bracket Challenge for AI Agents Only https://ift.tt/r5Zvjcd

Show HN: March Madness Bracket Challenge for AI Agents Only I built a March Madness bracket challenge for AI agents, not humans. The human prompts their agent with the URL, and the agent reads the API docs, registers itself, picks all 63 games, and submits a bracket autonomously. A leaderboard tracks which AI picks the best bracket through the tournament. The interesting design problem was building for an agent-first user. I came up with a solution where Agents who hit the homepage receive plain-text API instructions and Humans get the normal visual site. Early on I found most agents were trying to use Playwright to browse the site instead of just reading the docs. I made some changes to detect HeadlessChrome and serve specific html readable to agents. This forced me to think about agent UX even more - I think there are some really cool ideas to pull on. The timeline introduced an interesting dynamic. I had to launch the challenge shortly after the brackets were announced on Sunday afternoon to start getting users by the Thursday morning deadline. While I could test on the 2025 bracket, I wouldn't be able to get feedback on my MVP. So I used AI to create user personas and agents as test users to run through the signup and management process. It gave me valuable reps to feel confident launching. The stack is Next.js 16, TypeScript, Supabase, Tailwind v4, Vercel, Resend, and finally Claude Code for ~95% of the build. Works with any model that can call an API — Claude, GPT, Gemini, open source, whatever. Brackets are due Thursday morning before the First Round tips off. Bracketmadness.ai https://ift.tt/vxQjCeb March 17, 2026 at 07:56PM

Show HN: Claude Code skills that build complete Godot games https://ift.tt/GDBVMqC

Show HN: Claude Code skills that build complete Godot games I’ve been working on this for about a year through four major rewrites. Godogen is a pipeline that takes a text prompt, designs the architecture, generates 2D/3D assets, writes the GDScript, and tests it visually. The output is a complete, playable Godot 4 project. Getting LLMs to reliably generate functional games required solving three specific engineering bottlenecks: 1. The Training Data Scarcity: LLMs barely know GDScript. It has ~850 classes and a Python-like syntax that will happily let a model hallucinate Python idioms that fail to compile. To fix this, I built a custom reference system: a hand-written language spec, full API docs converted from Godot's XML source, and a quirks database for engine behaviors you can't learn from docs alone. Because 850 classes blow up the context window, the agent lazy-loads only the specific APIs it needs at runtime. 2. The Build-Time vs. Runtime State: Scenes are generated by headless scripts that build the node graph in memory and serialize it to .tscn files. This avoids the fragility of hand-editing Godot's serialization format. But it means certain engine features (like `@onready` or signal connections) aren't available at build time—they only exist when the game actually runs. Teaching the model which APIs are available at which phase — and that every node needs its owner set correctly or it silently vanishes on save — took careful prompting but paid off. 3. The Evaluation Loop: A coding agent is inherently biased toward its own output. To stop it from cheating, a separate Gemini Flash agent acts as visual QA. It sees only the rendered screenshots from the running engine—no code—and compares them against a generated reference image. It catches the visual bugs text analysis misses: z-fighting, floating objects, physics explosions, and grid-like placements that should be organic. Architecturally, it runs as two Claude Code skills: an orchestrator that plans the pipeline, and a task executor that implements each piece in a `context: fork` window so mistakes and state don't accumulate. Everything is open source: https://ift.tt/L94pIta Demo video (real games, not cherry-picked screenshots): https://youtu.be/eUz19GROIpY Blog post with the full story (all the wrong turns) coming soon. Happy to answer questions. https://ift.tt/L94pIta March 16, 2026 at 11:07PM

Show HN: Buda – AI agents forming a company (Claws running a startup) https://ift.tt/rC54Uyn

Show HN: Buda – AI agents forming a company (Claws running a startup) https://buda.im/ March 16, 2026 at 10:38PM

Show HN: Git Quest – I turned your GitHub commit history into an idle RPG https://ift.tt/h6Wc29l

Show HN: Git Quest – I turned your GitHub commit history into an idle RPG Hey HN, I built Git Quest, it reads your public GitHub history and turns it into an idle RPG character. How it works: - Your most-used language determines your class (TypeScript → Paladin, Python → Sage, etc.) - Commits generate Power and XP - Your character auto-battles dungeons while you code – no active play needed - Enemies drop loot across 5 rarity tiers - Live leaderboard ranks developers It only reads public GitHub data. I built it because I wanted something that rewards coding consistency without being another "streak" tracker. The idle mechanic means prolific coders naturally progress faster, but you don't have to babysit it. Would love feedback on the game loop and whether the class/language mapping feels right. https://ift.tt/nhZIaRq https://ift.tt/nhZIaRq March 16, 2026 at 09:44PM

Show HN: LLMonster Rancher https://ift.tt/sYvpSMl

Show HN: LLMonster Rancher I've long held a bit of nostalgia for the old PlayStation game Monster Rancher. You could "discover" monsters by popping in any arbitrary CD in your house – music, a PS game, a PC game, whatever – and it would generate a monster based on the disc's metadata, and add it to your ranch. It was a game about collecting, breeding, and battling these monsters. The generated monster usually had nothing at all to do with the disc's content, of course. There were some specific discs that were hard-coded in that would give you a relevant monster, but not a ton. It was a fairly niche thing, though, and the death of CDs sort of killed the whole idea. But now in the age of LLMs, it feels like maybe the time has come back around for something like this to be pretty fun again, so I've implemented it as an Agent Skill that: 1. accepts a URL and reads the content (or any input, really) 2. follows some standard guidance on generating monster JSON for it 3. uses a Gemini image model to generate a monster avatar 4. renders it all in a fun little trading card image 5. allows you to breed them into hybrids, battle them, and share them to Github Gists This was mainly a scratch-my-own-itch nostalgia indulgence. I briefly considered doing this as a full blown site, but agent skills give a fair bit more interactive flexibility while not costing me a dime. You can just point your agent (Claude Code, etc) to aiwebb/llmonster-rancher and tell it to get going. Hope y'all have fun with it. https://ift.tt/u6gi9fb March 16, 2026 at 07:53PM

Show HN: Detach – Mobile UI for managing AI coding agents from your phone https://ift.tt/rOabCPk

Show HN: Detach – Mobile UI for managing AI coding agents from your phone Hey guys, about two months ago I started this side-project for "asynchronous coding" where I can prompt Claude Code from my mobile on train rides, get a notification when it's done and then review and commit the code from the app itself. Since then I've been using it on and off for a while. I finally decided to polish it and publish it in case someone might find it useful. It's a self-hosted PWA with four panels: Agent (terminal running Claude Code), Explore (file browser with syntax highlighting), Terminal (standard bash shell), and Git (diff viewer with staging/committing). It can run on a cheap VPS and a fully functioning setup is provided (using cloud-init and simple bash scripts). This fits my preferred workflow where I stay in the loop: I review every diff, control git manually, and approve or reject changes before they go anywhere. Stack: Go WebSocket bridge, xterm.js frontend, Ubuntu sandbox container. Everything runs in Docker. Works with any CLI AI assistant, though I've only used it with Claude Code. Side project, provided as-is under MIT license. Run at your own risk. Feedback and MRs welcome. EDIT: Removed redundant text https://ift.tt/5FADkit March 16, 2026 at 12:40AM

Show HN: Lengpal – simple video chat for language exchange https://ift.tt/wmoic2x

Show HN: Lengpal – simple video chat for language exchange Hi HN, I built a small tool called Lengpal. It’s basically a very simple video chat room made for language exchange. Most people I know who do language exchanges just use Zoom, Meet, or Teams. It works, but those tools aren’t really designed for it. One thing that always comes up is managing the speaking time so both people get equal practice. So the only thing we focused on for now is a built-in timer that lets you split the session between languages. For example 30 minutes Spanish, 30 minutes English. The idea is intentionally simple. You create a room, send the link to your partner, and start the session. No matching, no complicated setup. We just launched today and are trying to see if this simple approach actually helps people doing exchanges. Website: https://lengpal.com We also launched on Product Hunt today if anyone is curious: https://ift.tt/hgf7VF6 Would love to hear what you think. https://ift.tt/mqsGJ5l March 15, 2026 at 11:29PM

Show HN: Sway, a board game benchmark for quantum computing https://ift.tt/N1mg8DL

Show HN: Sway, a board game benchmark for quantum computing A popular philosophy in the HN community is that inventing problems to be solved by a technology is antithetical to the user experience. Much to the horror of some, I did just that to discover/invent this game. I started with the structure of quantum com putation and asked what kind of problem benefits from it. The answer was surprisingly narrow, but this was one of the results. Enjoy! https://ift.tt/OipdlWG March 15, 2026 at 11:20PM

Show HN: GDSL – 800 line kernel: Lisp subset in 500, C subset in 1300 https://ift.tt/STsHxdF

Show HN: GDSL – 800 line kernel: Lisp subset in 500, C subset in 1300 https://firthemouse.github.io/ March 15, 2026 at 10:40PM

Show HN: Hacker News archive (47M+ items, 11.6GB) as Parquet, updated every 5m https://ift.tt/a8pYSOt

Show HN: Hacker News archive (47M+ items, 11.6GB) as Parquet, updated every 5m https://ift.tt/0MyWqQm March 15, 2026 at 12:12AM

Show HN: Learn Arabic with spaced repetition and comprehensible input https://ift.tt/SxhC2b8

Show HN: Learn Arabic with spaced repetition and comprehensible input Sharing a friends first-ever Rails application, dedicated to Arabic learning, from 0 to 1. Pulls language learning methods from Anki, comprehensible input and more. https://abjadpro.com March 14, 2026 at 11:24PM

Show HN: KeyID – Free email and phone infrastructure for AI agents (MCP) https://ift.tt/tHDqbMz

Show HN: KeyID – Free email and phone infrastructure for AI agents (MCP) https://keyid.ai/ March 14, 2026 at 11:23PM

Show HN: Hedra – an open-world 3D game I wrote from scratch before LLMs https://ift.tt/4XvOWQ1

Show HN: Hedra – an open-world 3D game I wrote from scratch before LLMs With the current inflow of LLM aided software, I thought I would share a cool "hand-coded" project from the previous era (I wrote this in highschool so roughly ~8 years ago). Hedra is an open world 3d game written from scratch using only OpenGL and C#. It has quite a few cool features like infinite generation, skinned animated mesh rendering, post processing effects, etc. Originally the physics engine was also written from scratch but i swapped for the more reliable bulletphysics. https://ift.tt/pPR6lJd March 14, 2026 at 10:35PM

Show HN: Svglib a SVG parser and renderer for Windows https://ift.tt/V2fPSrc

Show HN: Svglib a SVG parser and renderer for Windows svglib is a SVG file parser and renderer library for Windows. It uses Direct2D for GPU assisted rendering and XMLLite for XML parsing. This is meant for Win32 applications and games to easily display SVG images. https://ift.tt/fzhBC64 March 10, 2026 at 10:04PM

Show HN: Channel Surfer – Watch YouTube like it’s cable TV https://ift.tt/ODk5VaI

Show HN: Channel Surfer – Watch YouTube like it’s cable TV I know, it's a very first-world problem. But in my house, we have a hard time deciding what to watch. Too many options! So I made this to recreate Cable TV for YouTube. I made it so it runs in the browser. Quickly import your subscriptions in the browser via a bookmarklet. No accounts, no sign-ins. Just quickly import your data locally. https://ift.tt/rIJoCO7 March 11, 2026 at 09:34PM

Show HN: Mesa – A collaborative canvas IDE built for agent-first development https://ift.tt/R2HKjN3

Show HN: Mesa – A collaborative canvas IDE built for agent-first development Hi HN - I'm Ryan a product designer who codes, and I built Mesa. Current IDEs feel wrong for the type of development being done now - the focus is still on files. Mesa puts the focus on the full workflow: your agent, terminal, browser, and files all live as equal nodes on a canvas with full multiplayer support. (think figma but for code) I was tired of the overhead of switching windows, tabs, and terminals across multiple projects. Inspired by TouchDesigner and Factorio, I wanted something more fluid and visual. Been using it as a total replacement for Cursor at work every day now. Being able to see multiple repos at once and control agents on each without navigating windows has freed up my headspace and increased productivity. It's free to try — would love to know what you think! https://ift.tt/C7Ghr5H March 13, 2026 at 10:17PM

Show HN: Web-Based ANSI Art Viewer https://ift.tt/GYj4KfN

Show HN: Web-Based ANSI Art Viewer My love letter to ANSI art. Full width rendering, scrolling by baud rate, text is selectable, and more. There are some example links at the top if you're feeling lucky. https://sure.is/ansi/ March 10, 2026 at 03:40PM

Show HN: OneCLI – Vault for AI Agents in Rust https://ift.tt/dGPLwex

Show HN: OneCLI – Vault for AI Agents in Rust We built OneCLI because AI agents are being given raw API keys. And it's going about as well as you'd expect. We figured the answer isn't "don't give agents access," it's "give them access without giving them secrets." OneCLI is an open-source gateway that sits between your AI agents and the services they call. You store your real credentials once in OneCLI's encrypted vault, and give your agents placeholder keys. When an agent makes an HTTP call through the proxy, OneCLI matches the request by host/path, verifies the agent should have access, swaps the placeholder for the real credential, and forwards the request. The agent never touches the actual secret. It just uses CLI or MCP tools as normal. Try it in one line: docker run --pull always -p 10254:10254 -p 10255:10255 -v onecli-data:/app/data ghcr.io/onecli/onecli The proxy is written in Rust, the dashboard is Next.js, and secrets are AES-256-GCM encrypted at rest. Everything runs in a single Docker container with an embedded Postgres (PGlite), no external dependencies. Works with any agent framework (OpenClaw, NanoClaw, IronClaw, or anything that can set an HTTPS_PROXY). We started with what felt most urgent: agents shouldn't be holding raw credentials. The next layer is access policies and audit, defining what each agent can call, logging everything, and requiring human approval before sensitive actions go through. It's Apache-2.0 licensed. We'd love feedback on the approach, and we're especially curious how people are handling agent auth today. GitHub: https://ift.tt/1rCywvt Site: https://onecli.sh https://ift.tt/1rCywvt March 12, 2026 at 11:41PM

Show HN: A2Apex – Test, certify, and discover trusted A2A agents https://ift.tt/qGVEfCM

Show HN: A2Apex – Test, certify, and discover trusted A2A agents Hey HN, I built A2Apex ( https://a2apex.io ) — a testing and reputation platform for AI agents built on Google's A2A protocol. The problem: AI agents are everywhere, but there's no way to verify they actually work. No standard testing. No directory of trusted agents. No reputation system. What A2Apex does: - Test — Point it at any A2A agent URL. We run 50+ automated compliance checks: agent card validation, live endpoint testing, state machine verification, streaming, auth, error handling. - Certify — Get a 0-100 trust score with Gold/Silver/Bronze badges you can embed in your README or docs. - Get Listed — Every tested agent gets a public profile page in the Agent Directory with trust scores, skills, test history, and embeddable badges. Think of it as SSL Labs (testing) + npm (directory) + LinkedIn (profiles) — for AI agents. Stack: Python/FastAPI, vanilla JS, SQLite. No frameworks, no build tools. Runs on a Mac mini in Wyoming. Free: 5 tests/month. Pro: $29/mo. Startup: $99/mo. Try it at https://app.a2apex.io I'm a dragline operator at a coal mine — built this on nights and weekends using Claude. Would love feedback from anyone building A2A agents or thinking about agent interoperability. https://a2apex.io March 12, 2026 at 11:10PM

Show HN: We open sourced Vapi – UI included https://ift.tt/uiI8Gs3

Show HN: We open sourced Vapi – UI included We kept hitting the same wall building voice AI systems. Pipecat and LiveKit are great projects, genuinely. But getting it to production took us weeks of plumbing - wiring things together, handling barge-ins, setting up telephony, Knowledge base, tool calls, handling barge in etc. And every time we needed to tweak agent behavior, you were back in the code and redeploying. We just wanted to change a prompt and test it in 30 seconds. Thats why Vapi retell etc exist. So we wrote the entire code and open sourced it as a Visual drag-and-drop for voice agents ( same as vapi or n8n for voice). Built on a Pipecat fork and BSD-2, no strings attached. Tool calls, knowledge base, variable extraction, voicemail detection, call transfer to humans, multilingual support, post-call QA, background noise suppression, and a website widget are all included. You're not paying per-minute fees to a middleman wrapping the same APIs you'd call directly. You can set it up with a simple docker command. It comes pre-wired with Deepgram, Cartesia, OpenAI , Speechmatics Sarvam for STT, same for TTS, and OpenAI, Gemini, groq, Openrouter, Azure on the LLM side. Telephony works out of the box with Twilio, Vonage , CLoudonix and Asterisk for both inbound and outbound. There's a hosted version at app.dograh.com if self-hosting isn't your thing. Repo: github.com/dograh-hq/dograh Video walkthrough: https://youtu.be/sxiSp4JXqws We built this out of frustration, not a thesis. The tool is free to use and fully open source (and will always remain so), happy to answer questions about the data or how we built it. https://ift.tt/2NBAKeg March 12, 2026 at 10:03PM

Show HN: Rewriting Mongosh in Golang Using Claude https://ift.tt/UkxS7ch

Show HN: Rewriting Mongosh in Golang Using Claude https://ift.tt/AGOQcwa March 11, 2026 at 10:55PM

Show HN: Loquix – Open-source Web Components for AI chat interfaces https://ift.tt/gnL3FsA

Show HN: Loquix – Open-source Web Components for AI chat interfaces https://ift.tt/Ajhfv3M March 11, 2026 at 10:19PM

Show HN: StreamHouse – Open-source Kafka alternative https://ift.tt/Y9hptqR

Show HN: StreamHouse – Open-source Kafka alternative Hey HN, I built StreamHouse, an open-source streaming platform that replaces Kafka's broker-managed storage with direct S3 writes. The goal: same semantics, fraction of the cost. How it works: Producers batch and compress records, a stateless server manages partition routing and metadata (SQLite for dev, PostgreSQL for prod), and segments land directly in S3. Consumers read from S3 with a local segment cache. No broker disks to manage, no replication factor to tune — S3 gives you 11 nines of durability out of the box. What's there today: - Producer API with batching, LZ4 compression, and offset tracking (62K records/sec) - Consumer API with consumer groups, auto-commit, and multi-partition fanout (30K+ records/sec) - Kafka-compatible protocol (works with existing Kafka clients) - REST API, gRPC API, CLI, and a web UI - Docker Compose setup for trying it locally in 5 minutes What's not there yet: - Battle-tested production deployments (I'm the only user so far) - Connectors for consumers to immediately connect to (i.e clickhouse, elastic search etc) The cost model is what motivated this. Kafka's storage costs scale with replication factor × retention × volume. With S3 at $0.023/GB/month, storing a TB of events costs ~$23/month instead of hundreds on broker EBS volumes. Written in Rust, 15 crates thus far. Apache 2.0 licensed. GitHub: https://ift.tt/hu5IGb6 How it works blog on my main website: https://ift.tt/whu02k3 Happy to answer questions about the architecture, tradeoffs, or what I learned building this. https://ift.tt/hu5IGb6 March 11, 2026 at 09:14PM

Show HN: I built an ISP infrastructure emulator from scratch with a custom vBNG https://ift.tt/RKbmUQr

Show HN: I built an ISP infrastructure emulator from scratch with a custom vBNG Demo: https://ift.tt/espNjWG GitHub: https://ift.tt/eJzhcuU Aether is a multi-BNG (Broadband Network Gateway) ISP infrastructure lab built almost from scratch that emulates IPoE IPv4 subscriber management end-to-end. It supports IPoE/Ipv4 networks and runs a python-based vBNG with RADIUS AAA, per-subscriber traffic shaping, and traffic simulation emulated on Containerlab. It is also my first personal networking project, built roughly over a month. Motivations behind the project I'm a CS sophomore. About three years ago, I was assigned, as an intern, to build a OSS/BSS platform for a regional ISP by myself without mentoring. Referencing demo.splynx.com , I developed most of the BSS side ( bookkeeping, accounting, inventory management ), but, in terms of networking, I managed to install and setup RADIUS and that was about it. I didn't have anyone to mentor me or ask questions to, so I had given up then. Three years later, I decided to try cracking it again. This project is meant to serve as a learning reference for anyone who's been in that same position i.e staring at closed-source vendor stacks without proper guidance. This is absolutely not production-grade, but I hope it gives someone a place to start. Architecture overview The core component, the BNG, runs on an event-driven architecture where state changes are passed around as messages to avoid handling mutexes and locks. The session manager is the sole owner of the session state. To keep it clean and predictable, the direBNG never accepts external inputctly. The one exception is the Go RADIUS CoA daemon, which passes CoA messages in via IPC sockets. Everything the BNG produces(events, session snapshots) gets pushed to Redis Streams, where the bng-ingestor picks them up, processes them, and persists them. Simulation and meta-configs I am generating traffic through a simulator node that mounts the host's docker socket and runs docker exec commands on selected hosts. The topology.yaml used by Containerlab to define the network topology grows bigger as more BNG's and access nodes are added. So aether.config.yaml, a simpler configuration, is consumed by the configuration pipeline to generate the topology.yaml and other files (nginx.conf, kea-dhcp.conf, RADIUS clients.conf etc.) Known Limitations - Multiple veth hops through the emulated topology add significant overhead. Profiling with iperf3 (-P 10 -t 10, 9500 MTU, 24 vCPUs) shows BNG→upstream at ~24 Gbit/s, but host→BNG→upstream drops to ~3.5 Gbit/s. The 9500 MTU also isn't representative of real ISP deployments. This gets worse when the actual network is reintroduced capping my throughput to 1.6 Gbits/sec in local. - The circuit ID format (1/0/X) is non-standard. I simplified it for clarity. - No iBGP or VLAN support. - No Ipv6 support. I wanted to target IPv4 networks from the start to avoid getting too much breadth without a lot of depth. Nearly everything I know about networking (except some sections from AWS) I learned building this. A lot was figured out on the fly, so engineers will likely spot questionable decisions in the codebase. I'd genuinely appreciate that feedback. Questions - Currently, the circuit where the user connects is arbitrarily decided by the demo user. In a real system with thousands of circuits, it'd be very difficult to properly assess which circuit the customer might connect to. When adding a new customer to a service, how does the operator decide, based on customer's location, which circuit to provide the service to ? https://ift.tt/KvfXZGD March 11, 2026 at 08:38PM

Show HN: Satellite imagery object detection using text prompts https://ift.tt/3jlR5gE

Show HN: Satellite imagery object detection using text prompts I built a browser-based tool for detecting objects in satellite imagery using vision-language models (VLMs). You draw a polygon on the map and enter a text prompt such as "swimming pools", "oil tanks", or "buses". The system scans the selected area tile-by-tile and returns detections projected back onto the map as GeoJSON. Pipeline: select area and zoom level, split the region into mercantile tiles, run each tile with the prompt through a VLM, convert predicted bounding boxes to geographic coordinates (WGS84), and render the results back on the map. It works reasonably well for distinct structures in a zero-shot setting. occluded objects are still better handled by specialized detectors like YOLO models. There is a public demo and no login required. I am mainly interested in feedback on detection quality, performance tradeoffs between VLMs and specialized detectors, and potential real-world use cases. https://ift.tt/qZ05e4N March 9, 2026 at 02:52PM

Show HN: Agentic Data Analysis with Claude Code https://ift.tt/xuydoig

Show HN: Agentic Data Analysis with Claude Code Hey HN, as a former data analyst, I’ve been tooling around trying to get agents to do my old job. The result is this system that gets you maybe 80% of the way there. I think this is a good data point for what the current frontier models are capable of and where they are still lacking (in this case — hypothesis generation and general data intuition). Some initial learnings: - Generating web app-based reports goes much better if there are explicit templates/pre-defined components for the model to use. - Claude can “heal” broken charts if you give it access to chart images and run a separate QA loop. Would either feedback from the community or to hear from others that have tried similar things! https://ift.tt/zvhU8OR March 10, 2026 at 11:44PM

Show HN: DenchClaw – Local CRM on Top of OpenClaw https://ift.tt/USBzH2n

Show HN: DenchClaw – Local CRM on Top of OpenClaw Hi everyone, I am Kumar, co-founder of Dench ( https://denchclaw.com ). We were part of YC S24, an agentic workflow company that previously worked with sales floors automating niche enterprise tasks such as outbound calling, legal intake, etc. Building consumer / power-user software always gave me more joy than FDEing into an enterprise. It did not give me joy to manually add AI tools to a cloud harness for every small new thing, at least not as much as completely local software that is open source and has all the powers of OpenClaw (I can now talk to my CRM on Telegram!). A week ago, we launched Ironclaw, an Open Source OpenClaw CRM Framework ( https://ift.tt/CQY50SB ) but people confused us with NearAI’s Ironclaw, so we changed our name to DenchClaw ( https://denchclaw.com ). OpenClaw today feels like early React: the primitive is incredibly powerful, but the patterns are still forming, and everyone is piecing together their own way to actually use it. What made React explode was the emergence of frameworks like Gatsby and Next.js that turned raw capability into something opinionated, repeatable, and easy to adopt. That is how we think about DenchClaw. We are trying to make it one of the clearest, most practical, and most complete ways to use OpenClaw in the real world. Demo: https://www.youtube.com/watch?v=pfACTbc3Bh4#t=43 npx denchclaw It has a CRM focus because we asked a couple dozen hard-core OpenClaw users "what do you actually do", and it was sales automation, lead enrichment, biz dev, creating slides, linkedin outreach, email/notion/calendar stuff, and it's always painful to set up. But I use DenchClaw daily for almost everything I do. It also works as a coding agent like Cursor - DenchClaw built DenchClaw. I am addicted now that I can ask it, “hey in the companies table only show me the ones who have more than 5 employees” and it updates it live than me having to manually add a filter. On Dench, everything sits in a file system, the table filters, views, column toggles, calendar/gantt views, etc, so OpenClaw can directly work with it using Dench’s CRM skill. The CRM is built on top of DuckDB, the smallest, most performant and at the same time also feature rich database we could find. Thank you DuckDB team! It creates a new OpenClaw profile called “dench”, and opens a new OpenClaw Gateway… that means you can run all your usual openclaw commands by just prefixing every command with `openclaw --profile dench` . It will start your gateway on port 19001 range. You will be able to access the DenchClaw frontend at localhost:3100. Once you open it on Safari, just add it to your Dock to use it as a PWA. Think of it as Cursor for your Mac (also works on Linux and Windows) which is based on OpenClaw. DenchClaw has a file tree view for you to use it as an elevated finder tool to do anything on your mac. I use it to create slides, do linkedin outreach using MY browser. DenchClaw finds your Chrome Profile and copies it fully into its own, so you won’t have to log in into all your websites again. DenchClaw sees what you see, does what you do. It’s an everything app, that sits locally on your mac. Just ask it “hey import my notion”, “hey import everything from my hubspot”, and it will literally go into your browser, export all objects and documents and put it in its own workspace that you can use. We would love you all to break it, stress test its CRM capabilities, how it streams subagents for lead enrichment, hook it into your Apollo, Gmail, Notion and everything there is. Looking forward to comments/feedback! https://ift.tt/bUdhegB March 9, 2026 at 09:55PM

Show HN: I gave my robot physical memory – it stopped repeating mistakes https://ift.tt/SZ82DRB

Show HN: I gave my robot physical memory – it stopped repeating mistakes https://ift.tt/FS9pKzn March 9, 2026 at 11:36PM

Show HN: Skir – A schema language I built after 15 years of Protobuf friction https://ift.tt/WLdg0tN

Show HN: Skir – A schema language I built after 15 years of Protobuf friction Why I built Skir: https://ift.tt/zdabGcW... Quick start: npx skir init All the config lives in one YML file. Website: https://skir.build GitHub: https://ift.tt/Z3cks4W Would love feedback especially from teams running mixed-language stacks. https://skir.build/ March 9, 2026 at 12:17AM

Show HN: Astro MD Editor – Schema-aware editor for Astro content collections https://ift.tt/w8HKWgL

Show HN: Astro MD Editor – Schema-aware editor for Astro content collections I built this for my own Astro projects where I got tired of hand-editing YAML frontmatter and switching between files. astro-md-editor reads your collection schemas and gives you a local editor UI with typed frontmatter controls (including image/color/icon pickers) alongside a markdown/MDX editor. Run it with: npx astro-md-editor Would love feedback on schema edge cases or missing field types. https://ift.tt/FAx2wuv March 8, 2026 at 11:44PM

Show HN: I built a simple book tracker because I kept buying books I owned https://ift.tt/qHek8SK

Show HN: I built a simple book tracker because I kept buying books I owned I'm Maureen, a senior and self-taught developer. I love browsing second-hand book markets but kept coming home with books I already owned. I couldn't find a simple enough app to track my library — everything required an account, had ads, or pushed a subscription. So I built one myself. SeniorEase Library (Android): scan an ISBN, book is added instantly. No account, no ads, one-time €2.99. First 10 books free. Would love any feedback! https://ift.tt/D3Rt1yr March 8, 2026 at 11:17PM

Show HN: Agentcheck – Check what an AI agent can access before you run it https://ift.tt/5vrHETy

Show HN: Agentcheck – Check what an AI agent can access before you run it Hey HN! I've just open-sourced agentcheck, a fast, read-only CLI tool that scans your shell and reports what an AI agent could access: cloud IAM credentials, API keys, Kubernetes contexts, local tools, and more. Main features: - Broad coverage: scans AWS, GCP, Azure, 100+ API key environment variables and credential files, Kubernetes, Docker, SSH keys, Terraform configs, and .env files - Severity levels: every finding is tagged LOW, MODERATE, HIGH, or CRITICAL so you know what actually matters - CI/CD integration: run agentcheck --ci to fail a pipeline if findings exceed a configurable threshold, with JSON and Markdown output for automation - Configurable: extend it with your own env vars, credential files, and CLI tool checks via a config file When you hand a shell to an AI agent, it inherits everything in that environment: cloud credentials, API keys, SSH keys, kubectl contexts. That's often more access than you'd consciously grant, and it’s hard to keep track of what permissions your user account actually has. Agentcheck makes that surface area visible before you run the agent. It’s a single Go binary, no dependencies. Install with Homebrew: brew install Pringled/tap/agentcheck Code: github.com/Pringled/agentcheck Let me know if you have any feedback! https://ift.tt/Bo5Ea02 March 8, 2026 at 11:05PM

Show HN: Tessera – MCP server that gives Claude persistent memory and local RAG https://ift.tt/AEvu03P

Show HN: Tessera – MCP server that gives Claude persistent memory and local RAG https://ift.tt/HS9BX0o March 8, 2026 at 12:42AM

Show HN: Prompt Armour – Real-time PII detection for AI chatbots, 100% local https://ift.tt/aGDYjFX

Show HN: Prompt Armour – Real-time PII detection for AI chatbots, 100% local https://prompt-armour.vercel.app/ March 8, 2026 at 12:34AM

Show HN: OpenGraviton – Run 500B+ parameter models on a consumer Mac Mini https://ift.tt/2M6FohH

Show HN: OpenGraviton – Run 500B+ parameter models on a consumer Mac Mini Hi HN, I built OpenGraviton, an open-source AI inference engine designed to push the limits of running extremely large models on consumer hardware. The system combines several techniques to drastically reduce memory and compute requirements: • 1.58-bit ternary quantization ({-1, 0, +1}) for ~10x compression • dynamic sparsity with Top-K pruning and MoE routing • mmap-based layer streaming to load weights directly from NVMe SSDs • speculative decoding to improve generation throughput These allow models far larger than system RAM to run locally. In early benchmarks, OpenGraviton reduced TinyLlama-1.1B from ~2.05GB (FP16) to ~0.24GB using ternary quantization. Synthetic stress tests at the 140B scale show that models which would normally require ~280GB FP16 can fit within ~35GB when packed with the ternary format. The project is optimized for Apple Silicon and currently uses custom Metal + C++ tensor unpacking. Benchmarks, architecture, and details: https://opengraviton.github.io GitHub: https://ift.tt/iLOwpRP https://opengraviton.github.io March 7, 2026 at 11:37PM

Show HN: diskard – A fast TUI disk usage analyzer with trash functionality https://ift.tt/Vd7exyL

Show HN: diskard – A fast TUI disk usage analyzer with trash functionality This is an ncdu clone written in Rust that I figured others might find useful! The main things that differentiate it from ncdu are: - It's very fast. In my benchmarks it's often twice as fast. - It allows you to send files to trash rather than permanently delete. Please try it out and lmk if I can improve on anything! https://ift.tt/JYNrWSX March 6, 2026 at 09:35PM

Show HN: Modembin – A pastebin that encodes your text into real FSK modem audio https://ift.tt/4OlSN2v

Show HN: Modembin – A pastebin that encodes your text into real FSK modem audio A fun weekend project: https://ift.tt/VM2GvEN It's a pastebin, except text/files are encoded into .wav files using real FSK modem audio. Image sharing is supported via Slow-Scan Television (SSTV), a method of transmitting images as FM audio originally used by ham radio operators. Everything runs in the browser with zero audio libraries and the encoding is vanilla TypeScript sine wave math: phase-continuous FSK with proper 8-N-1 framing, fractional bit accumulation for non-integer sample rates, and a quadrature FM discriminator on the decode side (no FFT windowing or Goertzel), The only dependency is lz-string for URL sharing compression. It supports Bell 103 (300 baud), Bell 202 (1200 baud), V.21, RTTY/Baudot, Caller ID (Bellcore MDMF), DTMF, Blue Box MF tones, and SSTV image encoding. There's also a chat mode where messages are transmitted as actual Bell 103 audio over WebSocket... or use the acoustic mode for speaker-to-mic coupling for in-room local chat. https://ift.tt/VM2GvEN March 6, 2026 at 10:00PM

Show HN: Tracemap – run and visualize traceroutes from probes around the world https://ift.tt/7SduDP0

Show HN: Tracemap – run and visualize traceroutes from probes around the world Hi HN, I thought it would be fun to plot a traceroute on a map to visually see the path packets take. I know this idea has been done before, but I still wanted to scratch that itch. The first version just let you paste in a traceroute and it would plot the hops on a map. Later I discovered Globalping ( https://globalping.io ), which allows you to run traceroutes and MTRs from probes around the world, so I integrated that into the tool. From playing around with it, I noticed a few interesting things: • It's very easy to spot incorrect IP geolocation. If a hop shows 1–2 ms latency but appears to jump across continents, the geolocation is probably wrong. • Suboptimal routing is sometimes much easier to notice visually than by just looking at latency numbers. • Even with really good databases like IPinfo, IP geolocation is still not perfect, so parts of the path may occasionally be misleading. Huge credit to the teams behind Globalping and IPinfo — Globalping for the measurement infrastructure and IPinfo for the geolocation data. Feedback welcome. https://tracemap.dev/ March 5, 2026 at 11:40PM

Show HN: OmoiOS–190K lines of Python to stop babysitting AI agents (Apache 2.0) https://ift.tt/5tfqPKU

Show HN: OmoiOS–190K lines of Python to stop babysitting AI agents (Apache 2.0) AI coding agents generate decent code. The problem is everything around the code - checking progress, catching drift, deciding if it's actually done. I spent months trying to make autonomous agents work. The bottleneck was always me. Attempt 1 - Claude/GPT directly: works for small stuff, but you re-explain context endlessly. Attempt 2 - Copilot/Cursor: great autocomplete, still doing 95% of the thinking. Attempt 3 - continuous agents: keeps working without prompting, but "no errors" doesn't mean "feature works." Attempt 4 - parallel agents: faster wall-clock, but now you're manually reviewing even more output. The common failure: nobody verifies whether the output satisfies the goal. That somebody was always me. So I automated that job. OmoiOS is a spec-driven orchestration system. You describe a feature, and it: 1. Runs a multi-phase spec pipeline (Explore > Requirements > Design > Tasks) with LLM evaluators scoring each phase. Retry on failure, advance on pass. By the time agents code, requirements have machine-checkable acceptance criteria. 2. Spawns isolated cloud sandboxes per task. Your local env is untouched. Agents get ephemeral containers with full git access. 3. Validates continuously - a separate validator agent checks each task against acceptance criteria. Failures feed back for retry. No human in the loop between steps. 4. Discovers new work - validation can spawn new tasks when agents find missing edge cases. The task graph grows as agents learn. What's hard (honest): - Spec quality is the bottleneck. Vague spec = agents spinning. - Validation is domain-specific. API correctness is easy. UI quality is not. - Discovery branching can grow the task graph unexpectedly. - Sandbox overhead adds latency per task. Worth it, but a tradeoff. - Merging parallel branches with real conflicts is the hardest problem. - Guardian monitoring (per-agent trajectory analysis) has rough edges still. Stack: Python/FastAPI, PostgreSQL+pgvector, Redis (~190K lines). Next.js 15 + React Flow (~83K lines TS). Claude Agent SDK + Daytona Cloud. 686 commits since Nov 2025, built solo. Apache 2.0. I keep coming back to the same problem: structured spec generation that produces genuinely machine-checkable acceptance criteria. Has anyone found an approach that works for non-trivial features, or is this just fundamentally hard? GitHub: https://ift.tt/d356S9K Live: https://omoios.dev https://ift.tt/d356S9K March 5, 2026 at 11:07PM

Show HN: AgnosticUI – A source-first UI library built with Lit https://ift.tt/OKyimFC

Show HN: AgnosticUI – A source-first UI library built with Lit I’ve spent the last few years building AgnosticUI. It started as a CSS-first monorepo with logic manually duplicated across framework packages. It turned into a maintenance nightmare. I recently completed a total rewrite in Lit to align with web standards and unify the core. One major architectural shift was moving to a "Source-First" model. Instead of a black box in node_modules, the UI source lives in your local project workspace. This makes the components fully visible to LLMs, preventing the hallucinations common when AI tries to guess at hidden library APIs. I wrote a technical post-mortem on Frontend Masters detailing the hurdles of this migration (Shadow DOM a11y, Form Participation, and @lit/react vs React 19): https://ift.tt/8Smlw2e... https://ift.tt/goQNWKi March 5, 2026 at 11:06PM

Show HN: Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens https://ift.tt/qBSbT9R

Show HN: Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens LLM agents often place raw JSON tool outputs directly in the prompt. After a few tool calls, earlier results get compacted or truncated and answers become incorrect or inconsistent. I built Sift, a drop-in MCP gateway that stores tool outputs as local artifacts (filesystem blobs indexed in SQLite) and returns an `artifact_id` plus compact schema hints when responses are large or paginated. Instead of reasoning over full JSON in the prompt, the model runs a small Python query: def run(data, schema, params): return max(data, key=lambda x: x["magnitude"])["place"] Query code runs in a constrained subprocess (AST/import guards + timeout/memory caps). Only the computed result is returned to the model. Benchmark (Claude Sonnet 4.6, 103 questions across 12 datasets): - Baseline (raw JSON in prompt): 34/103 (33%), 10.7M input tokens - Sift (artifact + code query): 102/103 (99%), 489K input tokens Open benchmark + MIT code: https://ift.tt/5XYr4c6 Install: pipx install sift-gateway sift-gateway init --from claude Works with Claude Code, Cursor, Windsurf, Zed, and VS Code. Existing MCP servers and tools require no changes. https://ift.tt/5XYr4c6 March 5, 2026 at 08:53PM

Show HN: Qlog – grep for logs, but 100x faster https://ift.tt/Lu2XBnr

Show HN: Qlog – grep for logs, but 100x faster I built qlog because I got tired of waiting for grep to search through gigabytes of logs. qlog uses an inverted index (like search engines) to search millions of log lines in milliseconds. It's 10-100x faster than grep and way simpler than setting up Elasticsearch. Features: - Lightning fast indexing (1M+ lines/sec using mmap) - Sub-millisecond searches on indexed data - Beautiful terminal output with context lines - Auto-detects JSON, syslog, nginx, apache formats - Zero configuration - Works offline - Pure Python Example: qlog index './logs/*/*.log' qlog search "error" --context 3 I've tested it on 10GB of logs and it's consistently 3750x faster than grep. The index is stored locally so repeated searches are instant. Demo: Run `bash examples/demo.sh` to see it in action. GitHub: https://ift.tt/7FnzR9i Perfect for developers/DevOps folks who search logs daily. Happy to answer questions! https://ift.tt/7FnzR9i March 5, 2026 at 03:17AM

Show HN: WooTTY - browser terminal in a single Go binary https://ift.tt/EjWNMqf

Show HN: WooTTY - browser terminal in a single Go binary I needed a web terminal I could drop into K8s sidecars and internal tools without pulling in heavy dependencies or running a separate service. Existing options were either too opinionated about the shell or had fragile session handling around reconnects. WooTTY wraps any binary -- bash, ssh, or custom tools -- and serves a browser terminal over HTTP. Sessions survive reconnects via output replay. There's a Resume/Watch distinction so multiple people can attach to the same session without stepping on each other. https://ift.tt/hbG4WZU March 5, 2026 at 02:32AM

Show HN: Bashd – Helper scripts for bulk CLI file management https://ift.tt/Ok9sT4K

Show HN: Bashd – Helper scripts for bulk CLI file management My personal Bash scripts turned full-on toolkit. Great for managing large datasets, backups, or just for quick file navigation. https://ift.tt/eB7vDad March 5, 2026 at 12:42AM

Show HN: AI tool that brutally roasts your AI agent ideas https://ift.tt/zPUwv6d

Show HN: AI tool that brutally roasts your AI agent ideas I built whycantwehaveanagentforthis.com — submit any problem and get a structured analysis of whether an AI agent could solve it. The output includes a creative agent name, feasibility verdict, real competitor analysis (actual products with URLs), a kill prediction (which big tech company makes this obsolete, when), build estimate, and a savage one-liner. Built with Next.js + Claude API (Haiku). Runs on ~$5/day. Rate limited with Upstash Redis (7 layers). The prompt engineering to get accurate, non-hallucinated competitor analysis was the hardest part. Free, no signup. Feedback welcome — especially on AI response quality. https://ift.tt/I53iRLF March 4, 2026 at 12:24AM

Show HN: DejaShip – an intent ledger to stop AI agents from building duplicates https://ift.tt/19nEk4V

Show HN: DejaShip – an intent ledger to stop AI agents from building duplicates When you give an AI agent a popular task like "build a micro-SaaS to make money," hundreds of agents are triggered to build the exact same things. DejaShip is a semantic coordination layer to stop this wasted compute. Before writing code, the agent checks the "airspace". If a lot of similar projects already exist, the agent can pivot to a new idea, or if it is free in its choice, it can prefer to collaborate instead of blindly cloning it. It works as an MCP server. Open source (MIT), no accounts or API keys required. Under the hood: The backend embeds keywords locally using fastembed to search pgvector for semantic collisions. To be transparent: The MVP is new, so the data corpus is tiny today. The value of this protocol only grows as more agent operators plug it in - or help decide how this coordination can be improved. (One of the biggest issues right now is the amount of false positives; it definitely needs improvement). Site links and MCP installation instructions are on the GitHub README. (npmjs package: dejaship-mcp). I'd love your brutal feedback. https://ift.tt/91gPqKJ March 3, 2026 at 11:43PM

Show HN: Open-Source Article 12 Logging Infrastructure for the EU AI Act https://ift.tt/54aYpbI

Show HN: Open-Source Article 12 Logging Infrastructure for the EU AI Act EU legislation (which affects UK and US companies in many cases) requires being able to truly reconstruct agentic events. I've worked in a number of regulated industries off & on for years, and recently hit this gap. We already had strong observability, but if someone asked me to prove exactly what happened for a specific AI decision X months ago (and demonstrate that the log trail had not been altered), I could not. The EU AI Act has already entered force, and its Article 12 kicks-in in August this year, requiring automatic event recording and six-month retention for high-risk systems, which many legal commentators have suggested reads more like an append-only ledger requirement than standard application logging. With this in mind, we built a small free, open-source TypeScript library for Node apps using the Vercel AI SDK that captures inference as an append-only log. It wraps the model in middleware, automatically logs every inference call to structured JSONL in your own S3 bucket, chains entries with SHA-256 hashes for tamper detection, enforces a 180-day retention floor, and provides a CLI to reconstruct a decision and verify integrity. There is also a coverage command that flags likely gaps (in practice omissions are a bigger risk than edits). The library is deliberately simple: TS, targeting Vercel AI SDK middleware, S3 or local fs, linear hash chaining. It also works with Mastra (agentic framework), and I am happy to expand its integrations via PRs. Blog post with link to repo: https://ift.tt/exaoFS1 I'd value feedback, thoughts, and any critique. March 3, 2026 at 05:11PM

Show HN: Herniated disc made me build a back-safe kettlebell app https://ift.tt/LCejgcJ

Show HN: Herniated disc made me build a back-safe kettlebell app I herniated a disc in 2023 and spent months in physio. Once cleared to train, standard workouts kept tweaking my back, especially when fatigue hit and my form broke down. I love EMOMs because they make time fly and push my limits without overthinking. Built this generator to combine that structure with exercise selection that won't wreck my back. It excludes american swings, russian twists, and movements that combine loaded spinal flexion with rotation. The algorithm prioritizes anterior-loaded movements (goblet squats, front rack work) based on McGill's spinal loading research. React 19 + Tailwind + Capacitor for iOS. Lifetime unlock is the main option because nobody needs another Netflix subscription. There's also a low-cost monthly if you want to try premium features without committing. Not medical advice. This is what worked for my transition from rehab back to lifting. Curious to hear from others: what was the hardest part of getting back to training after disc issues? https://kbemom.com/ March 3, 2026 at 11:11PM

Show HN: MoodJot – Mood tracker mobile app with community feed, built with KMP https://ift.tt/NFeYmR1

Show HN: MoodJot – Mood tracker mobile app with community feed, built with KMP MoodJot is a mood tracking app I built solo using Kotlin Multiplatform and Compose Multiplatform. It ships on both iOS and Android from a single codebase. The main differentiator from existing mood trackers (Daylio, DailyBean, etc.) is a community feed where users can share moods and see how others are feeling. Technical details: - Compose Multiplatform for shared UI (31 screens) - GitLive Firebase KMP SDK for Firestore, Auth, Storage - ChatGPT integration for AI mood pattern analysis via Ktor - expect/actual for StoreKit 2 (iOS) and Play Billing 7.0 (Android) - Home screen widgets: SwiftUI WidgetKit (iOS) and RemoteViews (Android) - Custom localization: 5 languages without platform string resources - Kamel for cross-platform image loading, multiplatform-settings for persistence Other features: photo attachments, 10-point intensity scale, 80+ trackable activities, 25+ achievement badges, 14 emoji themes, goal tracking. Live on App Store and Google Play since November 2025. https://moodjot.app Happy to discuss the KMP architecture or any design decisions. https://moodjot.app March 2, 2026 at 11:08PM

Show HN: Open-source Loom / Screen Studio with editing and auto-zoom https://ift.tt/OHkyDzT

Show HN: Open-source Loom / Screen Studio with editing and auto-zoom https://ift.tt/qVob9tK March 2, 2026 at 11:00PM

Show HN: Panel Panic a Rust/Macroquad/WASM Panel de Pon/Tetris Attack Clone https://ift.tt/3anCBym

Show HN: Panel Panic a Rust/Macroquad/WASM Panel de Pon/Tetris Attack Clone Rust/macroquad game with single player AI mode, online VS, and local 1v1. All running via WASM in the browser. Still WIP as art assets still need to be added and tweaked. Full disclosure. Used Claude Opus, Nanobanana, and SunoAI a huge amount to do the heavy lifting for this project https://panel-panic.com March 2, 2026 at 12:18AM

Show HN: I built a tool that turns any API into a CLI for agents https://ift.tt/Hp6QauK

Show HN: I built a tool that turns any API into a CLI for agents TLDR; I built a tool that turns any API into a CLI designed for ai agents --- Got tired of dealing with bloated context windows from MCP servers and skills that stuff entire API docs into the agent's context CLIs fix this, agents run a single command to self-discover everything an API has to offer So, built a tool to generate them for any api. All CLIs are written in Go, fast and lightweight, no dependencies Help text (via the --help flag) is the killer feature: all context for each command/endpoint/parameter is extracted directly from the user-facing API docs and enhanced with llms. It's bundled directly with the CLI and agents fetch only what they need at runtime. No context overhead, no fumbled API calls. Most APIs don't have a CLI yet. Can have Opus one-shot simple ones, but building a great one with cross-platform binaries, install scripts, detailed help text, and auto-updates takes time and is frustrating to repeat for every API. Maintaining it the API grows is a headache Give InstantCLI any API docs url and it generates a production-ready CLI in minutes. It includes binaries + install scripts for all platforms, auto-updates as your API changes, docs-enhanced help text designed for agents, and hosting https://instantcli.com March 2, 2026 at 12:19AM

Show HN: Audio Toolkit for Agents https://ift.tt/Umn7wz0

Show HN: Audio Toolkit for Agents https://ift.tt/8xzlsR5 March 1, 2026 at 10:52PM