Building AI apps and agents with Microsoft FoundryMicrosoft’s Azure-based AI development and deployment platform shines with a strong selection of models and agent types and an excellent playground for experimenting with agents. At first glance, ...
Show HN: Kanban-CLI – a web UI for local Markdown todo listsAs we all are, I've been experimenting with ways to reduce external saas spend, and continually bring traditionally external pieces of context (prs, docs, trello boards) into the one mono repo.I have toyed with a markdown todo list and setting claude/codex into a "ralph" loop previously, but always missed the web ui for organising, planning, and tracking things in progress.So codex and I build kanban-cli, an installable or npx-runnable cli util that takes one or more markdown files, and uses markdown headers and todo syntax to track and manage agentic tasks.Let me know your thoughts, or if you've got a more convenient way of managing tasks!I was tempted to link to the project landing page https://kanban-cli.vochsel.com as I made a cute example demo, but linking to the repo felt less self-promo-y.Cheers!
Show HN: A navigable map and recommender for 17M music entitiesHello HN,This is toposonico, a music recommender and navigable map. At core it's a skipgram word2vec model trained over ~6M playlists. Tracks are embedded in a 128d space. Embeddings for albums, artists and labels are computed marginalizing over tracks. The 2D map was built with UMAP.Both the model and UMAP were trained in the cloud over a NVIDIA A100. All things considered it cost me around ~50EUR, over two main training sessions and a few experiments. For the slippy map I experimented with a few libraries. Ended up with Maplibre GL JS. Loved working with it, kudos to their developers. For the recommender indexes I used FAISS, another fantastic piece of software. Pretty happy with the thing running on a small and cheap box.Two things influenced me in making this. The first is decade-old idea: human navigation and exploration skills work in information spaces too. Many ML concepts fit this idea especially well. It would be nice to see more experiments in this direction. The second goes
Show HN: Nv – workspace orchestrator for jj built for parallel agent workflowshowdy y'all,i've been deep in jj for a while and been experimenting with jj workspaces for parallel workflows. it's more intuitive than git worktrees but it still has a couple of gotchas that have been a hindrance to my ideal workflow.so I built jj-navi - a tiny rust based cli that makes jj workspace orchestration a lot less pain in the ass.key bits: - `navi switch ` -> creates/switchs workspaces and cds into them automatically (via shell integration) - `navi list` -> shows insertions/deletions across workspaces and also runs jj snapshot (so you don't see stale work)check it out here at: https://github.com/eersnington/jj-navi (note: url at the top is a git.new one)also, this is heavily inspired by worktrunk (still my daily driver replacement for git worktrees) and jj-ryu by dillon mulroy from the orange cloud forking company.would love y'alls feedback, especially from heavy jj + agent users. feel free to open up issues on gh or hit me up on X.
Show HN: Mvndvs TERRARUM – A Renaissance-style 3D world mapIn this fast-paced, AI-exploding era, I felt a strong desire for a slower, more deliberate pace.I built a 3D interactive world map: https://world.gjlmotea.com/Lately, time seems to be flying by. I've been building a lot of quirky, experimental projects, but honestly, my mood has been quite restless and low. There are just too many options and new technologies emerging every day—choice paralysis sets in before I can even figure out what I truly want to build.But this project is different. It’s more grounded, human, and carries a sense of warmth. I wanted to create an immersive experience with a Renaissance, antique parchment aesthetic.Features:Explore: Browse different countries and click on nations or architecture for detailed information.Data Layers: Toggle between various global map modes including Architecture, Culture, Academia, Commerce, and Military.Themes: Multiple visual themes to switch between.3D Architecture: Scale the models of buildings (like Taipei 101) to your liking.Glo
Show HN: iClaw is part OpenClaw, part Siri, powered by Apple IntelligenceHi HN,Last month at a SundAI hackathon, my team built a prototype for an app called iClaw. The goal was to develop an AI agent using Apple Intelligence. I've since continued hacking away at this idea when I had time, and now I'm releasing it on https://geticlaw.com with code on GitHub.Apple Intelligence is a really poor model choice for an AI agent. It's not great at extracting information (it often injects preambles like "Here's the page..."), it struggles with following directions, and it gets overwhelmed when you ask it to choose from more than 3 available tools. But it's also a great choice because it comes pre-installed on many Macs without any configuration. It's also incredibly fast compared to just about every other 2-4B model I've run on my MacBook Air.iClaw is very experimental and will make mistakes, but it's designed around safety. iClaw lives in the App Sandbox where it only has access to the permissions you grant it. All tools calls that create or delete (files, emails, c
Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-previewScored 65.2% vs google's official 47.8%, and the existing top closed source model Junie CLI's 64.3%.Since there are a lot of reports of deliberate cheating on TerminalBench 2.0 lately (https://debugml.github.io/cheating-agents/), I would like to also clarify a few things1. Absolutely no {agents/skills}.md files were inserted at any point. No cheating mechanisms whatsoever2. The cli agent was run in leaderboard compliant way (no modification of resources or timeouts)3. The full terminal bench run was done using the fully open source version of the agent, no difference between what is on github and what was run.I was originally going to wait for it to land on the leaderboard, but it has been 8 days and the maintainers do not respond unfortunately (there is a large backlog of the pull requests on their HF) so I decided to post anyways.HF PR: https://huggingface.co/datasets/harborframework/terminal-ben...It is astounding how much the harness matters, based on this and other experiments I h
Show HN: I built a PyPI watchdog that tests whether packages workThe Python Package Index now curates over 700,000 packages. 10,000-15,000 are added daily. Nobody systematically checks whether they install and run across environments. I built something that does.The watchdog pulls packages, attempts installs across multiple Python environments, runs basic import verification, and publishes results continuously. The dashboard is live at https://sovereignmail.org/pypiplace . Data is also broadcast over the Yggdrasil mesh network for anyone who wants to pull and verify it independently.It's my first experiment running live on a free tier Oracle ARM instance.I find it useful. And kinda cool. I'd love anybody who want to run it to do so.https://github.com/PregnantPenguins789/vps-pypi-place https://github.com/PregnantPenguins789/yggcrawl
Show HN: Nimbus – Browser with Claude Code UXHi HN, I'm Anil. Nimbus is a desktop browser with an AI agent built into it. The UX is shamelessly inspired by Claude Code: a chat bar at the bottom, an agent log above it, and the webpage itself when its needed.This is mainly a UX experiment for me. And also the reason it isn't a Chrome extension: once you have a chat bar that understands intent, the URL field is redundant. You shouldn't have two places to tell the browser what you want. I didn't want to bolt an agent onto an existing browser's chrome and end up with duplicated controls everywhere — I wanted full freedom to redesign the shell from scratch, decide what stays, what goes, and what a browser even looks like when the agent is the primary interface. Download for macOS: https://usenimbus.app Launch video: https://youtu.be/dj23-XIiB1o
Accelerating frontier transformation with Microsoft partnersAI has moved quickly from experimentation to production. Customers want measurable business outcomes, along with security, governance and responsible AI built in from day one. Microsoft partners are a ...
Ask HN: Monetizing a Supplements DatasetA few years back, I got obsessed with the idea of analyzing the entire supplement market. The first couple of experiments didn't go far, but as models got better, I was able to:* Extract detail breakdown of every ingredient in every commercially sold supplement. I believe that today my dataset is the only data that could accurately answer questions like: which supplements contain the most X, which supplements would be the cheapest when seeking a specific ingredient, etc.* Extract signals from every research paper about supplements about the effects of specific supplements in relation to different conditions (effect type [neutral, positive, negative], effect size [small, moderate, great])I was kinda hoping that over time, the data that I've gathered will attract people who are into nutrition, researchers, value buyers, etc., but I am learning the hard way that the supplement space is hyper competitive [other websites in the nutrition space will not link to my project, but rather extract
Show HN: Egregore – Shared memory and coordination for multiplayer Claude Codehi HN — we're Cem and Oguzhan. today we are releasing Egregore (https://github.com/egregore-labs/egregore) as an open-source shared memory and coordination substrate for teams using Claude Code. MIT, runs locally, `npx create-egregore@latest --open`. Here's a 90-second walkthrough: https://shorturl.at/e1RX2we were essentially working on dynamic ontology systems (how to organize unstructured data given context / starting conditions dynamically). since december new capabilities that came around with opus 4.5 completely altered the nature of our work. but despite the radical increase in speed and ambition of our experiments, we were visibly diverging from a common vision. once we acknowledged that together, we decided to find ways to infrastructure mechanisms for convergence. first it was integrating the GitHub organization and repos we are working on, later we developed custom commands that would help us share research, request code reviews and even send each other spam through a tg conn
Hyper-Intelligence: Chow Tai Fook and Microsoft Join Hands to Redefine the Future of Global Luxury Retail with Hyper-IntelligenceAs generative AI moves beyond buzzwords and experiments into the core of enterprise operations, the real divide between companies is no longer whether they adopt AI—but how deeply they embed it into ...