Show HN: Makes local LLMs faster and more reliable by optimizing for your device https://ift.tt/lneuBHS

Show HN: Makes local LLMs faster and more reliable by optimizing for your device Time to first token is 39% faster Agent wall times decrease by 46% No swaps Tracks your resource usage in real-time and adjusts how the model runs so that it works perfectly on your device. Implements KV cache sizing, prefix caching, live RAM pressure management, context trimming, KV quantization, and more. Built a ton of features https://ift.tt/89M6S1z June 30, 2026 at 02:13PM

Show HN: Shot-scraper video tool for recording YAML-defined webapp feature demos https://ift.tt/gWhr7ao

Show HN: Shot-scraper video tool for recording YAML-defined webapp feature demos https://ift.tt/TE4nm9H June 30, 2026 at 12:58PM

Show HN: Clusy – Cursor for data science notebooks in cloud https://ift.tt/DTYv35w

Show HN: Clusy – Cursor for data science notebooks in cloud https://www.clusy.io/ June 30, 2026 at 01:09PM

Show HN: My 13-year-old built an ant colony tracker https://ift.tt/FrhWwu0

Show HN: My 13-year-old built an ant colony tracker He's 13 years old. He wanted to track his own ant colonies — growth, feeding, humidity, and other metrics. He built the whole app himself with some help from AI tools; I just helped him deploy it to a server. Would love to hear your feedback! https://formicarium.es June 30, 2026 at 12:48PM

Show HN: fenic – LLMs as dataframe operators, query meaning and structure https://ift.tt/WzODIsn

Show HN: fenic – LLMs as dataframe operators, query meaning and structure Hey friends. I'd like to share a project that's dear to me. fenic is a dataframe API with LLMs added as first-class citizens, a classic lazy dataframe API extended with new operators that are backed by LLMs. What this gets you is the ability to work with structured and unstructured data in the same context. Most importantly, the LLMs aren't integrates as opaque UDF black boxes. They're exposed as "semantic" operators that the planner can reason about alongside the classic ones. (There are examples and code snippets on the repo to see how everything works together) Why build this? I'm a data infra / systems person. When LLMs showed up, what I saw was a new type of compute that changes the characteristics of the workloads we deal with. I wanted to experiment with how our current systems can absorb these new workloads and compute types, and what it would take to make the DX as seamless as possible, that's where the UDF + arbitrary prompt was feeling too problematic. To support this properly, we had to introduce a few really cool things: New plan operators. You don't just send prompts at an LLM. You use operators like semantic join, semantic map and reduce, and semantic filter, among others. They mix with the classic operators, and because the planner sees them as real operators rather than black boxes, it can reorder work around them. Typed outputs. There's ergonomics to turn the output of a semantic operator straight into a typed dataframe column. A Pydantic schema for the LLM output becomes a typed struct column you can unnest, explode, and so on. New data types like a markdown data type. Markdown became an important way to share information with LLMs, even though it started life as a way to format text for presentation. It carries structure, and being able to access that structure the way you would a struct or JSON type adds to the developer experience I mentioned. Async UDFs. One of the more interesting shifts in workloads from the LLM explosion is the need to put heavily I/O-bound steps in your pipeline: fetching a response from an API, crawling a website, and so on. Async UDFs fill that gap, and the implementation handles the nuances for you: concurrency, retries, and the rest. An LLM-inference-aware planner and runtime. This is one of the parts I'm most excited about, and there's a lot still to do. Today: identical prompts within a batch collapse to a single model call, so duplicates cost zero tokens; requests are dispatched concurrently under per-provider rpm/tpm limits with retries and backoff; null and empty cells skip the model entirely; and you get token and cost metrics per operator. There's also an optional persistent response cache so re-runs skip the model. MCP as a new catalog primitive. Much like a registered view, you can register a dataframe pipeline as an MCP tool in the catalog. fenic then serves an MCP server with that pipeline as the tool's logic, executed over your data. These are just some of what's gone into fenic while experimenting with how LLMs can become part of our compute infrastructure. There's more, and plenty more to polish on what's already there. I've been using fenic for all sorts of things. On the small/personal end, I use it to take my podcast audio recordings and turn them into nicely structured tables of metadata I can research. On the heavier end, I use it as tooling for agents to analyze agent traces exported from Pydantic Logfire, to discover evals and turn them into reproducible artifacts in the form of dataframe pipelines. pip install fenic Repo: https://ift.tt/VmYDwGt Docs: https://docs.fenic.ai There's also a skill you can use with claude code, codex etc. to quickly get started with fenic in your favourite agentic coding environment. I'd love to hear your thoughts, criticism, and anything else that comes to mind. I'm here to answer questions. https://ift.tt/VmYDwGt June 30, 2026 at 12:39PM

Show HN: Openleetcode – local LeetCode runner with open test suites https://ift.tt/budcQwk

Show HN: Openleetcode – local LeetCode runner with open test suites https://ift.tt/BopaJQ0 June 30, 2026 at 12:16PM

Show HN: Don't ask if devs cheat with AI, test if they're good with it https://ift.tt/zA2oV31

Show HN: Don't ask if devs cheat with AI, test if they're good with it https://ift.tt/Y7hKEHJ June 30, 2026 at 11:45AM

Show HN: Shoaku – Your Coding Navigator https://ift.tt/VhAWFvk

Show HN: Shoaku – Your Coding Navigator AI Agents like Codex and Claude are incredibly powerful and have drastically sped up implementation. However, I noticed a strange side effect: I began to lose confidence in my own coding. I submitted a pull request after the AI completed the implementation. It looked good, but during code review, I was asked, "Why did you implement it this way?" I grew increasingly embarrassed because I couldn't immediately explain the complex code. Previously, I built confidence by understanding the design through reading and writing code, which was enjoyable, but now I've lost that. This coding assistant helps users understand their thought process and coding progress, with the AI acting solely as a guide and not writing code on its own. To still leverage the AI agent's autonomous implementation capabilities, a separate AI thread runs in the background in a temporary working directory, providing highly accurate navigation assistance to the user. The AI's responses are still a bit strange at times, but if this concept resonates with you, please share your feedback. As a solo creator, I find that very encouraging. Thank you. https://ift.tt/FMxmWfI June 30, 2026 at 10:24AM

Show HN: Second opinion – A skill to query different models https://ift.tt/2Tg0BSO

Show HN: Second opinion – A skill to query different models Make this skill to help me cross examine suggestions made by claude to other Claude or opencode supported models mid session. It compiles relevant context, consult a second opinion for me and support following up with the second opinion. A pattern that I find quite useful. Currently it supports claude to claude, claude to opencode and opencode to claude invocation. These are the two harnesses I use. https://ift.tt/9NX4ohw June 30, 2026 at 10:20AM

Show HN: ServerKit – A mobile UI for server management https://ift.tt/KPtLXBm

Show HN: ServerKit – A mobile UI for server management Problem Statement: A few months ago, I was outside of my city. I was on a bus when one of my team members messaged me saying users were unable to read the product description PDF. I had to wait 3 more hours until I got back home, opened the laptop, and SSH'd into the server to find out what was wrong. In that moment I realized that being able to manage a server from a phone is very important when a laptop is not nearby. What it does: It is a UI wrapper over standard SSH command outputs. It parses the SSH output and shows the results in UI elements, and also translates your actions to relevant SSH commands. This way users won't have to heavily rely on the command line – as we know, typing commands from a mobile device is also hard. However, it also has a terminal to allow you to do anything. It also supports Kubernetes, where you can see and manage pods, view logs and stats, and RDBMS to allow you to quickly perform database operations – a bit like phpMyAdmin or pgAdmin. Tech Stack: Flutter, SSH, Android Secured Storage, Firebase, Docker Why Android: I know – iOS is a major platform for this niche. But for now – as it is an MVP – I have decided to develop for Android to validate my idea and understand if it solves a real problem. The good news is, it does solve a real problem – at least the analytics say so. Within 30 days I got 5 premium users. About 30% of users connect their server and 23% of them use the app regularly. So now I am working on the iOS version. Current Limitations: Currently the app only supports Ubuntu – other Debian based OSes are not tested, though they might work as well. The Kubernetes and AWS features need more testing. Also, ServerKit VPS Lab currently limits sessions to only 30 minutes TTL to prevent misuse. Feedback Request: I would love your feedback on the VPS management and monitoring features, RDBMS features, and Kubernetes features. I also tried to keep the terminal simple, but your feedback on this is also valuable to me. Try it out: If you don't want to connect your own VPS, you can test the app using ServerKit Lab. It will allow you 30 minutes of free VPS to test the app. Install ServerKit: https://ift.tt/xlM4bsi... https://ift.tt/jJZcgf5 June 30, 2026 at 10:12AM

Show HN: The UNESCO Tsunami Warning Emails Are Gone https://ift.tt/xwIsKWg

Show HN: The UNESCO Tsunami Warning Emails Are Gone This key piece of tsunami warning and safety was discontinued this morning and evidently there's no way to get it back. :/ https://ift.tt/X2ewbfh June 29, 2026 at 02:06PM

Show HN: Rust / Red Alert inspired WASM game in the browser (open source) https://ift.tt/q4nOMTo

Show HN: Rust / Red Alert inspired WASM game in the browser (open source) https://punnerud.github.io/mpe-ra/ June 29, 2026 at 12:48PM

Show HN: HyperPaste – a free, open-source clipboard manager for macOS https://ift.tt/I429dsh

Show HN: HyperPaste – a free, open-source clipboard manager for macOS To me it always felt like clipboard history was one of the few things missing from macOS. There are already some excellent clipboard managers available, but after trying quite a few of them I kept coming back to the same goal: I wanted something that felt like it belonged on macOS. Fast, keyboard-first, private, and visually restrained. One thing I felt strongly about from the beginning was that it had to be open source. Clipboard managers have access to some of the most sensitive data we copy — passwords, API keys, personal information, financial details — and for something that sits in the background watching my clipboard all day, I personally wasn't comfortable using closed-source software. That ruled out a lot of otherwise great applications for me. The result is HyperPaste. HyperPaste is a free, open source clipboard manager for macOS, built with SwiftUI and AppKit. Clipboard data stays on your Mac — there are no accounts, cloud services, telemetry, or ads. Some highlights: - Instant search - Keyboard-first workflow - Rich support for text, code, links, colors, images, and files - Automatic color previews - Favorites for frequently used clipboard items - Native context menus and keyboard shortcuts - Local-first design with no ads or analytics One of the design goals was to avoid turning clipboard history into a productivity suite. I wanted HyperPaste to stay focused on one job: helping you quickly find and reuse things you've copied. The project is MIT licensed and the source code is available on GitHub. I'd genuinely appreciate any feedback, bug reports, feature suggestions, or criticism. I'll be around to answer questions throughout the day. https://hyperpaste.io June 29, 2026 at 11:13AM

Show HN: Sonar, local cited codebase briefings tailored to your role https://ift.tt/7fIxk4j

Show HN: Sonar, local cited codebase briefings tailored to your role https://ift.tt/W5kUyEN June 29, 2026 at 08:47AM

Show HN: macOS Native Markdown Reader with Vim Keybinding Using Swift https://ift.tt/hyLIopO

Show HN: macOS Native Markdown Reader with Vim Keybinding Using Swift I have been working on this MacOS Native Markdown Reader with Vim Keybinding using Swift and here is the first public version https://ift.tt/EUgHXlC June 29, 2026 at 11:24AM

Show HN: Klorn–I built an email firewall because every AI inbox made mine louder https://ift.tt/AtwbM8f

Show HN: Klorn–I built an email firewall because every AI inbox made mine louder https://ift.tt/K6lUSMF June 29, 2026 at 10:18AM

Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills https://ift.tt/Ge26Ocu

Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills Skills for Claude Code and Codex are hard to test. What I mean by hard is that there's no standard way to do it. You evaluate the skill once on something, it looks like it works. You publish it. Then the new super model releases (GLM 5.2 anyone?), it will quietly break for some part, and you won't find out until your users complain. I also faced the same problem, so I tried to build something lightweight to stop doing that. Caliper. It's a local and lightweight harness that runs a skill k times in isolated environments and gives you a pass@k score (How much times it succeeded in these k times). As a non-deterministic technology, you can't just say "it worked once". You need to answer how much it passed in k times. You define success in a YAML spec. I picked YAML to keep a schema and make it still readable for a human. You either use a LLM judge, a Python assertion, or both: Here's an simple evaluation example with a JSON extraction, so you write this in a YAML file: tasks: - name: Extracts action items as clean JSON prompt: "Read /tmp/transcript.txt and write the action items to /tmp/actions.json." expect: "A valid JSON array where every item has owner, task, due. No markdown fences." assert: | import json items = json.load(open("/tmp/actions.json")) assert isinstance(items, list) assert all({"owner","task","due"} <= i.keys() for i in items) Then with the CLI, you'll run it: caliper run extract-actions.eval.yaml --k 5 --baseline What's cool about the --baseline flag is that it will re-runs everything without the skill, so you can see whether the skill is doing the work or the base agent was going to pass anyway: ID Task k(5) pass@k task-1 Extracts action items as JSON 5/5 100% PASS With skill 100% No skill 60% Delta +40% Most models know how to get the JSON right most of the time (JSON extraction was solved by 2 years old already). But that's it, "most of the time" is the bug. That delta shows how the skill actually helped. (It's sometimes 0%, sometimes -100%!) I also created two skills you can get started right away with your favorite harness, e.g. Claude Code, Codex or Pi: - evaluate-skill: run and manage evals without leaving your workflow - grill-skill: reads your SKILL.md, interviews you about what "good" looks like, writes a 3-task spec (happy path, edge case, adversarial), and runs it You can install the skill with the command: npx skills@latest add edonadei/caliper I for now support claude-code, codex, pi, claude-api, openai-api. You can run the agent and the judge as separate backends, so you can run a skill on one and judge with another. GitHub: https://github.com/edonadei/caliper PyPI: https://pypi.org/project/caliper-eval/ Of course, it's a first step. I think the autorater layer can be vastly improved, more handholding to create and iterate on evaluation specs, supporting more harness, why not including this layer into a self-improvement bigger system? If you're also building agentic evaluations, I'm genuinely interested to hear how you are handling that. https://github.com/edonadei/caliper June 28, 2026 at 01:42PM

Show HN: DRM-Free Books https://ift.tt/Rz5LtIx

Show HN: DRM-Free Books After several years of mandatory DRM lockdowns from most commercial book sources, now authors have a choice when it comes to DRM for their books. Pick authors and books that are DRM-free, or download DRM-free classics that are out of copyright. https://ift.tt/UbE3CNk https://ift.tt/UbE3CNk June 28, 2026 at 12:58PM

Show HN: Zanagrams https://ift.tt/yE8FeO7

Show HN: Zanagrams https://zanagrams.com/ June 28, 2026 at 11:26AM

Show HN: Import the HN Home to a reading queue with clean reader view and TL;DR https://ift.tt/85F0KkO

Show HN: Import the HN Home to a reading queue with clean reader view and TL;DR https://ift.tt/hnGQFHS June 28, 2026 at 11:12AM

Show HN: Clanker TV https://ift.tt/Elisnr6

Show HN: Clanker TV https://botflix.tv/ June 28, 2026 at 10:30AM

Show HN: A faithful MUMPS 76 anniversary implementation – the original NoSQL DB https://ift.tt/hlK7Sjm

Show HN: A faithful MUMPS 76 anniversary implementation – the original NoSQL DB https://ift.tt/y0XHwJI June 28, 2026 at 07:41AM

Show HN: role-model, a router for hybrid local/cloud AI https://ift.tt/aSKUOQc

Show HN: role-model, a router for hybrid local/cloud AI Hey everyone, I'm launching role-model today: a routing protocol, a reference router runtime, and an extension for Pi that allows for better informed routing decisions. role-model is mostly deterministic, with fallback to a controller model, that routes requests based on a chosen routing strategy. the protocol is structured around assigning domains and roles to models, where requests sent by consumer applications like Pi have task types to enrich routing metadata and thereby accuracy. you can to run the built-in benchmark to compare performance of models across speed, quality and cost, as well as observed performance on real tasks. I have a diagram on how routing works in [0]. The runtime supports local models, either directly to your local endpoint (LM Studio, llama.cpp etc), or routing between multiple local models via vendored llama-swap. Since there was another model router post yesterday where people discussed the basics of routing, I will focus on discussing some of the interesting learnings I've made building and testing this: 1. Model routing is essentially trying to predict the future: which model will perform optimally (based on criteria defined by the user) on this request? 2. After you have routed the request, you want to evaluate if it was the right decision or if some other model would have performed better 3. You also realize that having the router assess difficulty (among other things) to make decisions by itself is far from ideal - we'd prefer to have the consumer application work with the router to define what the request needs 4. You also realize that it becomes much easier, decisions become much accurate, and the outcomes of routing becomes more impactful when there is more of a distinction between models For point 2, I will be launching evals that you can run locally to benchmark models in your pool on the same requests. The outcomes here can then be used for point 1, as input when routing new requests. For point 3, I've built the pi-role-model package for Pi, which lets the Pi agent inject role_model.intent metadata including difficulty, preferred roles or even specfic model ids, required capabilities (say tool use or image input) and so on. You should be able to customized this further in Pi, and route in additional ways by changing metadata. This is why I've also built the role-model routing protocol. For point 4, what model routing really does as a second order effect is create a market for specialized models - models that may or may not be smaller, could be cheaper or more expensive, may be locally runnable. It makes little sense to route between two frontier models (GPT 5.5 and Opus 4.8); it makes more sense to route between models where one of the factors of quality, speed, cost is a multiple of the other candidate models, and it makes even more sense to have specialized domain models: code, prose, math and science, visuals and so on. It is at this stage model routing becomes really valuable. While role-model has a reference runtime that I'm continuously building out (there's lots to do to improve routing, as well as give users more granular control over routing decisions, and also ways to improve cross-model caching and also add techniques like FastContext), the ultimate goal of role-model is for there to be a standard protocol for inference requests that is used by consumer applications, so that the provider, be it a router middleware or an inference provider, will be able to route to a model that strikes the best balance between cost, speed and quality and also respects user choices, and even lets the user control these preferences to use local models for some tasks and allow cloud for others. Links: [0] role-model - the case for a model routing protocol: https://ift.tt/6mwCnS3... [1] GitHub: https://ift.tt/Rm3ljwg [2] Docs: https://role-model.dev/ https://ift.tt/Rm3ljwg June 28, 2026 at 06:46AM

Show HN: Wind particles on Mapbox from a single EXIF JPEG https://ift.tt/SgcnqfR

Show HN: Wind particles on Mapbox from a single EXIF JPEG https://ift.tt/vrWSfwk June 27, 2026 at 02:16PM

Show HN: A Living Neural Web in HTML5 Canvas https://ift.tt/gEXnO1V

Show HN: A Living Neural Web in HTML5 Canvas https://techoreon.github.io/verpad/canvas-playground.html June 27, 2026 at 12:35PM

Show HN:I got tired of spending 3hrs daily on job applications,so I automated it https://ift.tt/EXH0Mf6

Show HN:I got tired of spending 3hrs daily on job applications,so I automated it https://jobspire.co.in/ June 27, 2026 at 11:21AM

Show HN: I built a hardware quantum RNG and wired it into a Magic 8-Ball https://ift.tt/ZSIYGgs

Show HN: I built a hardware quantum RNG and wired it into a Magic 8-Ball Gday, author here! I've wanted to hack together a "real" quantum random number generator for another upcoming project, and I got carried away a bit, and went down the 'over-engineering' cliff. So, for your nerdy enjoyment, I have documented it all up, and I added something cool for fellow "Multiple World Interpretation" followers in the Quantum Mechanics debate. This QRNG uses sexy bits: Each is the decision of a photon to go left or right after hitting a 50:50 beam splitter. Standard kinda device, where you attenuate a light source down to single photons, offer them semi-mirror to bounce off, and see which PMT detector they hit (or which universe we ended up in ;) ). Basically, Through → bit=0. Bounce → bit=1. As I take the MWI interpretation of Quantum Mechanics (its the more fun options), I have also built a Quantum Magic 8-Ball. Ask it a questions, and you get and receive exactly one answer here, plus every possible answer across the multiverse. https://quantumlever.stream/oracle Enjoy! https://dnhkng.github.io/posts/building-the-beam-universe-splitter/ June 26, 2026 at 02:05PM

Show HN: A map of every UK railway, including stations that no longer exist https://ift.tt/7HJLeVC

Show HN: A map of every UK railway, including stations that no longer exist Author here (Nathan). The goal for this site was to map the entire UK rail network: not just the parts a journey planner surfaces, but heritage lines, freight-only curves, named tunnels and viaducts, and the thousands of stations that have closed and were never mapped. The project is built entirely on open data. Lines and current stations come from OpenStreetMap via Overpass, closed stations from Wikidata (approximately 6,100 that fall outside a 250 m radius of a live OSM station), and postcode lookups from postcodes.io. The main challenge is that the sources rarely agree with one another, or even with themselves, so much of the work involved small reconciliation rules. For example, the heritage flag is propagated across every segment sharing a line name, so the Swanage Railway is coloured consistently. I shared an early version with a railway enthusiast community, and a large share of the fixes came from people who know the network considerably better than I do. A full write-up of the data challenges is available here: https://ift.tt/D3diAFr No account or app is required. You can search by postcode, station name, three-letter code, or line name. Corrections are very welcome, as there is always a station someone knows I have got wrong. https://ift.tt/SQiyGmY June 26, 2026 at 01:44PM

Show HN: Smart model routing directly in Claude, Codex and Cursor https://ift.tt/GXWqKaT

Show HN: Smart model routing directly in Claude, Codex and Cursor We built a model router that plugs into coding agents (e.g. Claude Code, Codex, Cursor, etc.) and intelligently sends requests to the best model to serve them. Here's a quick demo of running it locally: https://youtu.be/isKhAyivtfM At Weave, we write ~all our code with AI, and it's been getting more expensive. This came to a head when Opus 4.7 was released and, thanks to its tokenizer changes, our costs shot up. We knew we didn't need Opus for everything but we didn't want to lose out on the intelligence for the cases where you really need it. So we decided to build a model router to handle this for us. The Weave Router acts as an Anthropic/OpenAI endpoint specifically for coding agents. It looks at every inference request and intelligently (more on that in a sec) decides what model to send it to, handling all the translations required along the way. So it can use faster/cheaper models (e.g. DeepSeek v4, GLM 5.2, Kimi K2.6) when possible, and frontier models (Opus 4.8 & GPT 5.5 (& Fable whenever it's back)) when necessary. How do we know what model to route to? We trained an RL model on tens of thousands (so far!) of agent traces. We reward the routing model when it selects an LLM that successfully completes the given task. Here's an example: if you ask the router to plan a complex change, it will (probably) route that request to Opus 4.8. Subagents exploring the codebase to gather context will be routed to more suitable models (e.g. DeepSeek V4 Flash). Then when you have the plan ready to implement, it will be (most likely) be handed to a quicker model (e.g. GLM 5.2) to carry it out. We've been using this internally for the last month or so. We've saved 40% on tokens vs. what we otherwise would have paid, with no noticeable differences in quality or velocity. The router is source-available under Elastic License 2.0, so you can self-host it. Or if you prefer, you can also use our hosted version: weaverouter.com. I'll be here to answer any questions you may have! https://ift.tt/FHhA510 June 26, 2026 at 12:40PM

Show HN: Apply for jobs by directly emailing relevant people at a company https://ift.tt/9TmeSWY

Show HN: Apply for jobs by directly emailing relevant people at a company I created this tool that massively increases your chance of landing an interview by directly emailing the relevant people in the companies, making you stand out in the crowd of applications received on job portals. Simply enter the name of the company and position, the tool searches the internet for relevant people, gives you their emails and LinkedIN profiles and also lets you send them highly personalised emails right from your own email. https://dmtheboss.com/ June 26, 2026 at 11:03AM

Show HN: ZeroGate – API gateway to scale cloud GPUs to zero when idle https://ift.tt/vgKV54s

Show HN: ZeroGate – API gateway to scale cloud GPUs to zero when idle https://ift.tt/8zTc06i June 26, 2026 at 10:23AM

Show HN: I built a tool that matches Founders to VCs based on their pitch deck https://ift.tt/rWi16Ih

Show HN: I built a tool that matches Founders to VCs based on their pitch deck Hey HN, I am a VC and 3x venture-funded Founder. VCs and Founders are both playing a low-probability matching game. Better targeting both ways is the way to solve this problem for both parties. So I build Investor Match - Founder uploads a pitch deck (or paste a Docsend link), and it returns 20 ranked investor matches with fit scores, contact details and pre-drafted outreach emails. There is also a deck Teardown feature to improve your deck before sending to Investors. We launched in Jan. and over 3,000 founders have run their decks. There are over 10,000 VCs in the database. Founders have reported over $100M in commitments from matches so far. When I was a founder, I was scraping Crunchbase and Techcrunch for investors and cold-emailing them, generally without enough context on stage, sector fit, or what they actually invest in. Most prior matching systems were dumb key-word matches (you are B2B, Investor X invests in B2B so match). Investor Match does full symentac match after having read all Investor websites, social media, portfolios, actual investments and news articles. It does a much better match for your geography, stage, sector, etc. The core flow: Founder uploads deck, context is extracted and confirmed by Founder to create a Company Card. That card gets matched against investor profiles including stage, check size, sector, currently deploying status, and other thesis signals. Decks are encrypted and never shared without founder consent. Cold emails are generated with specific personalization to the specific partner and their portfolio at the firm. There is also a PDF of the recommendations created with a reason for the fit. Founders with existing investors who send that list to their exising stakeholders tend to get 100% warm intros to these new investors. You have the context to do both cold and find warm intros. The system does not send emails, it is not a spam gun. You still run the outreach process. While the core flow is the Founder one, there there are hundreds of VCs who have active accounts and use the tool to receive deal flow, create a firm specific deck bot, and do warm intros for their portcos raising. This is how I use it as a VC. The last three pre-seed companies I invested in all found their Seed leads in the 20 VCs recommended by this tool. I was able to make 10-15 warm intros instead of in the past when I would remember 1-2 people to intro. The tool consumes millions of tokens per deck and provides the first 3 matches free as well as a high level Deck Teardown. To see full matches and emails, etc, it is $20 for matches and $10 for Teardown. I am just trying to cover server costs (barely today), and this is not a business to monetize founders. At $1 per high-quality VC match, it is a good deal when raising millions. Still in beta, with some rough edges. Would love feedback from anyone who has fundraised recently or built something similar. https://investormatch.pro June 26, 2026 at 09:34AM

Show HN: Bible as RAG Database https://ift.tt/9BAtKfc

Show HN: Bible as RAG Database Made this in a free evening. Index an permissive license translation of the Bible (WEB) into a RAG database to allow returning passages of similar semantic meaning. Lots of fun. For example, "more money more problems" returns Ecclesiastes 5:9-13 which, I'll just say, is spot on.. "Moreover the profit of the earth is for all. The king profits from the field. He who loves silver shall not be satisfied with silver, nor he who loves abundance, with increase. This also is vanity. When goods increase, those who eat them are increased; and what advantage is there to its owner, except to feast on them with his eyes? The sleep of a laboring man is sweet, whether he eats little or much; but the abundance of the rich will not allow him to sleep. There is a grievous evil which I have seen under the sun: wealth kept by its owner to his harm." Anyway - thought it was fun enough to share. It's slow and I vibe coded it so I haven't sorted out how to make it not take 15 seconds to vector search against the full 4GB index. https://ift.tt/1sofnQV June 24, 2026 at 09:42PM

Show HN: Hikaru Labs – Bulk image and file processing, 100% in-browser https://ift.tt/tJVSyLw

Show HN: Hikaru Labs – Bulk image and file processing, 100% in-browser https://hikarulabs.xyz June 25, 2026 at 11:48AM

Show HN: Top' for Redis Using eBPF https://ift.tt/g9byH6p

Show HN: Top' for Redis Using eBPF https://ift.tt/BdLTfrg June 25, 2026 at 01:01PM

Show HN: iOS Apps on Linux https://ift.tt/0FvAt6Q

Show HN: iOS Apps on Linux We developed and tested SwiftUI for Linux (and AppKit, NSFoundation, etc.) -- looking for more Swift apps to test on Linux! https://ift.tt/1Eb2a9W June 25, 2026 at 11:29AM

Show HN: Navatala GPU – multi-back end GPU kernels and Python bindings https://ift.tt/BQkcwmr

Show HN: Navatala GPU – multi-back end GPU kernels and Python bindings https://ift.tt/mG2hJP5 June 25, 2026 at 10:58AM

Show HN: FileVeil · Hide Any File Inside Another File https://ift.tt/j0G7vtm

Show HN: FileVeil · Hide Any File Inside Another File I built FileVeil to hide any file inside another file. Use a photo, video, document, audio file, or archive as the cover file. The resulting file still looks and works normally while securely containing encrypted hidden files. Everything runs locally in your browser. No uploads. No servers. AES-256-GCM encryption. Video demo: https://www.youtube.com/watch?v=tcxjIDRZh9s I'd love your feedback on the implementation, UX, and real world use cases. https://fileveil.com/ June 25, 2026 at 10:07AM

Show HN: I made Google Trends for Hacker News by indexing 18 years of comments https://ift.tt/6JLDQ5o

Show HN: I made Google Trends for Hacker News by indexing 18 years of comments https://ift.tt/3ZEUWIw June 25, 2026 at 10:08AM

Show HN: Follow the Thread – a calmer, typographic way to read Wikipedia https://ift.tt/UDZbPrI

Show HN: Follow the Thread – a calmer, typographic way to read Wikipedia https://ift.tt/2yt3dJn June 24, 2026 at 01:16PM

This Laser Hair Growth Device Actually Works. For Prime Day, It’s Cheaper Than Ever.

It’s hands-free, mess-free, and now, $100 off.

Show HN: DBOSify – Drop-in Temporal replacement built on Postgres https://ift.tt/rY8iopO

Show HN: DBOSify – Drop-in Temporal replacement built on Postgres https://ift.tt/zeQGiCU June 24, 2026 at 01:20PM

Show HN: Metaspec: The DpANS3R Common Lisp Spec in S-Expr and HTML Format https://ift.tt/5qCmZME

Show HN: Metaspec: The DpANS3R Common Lisp Spec in S-Expr and HTML Format I started this project back in 2015, to translate the TeX original specification into an easily parsed format (s-doc), and to create an HTML rendering of that format as a proof of concept. The project is homed here: https://ift.tt/wMEAOnh Differences from the Hyperspec (from the README): - Most importantly, it is free to modify and distribute. - The original TeX is very hard to parse and use for things other than generating a printed copy. The Hyperspec is an HTML rendering which can be parsed as HTML, but loses a lot of information. The Metaspec has an easily parsed intermediate form that can be used for all kinds of purposes, like converting into lookups. - Math equations are rendered using MathML. - Includes the acknowledgements and appendix sections. - Uses progressively enhanced Javascript to provide search and light/dark theme switching. - Incorporates over 145 patches for content, using corrections accumulated over the years, and documented in the errata page. - Includes TeX comments, which can contain interesting historical data. - Includes links and identifiers to bibliographical references. https://metaspec.dev/# June 24, 2026 at 12:28PM

Show HN: peerd – AI agent harness that runs entirely in your browser https://ift.tt/xuJ1Kh8

Show HN: peerd – AI agent harness that runs entirely in your browser Hey HN. http://peerd.ai is an AI agent harness that lives entirely in your browser as a web extension. You don’t have to install a separate “AI browser”. You don’t have to bolt on or run some external process or manage a clunky mcp integration. It’s just a fully contained web extension, written in no build vanilla JS with minimal non-browser dependencies, using your own provider keys, and Apache 2. This isn’t just a fun hack. While it has largely been a solo side project, I genuinely believe the browser and the web could be the most natural platform for AI agents to operate safely, autonomously, and most importantly without A2A middlemen (more on that in a sec). To demonstrate that point peerd doesn’t just drive browser automation. It spins up isolated sandboxes using tabs and worker instances to support various real workload types. Those include headless JS computational work, visual JS notebooks, personal client side apps, and real Linux VMs on top of wasm with full http networking. The industry discourse over the last several months has been dominated by “which substrate is the best for ai agent sandboxes” with many competing answers focused on different models and use cases. Cloudflare is one of the most prominent examples, positioning its v8 isolate based workers as the best in class solution thanks to faster than container startup times and strong isolation guarantees. The v8 isolate is of course the product of chromium, which runs on billions of browsers around the world for free. The browser as a whole is perhaps the most battle tested sandbox system in the entire software industry. It’s been built on 3 decades of learning from hostile content, hostile code, and hostile users. Native and cloud agents are necessarily rebuilding all or most of this posture from scratch. peerd doesn’t. It leverages everything the browser has to offer and pushes it to its functional limits, while inheriting its security baseline and isolation from the host system. Robust sandboxing isn’t the only thing the browser offers and peerd uses. It comes with extremely powerful and underrated primitives, from webCrypto, webRTC, webAuthn, webGPU, and ~soon WebNN. Direct web access, with your real live sessions, and api calls with fetch present an alternative model to MCP integrations. The agent can write and spawn web apps right there in a tab, no hosted service necessary. Then there’s the A2A piece: peerd already has a rudimentary p2p (peerd-to-peerd?) network in place using webRTC. Today you can connect with peers on the network, add them as contacts, and share signed apps you’ve created. I’m working on extending these apps to be able to leverage the same p2p network to support decentralized web apps (dwapps), as well as facilitate true p2p A2A with no platform or middlemen. Given this is an early part time project, this is an extremely experimental build and in a v0.x preview state. I’ve taken care to attempt to address the lethal trifecta: the main agent loops/sessions never ingest untrusted DOM code or possess low level navigation tools. It delegates those tasks to dedicated web runners with no wider tooling or secrets access that return summarized results. Both the DOM and the summarized results are bracketed as untrusted, meaning two stacked prompt injection escapes are needed. All egress goes through a central module that has a customizable deny list, and only models calls to designated allowed endpoints are possible. See more in the docs, site, and the code itself. Ultimately, use at your own risk. Today anthropic, open router, local ollama, and even an experimental WebGPU instance of Gemma are supported. Honest limitations: Chrome store and AMO are still pending until it can get more eyeballs and live usage. Just loading unpacked from GitHub is the easiest way to go, and as a bonus makes it easy to audit thanks to no build. Linux on wasm depends on the Cheerpx engine, which is not open source and has restrictions for commercial use. That may be a good reason to reassess it compared to alternatives, but it’s also the most performant and looks closest to implementing 64bit support. Poke around, use it, critique it, and have fun. https://ift.tt/bQSkVjI June 23, 2026 at 11:05AM

Show HN: Forte – Cloud infra to get startups to production faster https://ift.tt/Ladkhfp

Show HN: Forte – Cloud infra to get startups to production faster Forte is an opinionated cloud platform that gets developers to production faster. Developers bring their code and Forte containerizes it with autoscaling and no cold starts, securely configures auth, and provides logging insights and monitoring out of the box. I used to help lead service development at AWS, and even before AI coding was widespread, our biggest bottleneck was rarely feature development. We would spend months on security prep, observability tooling, on-call optimization, and other overhead before launching new features. When I worked in startups, every team hit a surprisingly similar set of problems and spent weeks rebuilding auth, logging, monitoring, and payments. Platforms like Heroku, Render, and Railway are helpful for getting a container running but don't provide the rest of the tooling the teams need to go to production -- auth, secure defaults, and request-level logging. We built Forte to solve that entire stack of problems. You can check out Forte at https://ift.tt/eRiJKcF (it's free to sign up and doesn't require a payment method). We'd love to hear your questions and feedback! https://ift.tt/eRiJKcF June 24, 2026 at 12:06PM

Show HN: Graft – one golden VM image for your Mac dev box and CI runners https://ift.tt/Qdj0lt1

Show HN: Graft – one golden VM image for your Mac dev box and CI runners https://ift.tt/oP1ptzg June 24, 2026 at 10:57AM

Show HN: Orchid – Local-first record and replay for AI agent debugging https://ift.tt/crlbYKL

Show HN: Orchid – Local-first record and replay for AI agent debugging Orchid (Orchestration interactive debugger) is a zero-instrumentation proxy that captures every API & LLM call in your agent pipeline, then lets you inspect and replay the entire run locally, step by step. No instrumentation, no vendor lock-in, no cloud dependency. It also provides a visual inspector and MCP server, so you can inspect the session yourself or use your favorite agentic coding IDE to debug your agent runs. I built it because I was tired of debugging agent failures by grepping through logs, and the available AI observability tools all seemed to require intrusive instrumentation and/or sending my prompts and responses to a cloud service. I wanted something that would let me debug agent runs locally, without having to worry about vendor lock-in or data privacy. Orchid is that tool. The call inspection features work extremely well, at least for my use cases, but the replay feature is perhaps more interesting. It makes LLM pipeline testing deterministic without mocking or re-running expensive API calls. Free, self-hosted, runs on your machine or infrastructure: https://ift.tt/59kiTKJ Would love feedback from anyone building multi-step agentic systems or struggling with non-deterministic LLM test failures. https://ift.tt/59kiTKJ June 24, 2026 at 10:48AM

Show HN: eBook to audiobook narration with realistic AI voices https://ift.tt/VyPKGA0

Show HN: eBook to audiobook narration with realistic AI voices For a while I've wanted to try out the new AI voices for long-form narration, but everything I found required a subscription that didn't justify my limited usage. I came across the open Kokoro model [0] and the voices are very good -- good enough to listen to for hours without the fatigue I got from legacy, robotic TTS voices. The model is 82m parameters and designed to run fast, but I still struggled to get reasonable times from CPU inference on my 12-core laptop. I thought a cloud-based GPU service would let me generate audiobooks fast enough to feed my own self-hosted library, and that same pipeline could become a product other people could use. I had two goals in building this: get some exposure to AI multi-agent coding workflows, and build a TTS product targeting ebook to audiobook conversion specifically. 99% of ebookaloud was written by DeepSeek v4 in OpenCode. I've used about 750 million tokens costing $12 in credits over the course of a month, and I'm very pleased with the results. Every change/feature went through a plan -> implement -> test -> review -> correct -> commit cycle with a mix of Pro and Flash agents. This was generally limited to one or two concurrent workers. I had a separate eval agent for quality control on various parts of the extraction and synthesis pipeline, which I could run 8-10 at a time. I may be approaching Yegge's Stage 6 [1] in terms of AI workflow automation. I later set up Claude Code and ran Opus 4.8 side by side with DeepSeek. There are definitely quality differences, but I'm an experienced developer with a hands-on approach. I didn't write any of the code, but I have read critical sections of what it generated and had extensive conversations with DS Pro about each step of the approach. Opus didn't have much critical to say about DeepSeek's choices, and I'm not convinced a frontier model would have made an appreciable difference for my workflow. I suspect on a large codebase the differences would become more apparent, but the few changes I implemented with Opus had similar issues to all the models I've used: random changes without my direction, over-complicating simple solutions, taking unanticipated/destructive actions when it gets stuck, etc. I do see Opus being capable of handling more of the complex planning and orchestration that I was involved in. That's something I may want sometimes but not others. As to the product itself, there are a lot more sophisticated solutions out there. I'm not trying to compete with ElevenLabs. I'm targeting m4b generation for a seamless audiobook experience with a pay-as-you-go pricing model and good-enough output quality. This is the first product I've ever tried to commercialize, and AI code generation put something polished within reach. Without AI, this would have taken me 6-8 months of manual research and development, and I would have gotten burned out long before completing it. I have a free sample on the front page of the site if you just want to see what it generates in terms of voice/format. I made a few opinionated decisions regarding output quality. I aimed for 140 wpm for most of the voices to match industry standards, but some are much slower or faster and lose prosody at that rate. Rather than give users a wall of options, I'm deferring to the playback device for things like speed control. If the site sees real usage I'd like to expand to support Kokoro's other languages, and extraction and synthesis from PDF would round out the product quite a bit. [0] https://ift.tt/U4u0WwQ [1] https://ift.tt/bEhLQBt... https://ebookaloud.com June 24, 2026 at 11:04AM

Show HN: L0/L1/L2 agents, leases, gates, audits, Git-worktree isolation https://ift.tt/lfgH9Qd

Show HN: L0/L1/L2 agents, leases, gates, audits, Git-worktree isolation https://ift.tt/UV7zqlb June 24, 2026 at 10:22AM

Show HN: Nub – A Bun-like all-in-one toolkit for Node.js https://ift.tt/qujNzQX

Show HN: Nub – A Bun-like all-in-one toolkit for Node.js https://ift.tt/WP7TRJI June 24, 2026 at 10:14AM

Show HN: Caplets - Give your agent capabilities, not giant tool walls https://ift.tt/6YrRtjN

Show HN: Caplets - Give your agent capabilities, not giant tool walls https://caplets.dev June 23, 2026 at 12:31PM

Show HN: I gave Claude Code the keys to the Visual Studio debugger https://ift.tt/0dNBYjD

Show HN: I gave Claude Code the keys to the Visual Studio debugger I use Visual Studio daily, and Claude Code only ships native integration for VS Code (annoying). So, I built the Visual Studio half myself. It's an unofficial extension that speaks Claude Code's undocumented IDE protocol. It started simple. Review Claude's edits in the real VS diff and accept or reject there, with no duplicate y/n prompt in the terminal, plus sharing the C# and C++ compiler errors with it directly. The infra I built for the extension allowed me to add the interesting part, the VS debugger. When you're paused at a breakpoint, Claude can read the call stack and locals, and with a toggle it can drive the debugger itself: set breakpoints, step, start and stop a session, and find a bug by running the code instead of reading it. There's a short walkthrough in the README where it catches a bug that never shows up in the output, by watching a counter fail to reset as it steps through a loop. Would really appreciate if you take the time to check it out. Thanks! https://ift.tt/BDFlso8 June 23, 2026 at 12:14PM

Show HN: Treedocs: Documentation that automatically checks for staleness https://ift.tt/SIJugLb

Show HN: Treedocs: Documentation that automatically checks for staleness https://dandylyons.github.io/treedocs/ June 23, 2026 at 11:07AM

Show HN: TikZ Editor – WYSIWYG editor for figures in LaTeX https://ift.tt/TL507Qz

Show HN: TikZ Editor – WYSIWYG editor for figures in LaTeX Hi all! TikZ is a widely-used LaTeX package for drawing figures in papers. It uses commands like \draw[->] (0,0) -- (1,2); to draw lines, shapes, text, etc. Academics usually code up their figures by hand, so there is lots of twiddling around with the coordinates and recompiling until things look nice. I guess it’s a bit like SVG, but it’s more code than markup, for example it has loops with \foreach. I built an open-source WYSIWYG TikZ editor (available for web and desktop) that allows you to edit your TikZ source code visually by dragging and resizing elements. It simultaneously shows the source code and the rendered figure, and lets you edit either one while the two views stay in sync. I’m not aware of any other editors that are simultaneously source editors and WYSIWYG (even for editing SVG or HTML), and I’m quite pleased with how well the combination works. The way the app is implemented is by parsing the TikZ code, and at all times keeping track of the exact source location of each object. Thereby, when a user drags an element to a new position, the app can override just the numbers in the coordinate without changing anything else in the code (such as line breaks or indentation). This approach essentially required reimplementing a large fraction of TikZ, which is the kind of task that no human would ever want to do. I think building software that doesn’t exist yet because it would be impossibly tedious to code up is one of the great new possibilities thanks to coding agents, and it’s worth brainstorming for other examples. (This app was built almost entirely by Codex.) Implementing the app came with lots of fun side quests, including building converters from SVG / pptx / ipe to TikZ, re-implementing the LaTeX hyphenation and line-breaking algorithm to support multi-line nodes, and making a color picker that uses the red!20!black color mixing notation used in LaTeX papers. https://ift.tt/YfwGyz6 June 23, 2026 at 10:24AM

Show HN: Transformer Primitives – A visual explainer you can send to anyone https://ift.tt/10fhtr2

Show HN: Transformer Primitives – A visual explainer you can send to anyone I have had a few conversations in the past year with non-technical folks (traditional finance types, consultants) who asked for a simple explainer on how GPTs work. These people generally have the horsepower to grasp new concepts quickly but don't necessarily have the math background to dig in super deeply and want a stronger framework than "they predict words". I had generally been pointing them to Karpathy, Illustrated Transformer, and other youtube content but I figured something more hands on without the math requirement might be better at explaining questions like "why matrix multiplication?". I built this as a simple 60-70 minute interactive course with some demos I could send along to them. I've found it effective as the initial foray into understanding jargon and concepts before they graduate to Karpathy et al. It's free, no signup required. I would love feedback on where it might lose a non-technical reader, and where someone who does this for a living thinks I have simplified past the point of being correct. understandgpt.xyz https://understandgpt.xyz/ June 23, 2026 at 09:59AM

Show HN: Bun-sqlgen – Type-safe raw SQL for Bun, no ORM https://ift.tt/zs1vxFZ

Show HN: Bun-sqlgen – Type-safe raw SQL for Bun, no ORM https://ift.tt/ZMYIEB1 June 23, 2026 at 10:20AM

Show HN: perl-lsp – annotation free static analysis for Perl https://ift.tt/qkR5OAN

Show HN: perl-lsp – annotation free static analysis for Perl Built in Rust on top of ts-parser-perl and tower-lsp. Witness bags with graph traversal (value edges, call flow edges). How it works: - builds witnesses and scopes by walking the parse tree. Fully known values get concrete types, otherwise they get an edge pointing to the last witness we have for this symbol - a worklist runs to a fixed point: reducers fold each symbol's witnesses and chase edges. At this point, the witness bag is complete and ready to use - all downstream features are queries into the bag, following along the graph edges that are relevant Extensible - you can bring your own Rhai plugin to shortcut common patterns (exporters and OOP frameworks), or even add new types of definitions (worker tasks and web routes). The build/query timing distinction with edges lets you late bind types, which is duly similar to how Perl itself works: `Foo->new` isn't known if it's the constructor for Foo or calling a method on the sub name `Foo`; late binding lets you make that call after the worklist folds. https://ift.tt/VaJZBYR June 23, 2026 at 09:17AM

Show HN: Oak – Git replacement designed for agents https://ift.tt/EjzKn63

Show HN: Oak – Git replacement designed for agents Oak is a version control system I've been working on designed for agents. It improves the speed and context your agents need when working on serious projects. With virtual mounts, agents locally and in the cloud no longer need a full copy of a repo to get working. You can work on many tasks in parallel without needing to download everything or fight worktrees. Version control shouldn't waste you or your agents time. It should be fast, creative and fun to make things with agents. Oak is still early in development. There's no Windows build and missing plenty of features (no CI, no issues, no comments). We still use GitHub Actions for building Oak now, but we've been fully bootstrapped on Oak with no Git backup for several months: https://oak.space/oak/oak . Blog post: https://oak.space/blog#git-is-forever Docs: https://oak.space/docs https://oak.space/blog June 22, 2026 at 11:37AM

New on TikTok: Commented on@True Crime World’s post

Watch our new video on Tiktok! https://ift.tt/yke7AnF

Show HN: Block/buzz: a workspace built for teams of humans and agents https://ift.tt/herlHU7

Show HN: Block/buzz: a workspace built for teams of humans and agents https://ift.tt/Su6KdzR June 22, 2026 at 01:16PM

Show HN: Selector Forge – browser extension for AI-generated resilient selectors https://ift.tt/evU2zCb

Show HN: Selector Forge – browser extension for AI-generated resilient selectors Hi HN, I'm Ahmad from the Intuned ( https://intunedhq.com ) team. Today, we're releasing and open-sourcing Selector Forge ( https://ift.tt/X1oIpgJ ), a browser extension that generates reliable CSS/XPath selectors using AI. You can use it to create a selector for a single element or for an array of elements. The selectors it creates are meant to be "semantic" and more resilient to page changes than what Chrome DevTool’s “Copy Selector” (and other similar extensions) give you. Those tend to hand you something brittle like `#top > div.w-100.ph0-l.ph3.ph4-m > h1 > span`, which can break with a minimal page change. Selector Forge aims for selectors that don't break as easily. Here are some selectors that Selector Forge created: `//div[@aria-label="Showing weekly downloads"]//p[@aria-live="polite"]` (item selector) and `//*[local-name()='svg' and @aria-label="Download statistics"]/following-sibling::div` (list selector). Here is a video demo of using the extension: https://www.youtube.com/watch?v=8IjjeDQkKmo Selector Forge on Chrome: https://ift.tt/HKVZpac... Selector Forge on Firefox: https://ift.tt/TgxmsVe... Selector Forge code: https://ift.tt/tOhenFV Backstory: For the past couple of years we've been building Intuned Agent, a coding agent for building and maintaining browser automations. We quickly figured out that the most fragile part of any browser code is usually the selectors and that creating good selectors can go a long way towards improving the quality and reliability of the automation itself. So we abstracted selector creation into its own agent, wrapped it as a tool, and let our codegen agent call it. LLMs by default don't do a great job generating good selectors, so this turned out to be really useful and improved the code our agent generates. We recently thought that this piece (the selector agent/creation) is useful on its own (outside our platform) so we packaged it as a browser extension. That’s this post! Selector Forge is open source, and the version in the browser stores (Chrome and Firefox) is free for up to 200 selectors/month. Unlimited usage is part of our paid plans. We realize most developers aren't writing this kind of code by hand anymore, so the next step is exposing this functionality in a way coding agents can call directly, over a CLI or MCP. Here's our roadmap: https://ift.tt/891kfdC Excited to hear your thoughts, questions, and feedback! https://ift.tt/tOhenFV June 22, 2026 at 10:21AM

Show HN: React Native Boost – swaps RN's Text/View wrappers for native ones https://ift.tt/DmWE4L6

Show HN: React Native Boost – swaps RN's Text/View wrappers for native ones https://ift.tt/sbvBgSt June 22, 2026 at 01:01PM

Show HN: Smolsonic – A Subsonic-compatible music server written in Rust https://ift.tt/7QKYnfi

Show HN: Smolsonic – A Subsonic-compatible music server written in Rust https://ift.tt/jNgGASd June 22, 2026 at 12:40PM

Show HN: Socket to Me, a static file server that runs in the browser https://ift.tt/KTWEQaZ

Show HN: Socket to Me, a static file server that runs in the browser The service lets you share an entire folder - not just a single file - with anyone on the Internet in a single click. Under the hood, GET responses are hydrated with file fragments streamed over a duplex WebSocket connection. Close the browser tab, and the server disappears. Files can also be password-protected. I built it because I needed a way to share a static website with a client without first uploading the work to a cloud service. https://socket2.me/ June 22, 2026 at 08:24AM

Show HN: Revenant – automatic LLM powered reverse engineering and reimplement https://ift.tt/3n9ZjRV

Show HN: Revenant – automatic LLM powered reverse engineering and reimplement I am a hardware engineer and security researcher and I've been wondering whether my work could be partially automated, so I can focus on other topics as well, so I build revenant - a LLM powered (Claude, OpenAI, local AI) toolkit that builds around radare2, ghidra etc and can fully automatically analyze firmware, implement open source skeletons incl. pinouts, hardware bringup, peripheral bringup etc. or can even 1:1 replicate existing firmware so old hardware can be resurrected with modern toolchains. Some applications are: - Give old hardware new life - Security Analysis of shady firmware Check it at: https://ift.tt/eQw1kyE I would love some input on this and maybe some recommendations for improvements. June 22, 2026 at 10:15AM

Show HN: DebugBrief – turn debugging sessions into reports, no AI https://ift.tt/Me9SR5U

Show HN: DebugBrief – turn debugging sessions into reports, no AI https://ift.tt/WHND9h4 June 21, 2026 at 03:57PM

Show HN: GreyFox – Free self-hosted AI proxy, token quotas, and local cache https://ift.tt/kVgGRaP

Show HN: GreyFox – Free self-hosted AI proxy, token quotas, and local cache https://ift.tt/LzvmHZu June 21, 2026 at 03:09PM

Show HN: CleverCrow: give tokens to your favorite projects https://ift.tt/yfi7oc4

Show HN: CleverCrow: give tokens to your favorite projects Howdy all. I'm Zack :wave:. I've been thinking about the problem of misguided AI pull requests and figured I'd throw a possible solution out there for feedback. Basically, CleverCrow lets supporters give tokens to a GitHub repo (or set of issues in that repo) for the maintainers to use to build/fix stuff. The fun implementation challenges have been around implementing the pooling dynamics and keeping the maintainers in charge while the backers are motivated to support their work. https://clevercrow.io June 21, 2026 at 03:06PM

New on TikTok: She asked what time it is 🤷🏾‍♂️ #fyp 😂😂😂😂

Watch our new video on Tiktok! https://ift.tt/YGsWBDK

Show HN: Pulse – Dashboard for Claude Code, approve tool calls from your phone https://ift.tt/xi0dbju

Show HN: Pulse – Dashboard for Claude Code, approve tool calls from your phone Hi everyone, I'm a student from Flanders and I like to use Claude Code for my purposes, ideas and also just for fun and also make solutions for problems in our world!) So that's why I built "Pulse", it's an local application that you can easily install to your device and easily follow what your claude agent is doing right now in your terminal session with an ambiance design and easily give permissions for your agent. For those who wants to see directly how much tokens you spent, and how much the session costs, and approve tool calls from everywhere from your phone and everything runs locally without an account can install Pulse from GitHub: https://ift.tt/vMQI7ER https://ift.tt/vMQI7ER June 20, 2026 at 04:46PM

New on TikTok: Commented on@Rock Hall’s post

Watch our new video on Tiktok! https://ift.tt/uJ3FYAd

Show HN: Stock analysis tool with quality scores and fundamental charting https://ift.tt/DMyV2Ba

Show HN: Stock analysis tool with quality scores and fundamental charting This is a project I have been working on for the past several months Extracted all fundamentals for every US company from SEC filings through XBRL tags. https://intrinsiqq.com June 21, 2026 at 09:49AM

Show HN: An ASCII 3D Rendering Engine https://ift.tt/oIC6LvE

Show HN: An ASCII 3D Rendering Engine https://glyphcss.com June 20, 2026 at 03:10PM

Show HN: Web-Based FPGA Viewer https://ift.tt/vXms5NE

Show HN: Web-Based FPGA Viewer As part of our EDAcation project, we are building an extension for VSCode to facilitate digital hardware design. We built an FPGA viewer to integrate into VSCode, but since VSCode is essentially just a web browser anyway, we figured why not publish it as a separate website as well? So that's what we did, and you can see the results for yourself on the linked webpage. You can inspect a variety of iCE40 & ECP5 FPGAs as well as visualize various PnR results. We included some example designs, but if you are familiar with Nextpnr, you can also upload your own. All data stays local, the viewer runs entirely from within your browser. The chip renderer is written in Rust and compiled to WebAssembly. You can check out the code if you want, all of our projects are fully open source. Our goal is to make digital hardware design more accessible, and this project fits right in with that mission. Curious to hear your opinions! https://edacation.github.io/nextpnr-viewer/ June 20, 2026 at 09:30AM

Show HN: StartupWiki – A Free Alternative to Crunchbase https://ift.tt/U5PcV6h

Show HN: StartupWiki – A Free Alternative to Crunchbase I've been building StartupWiki, a free startup database designed to make it easier to discover and research companies. The original motivation was frustration with how difficult it can be to find information on early-stage startups. Most databases need accounts, or subscriptions, ro just feel too cluttered. I wanted a website that felt like Wikipedia, no accounts, no subscriptions, no weird metrics, just go in, the info is on the page. The project is still very early, but currently includes: Startup profiles Search and filtering Company categorization Public API (in progress) I'm especially interested in feedback on: What information you look for when researching startups Features missing from existing startup databases API use cases I'd love to hear feedback. https://ift.tt/mUO4e2W June 20, 2026 at 11:59AM

Show HN: Tiny.Place – AI Social network for orchestration, payments & jobs https://ift.tt/JGg4mEf

Show HN: Tiny.Place – AI Social network for orchestration, payments & jobs https://ift.tt/elJQ2VD June 20, 2026 at 11:39AM

Show HN: Hi-shell – type commands in English, get ghost text in zsh https://ift.tt/BYkMXdj

Show HN: Hi-shell – type commands in English, get ghost text in zsh https://ift.tt/1cwDpWz June 20, 2026 at 10:54AM

Show HN: Criterion Closet as a website – pull any of 1,247 films off the shelf https://ift.tt/fqgStZ7

Show HN: Criterion Closet as a website – pull any of 1,247 films off the shelf https://the-criterion-closet.vercel.app June 20, 2026 at 09:18AM

Show HN: Pagecast – Publish Markdown/HTML Reports to Cloudflare Pages https://ift.tt/roDgbNz

Show HN: Pagecast – Publish Markdown/HTML Reports to Cloudflare Pages I built this because I kept generating HTML/Markdown reports from Claude Code/Codex and needed a permanent share link instead of a localhost tunnel. Pagecast is a local CLI that publishes those files to your own Cloudflare Pages account. It supports Markdown and HTML, stable URLs, renaming, republishing to the same URL, and watch mode for continuous updates to same file. It is MIT licensed. The main design choice is that there is no hosted Pagecast account. It uses your Cloudflare account and deploys there directly and has claude code and codex integrations as skill/hooks. Basically it can be used as a replacement for codex sites or claude artifacts https://ift.tt/7cQWseb June 18, 2026 at 03:42PM

Show HN: Music from every single country on Earth, generated in Esperanto https://ift.tt/U58S4rs

Show HN: Music from every single country on Earth, generated in Esperanto https://ift.tt/RLvPGFy June 19, 2026 at 09:20AM

Show HN: Metiq: a real time 3D globe for 100 public datasets https://ift.tt/9IL21Os

Show HN: Metiq: a real time 3D globe for 100 public datasets The concept for metiq.space came after playing Global Magnates with friends and realizing how fragmented live global data is. ships, aircraft, satellites, ports, weather, hazards, infrastructure, cyber, and public datasets all exist, but they usually live in separate tools and maps. The goal was to build one interactive 3D globe where live public data could be visualized by latitude, longitude, and altitude. Surface data stays on the globe, while aircraft, satellites, and other above surface things can be represented in actual 3D space instead of being flattened onto a map. The outcome is an interactive globe that showcases Earth, air, sea, space, cyber, defense, infrastructure, politics, and the list is continuously growing. Majority of development right now is going into data filtering and deduping. https://metiq.space June 16, 2026 at 10:43AM

Show HN: SEO Audit and Backlink Monitoring. All-in-One Platform https://ift.tt/7HdCyEY

Show HN: SEO Audit and Backlink Monitoring. All-in-One Platform SeLinkPro combines a full-site technical audit (4xx/5xx, broken links, missing tags, indexing blockers) with automated backlink monitoring, bulk indexation checks, and domain metric analysis. One platform. Complete SEO control. https://selinkpro.com/ June 19, 2026 at 10:56AM

Show HN: Wolffish – An OS personal desktop AI agent https://ift.tt/DV3FdpN

Show HN: Wolffish – An OS personal desktop AI agent Heya everyone I'm Younes, and I've been building Wolffish for a while now. I want to tell you why... I love AI. I use it every single day. But every AI agent I tried left me disappointed. Either, it's a CLI tool that is a black box not even the creators understand, or it is a server running with exposed ports inviting all the malice of the internet, or it breaks after every update, or it takes 30 minutes just to set up before you can even say hello, or the worst one yet, you need a course and certificate to begin using the darn thing ... I just wanted something simple. Something I install, open, and it works. Something my dear grandma could use. Something that actually does real work on my computer — not just generates text I copy-paste somewhere else. Something I could hand over the keys to my private digital setup with peace of mind. So I built Wolffish. It's a desktop app. You install it and it works out of the box. No server. No setup templates. No bullshit. No broken updates. It's secure — your data stays on your machine. PERIOD! It's private — your data is not saved on some dude's server. It's easy to use, easy to extend, and easy to understand. It works with DeepSeek, GLM, Claude, GPT, and even runs fully offline with local models. It's free. It's open source. And I use it every single day. Wolffish is built for a future where open-weights models are frontier-level in intelligence — you download them, run them, and own them. Your digital agent works for you and belongs to you. Repo: https://ift.tt/ONWJftc Demo walkthrough: https://www.youtube.com/watch?v=MA6KkeZyFF4 Cinematic reveal: https://www.youtube.com/watch?v=TKdTWd6BXR8 I'd love to hear what you think https://www.wolffi.sh/ June 19, 2026 at 07:32AM

New on TikTok: Commented on@DMarie❌️’s post

Watch our new video on Tiktok! https://ift.tt/I5C6HDN

Show HN: HumansMap – Explore family dynasties, relationship, org networks https://ift.tt/vT1Okdy

Show HN: HumansMap – Explore family dynasties, relationship, org networks https://ift.tt/dGu8aJB June 18, 2026 at 12:24PM

Show HN: 10x better performance from the Coding Harnesses with LLM-wiki https://ift.tt/fl7QB4W

Show HN: 10x better performance from the Coding Harnesses with LLM-wiki https://llm-wiki.net/ June 18, 2026 at 11:23AM

Show HN: Sudoku Word Search," hidden words required to solve letter-sudoku https://ift.tt/0yKutJ2

Show HN: Sudoku Word Search," hidden words required to solve letter-sudoku I was screwing around with trying to mash up puzzle types and reinvented what I'm calling Sudoku Word Search. It's a letter-sudoku puzzle with words hidden in the puzzle, and you have to deduce where the words are in order to solve them. As in, the puzzle does not have a unique solution using sudoku logic alone. You must use one of two forms of hidden word logic to finish the puzzle. 1) Deduce where a word must be placed and add letters, or 2) deduce where a word may not be placed and restrict letters. To keep it more sudoku like and aid in solving, every row, column, and box has at least one letter of a found word. In playtesting I thought it was fun, although at times very difficult for me (I'm not an expert sudoku player), so I thought I'd build it out to share. The puzzles are generated by creating racks of 9 unique letters, finding all words that can be made with those letters, generating sample grids, finding the words in them, throwing out candidates that don't fit the word placement criteria, then carving the board by removing letters until two constraints hold: we have >=2 solutions by sudoku logic and exactly 1 solution when the word search logic is added. Overall about 60000 puzzles are generated and thrown out for every sound one. I used Claude pretty extensively for the code, which includes: - Puzzle generator - Puzzle solver - Puzzle explainer - Static website (Cloudflare) - Online puzzle player (local storage) - Online static puzzle walkthrough - Print book layouts - PDF layouts Overall, it's been a lot of fun to focus on for a few weeks. https://ift.tt/uyGf1K3 https://ift.tt/Jfp9IY6 June 18, 2026 at 10:00AM

Show HN: Gerrymandle - Daily puzzle game where you redraw electoral districts https://ift.tt/JG6Ntna

Show HN: Gerrymandle - Daily puzzle game where you redraw electoral districts https://gerrymandle.cc/ June 18, 2026 at 10:16AM

Show HN: Mantyx – Batteries included managed agent runtime https://ift.tt/6KesMAY

Show HN: Mantyx – Batteries included managed agent runtime https://mantyx.io/ June 17, 2026 at 01:01PM

Show HN: The full Minecraft game as an embeddable Framer component https://ift.tt/Sq4tmax

Show HN: The full Minecraft game as an embeddable Framer component https://ift.tt/tQ4DEb1 June 17, 2026 at 12:43PM

Show HN: Deconvolution – a Rust image deconvolution and restoration crate https://ift.tt/kbI8vYd

Show HN: Deconvolution – a Rust image deconvolution and restoration crate I've been working on deconvolution, a comprehensive Rust image deconvolution and restoration library. Deconvolution implements 28 different image deconvolution/restoration methods which range from practical blur removal techniques to research-grade scientific imaging algorithms. Features: - Top-level functions use image::DynamicImage and return images - Inverse filters, Wiener, Richardson-Lucy, constrained, proximal, Krylov, MLE restoration - Blind Richardson-Lucy, blind maximum likelihood, parametric PSF estimation - Kernel2D, Kernel3D, Transfer2D, Transfer3D, Blur2D/Blur3D - Gaussian, motion, defocus, microscopy models, support utilities, PSF/OTF conversion - Edge tapering, apodization, range normalization, NSR estimation - Deterministic blur, noise, synthetic fixture generation - ndarray support for 2D image arrays and 3D volume this project is a WIP, of course:) https://ift.tt/Mpb1fm7 June 15, 2026 at 08:40AM

Show HN: An 8-bit live gamecast for baseball https://ift.tt/cQXGHuv

Show HN: An 8-bit live gamecast for baseball Hey HN, I built a website to watch live baseball games in an 8-bit broadcast. It takes live MLB data streams and converts them into near real-time pixel art gamecasts. Been waiting to share this for when there’s actually a good slate of games happening since the site is pretty bare otherwise. Here is today's schedule: Mets @ Reds - 9:40am PDT https://ift.tt/bOTlutr Royals @ Nationals - 10:05am PDT https://ift.tt/1rx2Zel Marlins @ Phillies - 10:05am PDT https://ift.tt/MpG5fX0 Tigers @ Astros - 11:10am PDT https://ift.tt/LBoFrG6 Padres @ Cardinals - 11:15am PDT https://ift.tt/u5Wcsdt ..and another 14 games throughout the later day. I'm still early on in this project, but I've tried to add little details with actual stadiums, day and night modes, between inning graphics and interstitials, live scoreboards, etc. Would love any feedback and ideas. Thanks for checking it out! https://ribbie.tv/watch June 17, 2026 at 12:44PM

Show HN: In-browser Python/Pandas/Git practice with animated Git simulator https://ift.tt/QZC1dnx

Show HN: In-browser Python/Pandas/Git practice with animated Git simulator I've created an in-browser Python/Pandas/Git practice environment for my online learning platform and also for my corporate training classes. I'd be happy to discuss how I went about designing this, how I'm using it in my classes, and the architectural decisions I've made. Most interesting, to me, is how much is running in the browser. Thanks to Svelte, Pyodide, isomorphic-git, LightningFS, and CodeMirror I'm able to provide a full environment for Python, Pandas, and Git. I built much of this with Claude Code, and I'm happy to discuss how that went — what worked well and where I had to step in and make the calls myself. I'm especially excited about the Git simulator: it shows the commit tree change as you run commands, plus an animated view of how files move between the working tree, the staging area, and HEAD. The AI tutor, which uses Claude Haiku, was given my newsletters, classes, and exercises as inputs, along with a description of my pedagogical approach: instructors should give hints and feedback, but not reveal the answer. https://ift.tt/wTVKq8b June 17, 2026 at 11:46AM

Show HN: Agenthatch – Compile any skill into a standalone Python agent https://ift.tt/dUlcZvD

Show HN: Agenthatch – Compile any skill into a standalone Python agent https://ift.tt/TWgxc1L June 17, 2026 at 09:12AM

Show HN: Ctx, save tokens by loading only the relevant tools https://ift.tt/9eFMBJz

Show HN: Ctx, save tokens by loading only the relevant tools Hi HN! Token cost has started to become a high topic of concern to all of us. I tried a few (awesome) tools such as rtk, caveman, and the recent (hillarious but effective) ponytail. What they usually do, is in-line token reduction, e.g. try to compress requests / responses as much as possible. But then it hit me (and I’m sure others had similar ideas) - just like we have routers that pick the right model, why not have something that will also narrow down the amount of available tools, skills and mcps based on repo/context? People usually accumulate skills, agents, MCP servers, harnesses, prompts, repo instructions, and local scripts. I’m not saying we are all hoarders, but we sort of are. When did you remove a skill recently? After a while, the model has way too many options to choose from. ctx tries to fix that by selecting context before the session gets bloated.So no, it doesn’t cleanup your messy garage, but it gives you magic glasses that let you focus only on the tools you need. It does it by watching the repo and task, walks a graph of available tooling, and recommends a small top-scored bundle of skills, agents, MCP servers, and harnesses. How does it know? To make sure results are not hallucinated, and repeatable, I curated a list of 91k+ skills, 467 agents, 10.7k MCP servers, 207 harnesses, and built a graph to help ctx make decisions on what to recommend. While I used AI to generate it of course, I curated it and revised it to make sure the data is up to date. So how this is different from rtk, caveman, ponytail, and similar token-saving tools? As mentioned above those tools mostly reduce tokens after something is already being used. rtk compresses command output. caveman-style tools make the assistant respond with fewer words. ponytail, is, well, awesome, but again it focuses more on reducing code (YAGNI) ctx is upstream. It tries to avoid loading irrelevant skills, agents, MCPs, and harnesses into context at all. So it is not really a replacement. It should work side by side with them! Use ctx to choose the right tools. Use rtk to reduce terminal-output noise. Use terse-output tools if you want shorter responses. The goal is simple: save tokens without forcing the user to manually test and compare thousands of possible skills, agents, MCP servers, and harnesses. Repo: https://ift.tt/IeKESwc https://ift.tt/IeKESwc June 16, 2026 at 02:14PM

Show HN: Pen and paper resource development game https://ift.tt/qAnFlSa

Show HN: Pen and paper resource development game I've been working for a while on trying to curate a game that has the emergence of procedurally generated computer games but that can be played with only pen and paper. Here I present the best version I've been able to come up with that is simple and emergent. I've really enjoyed being able to engage with this sort of game while not feeling like my brain in rotting. I recon my numeracy improves while playing it. https://ift.tt/GlwNBbK June 16, 2026 at 01:49PM

Show HN: Microlearning apps with a TikTok-style feed to beat doomscrolling https://ift.tt/cSgW97D

Show HN: Microlearning apps with a TikTok-style feed to beat doomscrolling I wanted to kick my doomscrolling habit, so I built a microlearning app that uses a TikTok-style algorithm, same addictive feed mechanics, but you actually learn something. I started with a general version, Scroll: Daily Microlearning (microlearning.usescroll.app), but quickly realised it works better when focused on a single topic. So I split it into: Scroll: Personal Finance ( https://ift.tt/HsGam8S ) Scroll: Learn AI ( https://ift.tt/Hu2o1hv ) Scroll: Daily Microlearning ( https://ift.tt/VOtivjK ) https://usescroll.app June 16, 2026 at 01:06PM

Show HN: Claireon – MCP Server for Unreal Editor https://ift.tt/4AVGfJM

Show HN: Claireon – MCP Server for Unreal Editor https://ift.tt/cOMeuL1 June 16, 2026 at 11:56AM

Show HN: The Dictionary Game (Fictionary/Balderdash) as a Daily Puzzle https://ift.tt/rLgecDz

Show HN: The Dictionary Game (Fictionary/Balderdash) as a Daily Puzzle I love the dictionary game: someone takes an unfamiliar word from the dictionary and writes down the definition. Then the other players come up with their own, fake, definition, and guess which one is real. I built a Wordle-style daily game out of this concept. You get shown a word and four definitions and it's up to you to figure out which one is real. There are five new words to try every day. The real definitions are from Wiktionary, the fake ones are made up by Claude (and sometimes me). Let me know what you think, and how this could be improved! https://ift.tt/kWt9Pvb June 16, 2026 at 09:56AM

Show HN: git-lrc – Free, Micro AI Code Reviews That Run on Git Commit https://ift.tt/Np9lkR2

Show HN: git-lrc – Free, Micro AI Code Reviews That Run on Git Commit Hi HN, I'm the author of git-lrc, would appreciate some feedback from the community Last year my team started using AI coding tools more heavily, and we found ourselves generating tons of code, but spending less time looking at the stuff that's been generated. We felt like we were losing a bit of grip/understanding of what we were building. Regressions occasionally slipped through. Sometimes changes made it all the way to production only to be reverted later. We tried several AI code review tools, but most operate at PR time. That felt too late. I wanted review to happen while the implementation was still fresh in the developer's mind at a team level (soft enforcement). I also wanted to emphasize responsibility for keeping prod stable with each individual engineer. So I built git-lrc. When you commit, git-lrc opens a review UI with your diff. It summarizes what changed, points out things that deserve a second look, and lets you quickly jump through the important parts of the change. Over time, git-lrc has grown to check for around 100 common risk patterns across 10 categories, including security, reliability, performance, maintainability, etc. Note that this is far from a formal review. It's a quick 60 seconds spent looking at your own work before it gets recorded in git. It also generates a short "summary deck" that highlights the main changes, with special emphasis on potential risks. With git-lrc you can quickly sanity-check what you're about to ship and obtain greater confidence in what's been generated. In my mind it is less of an AI reviewer and more as a habit for AI-assisted development: a small pause to make sure we understand and stand behind the code we're shipping. Developers can review the change, vouch for it, or consciously skip the review. Those decisions get recorded in git history, creating a trail of how code was reviewed before it shipped. It'd be great if you could take a look, give it a try in your projects or teams and let me know what you think. Happy to take feedback from the HN community and improve it over time! GitHub: https://ift.tt/sia0XNG https://ift.tt/sia0XNG June 16, 2026 at 10:04AM

Show HN: A pure-Ruby X11 terminal https://ift.tt/7CO8aWv

Show HN: A pure-Ruby X11 terminal I use this as my regular xterm replacement... Why? Because I can. It's pure-Ruby down to the font-renderer, and the X11-bindings. (I also run a Ruby WM, a Ruby editor, file manager, and more, so this is just par for the course of my descent into madness) It supports double-width and double-height text, unicode (but double-width characters may currently be rescaled down), layering fonts, special rendering of box-drawing characters (to ensure they seamlessly scale and connect, and has reasonably complete vt-100/vt-102 emulation. The whole thing is available as a Rubygem and comes with an ANSI text backend, so you can run your terminal in your terminal. The bulk was written manually, but the last few days I had Claude write a test harness to shake out a bunch of bugs, and start refactoring and cleaning up the code base (it's still full of warts). https://ift.tt/SLO4c6G June 15, 2026 at 02:15PM

Show HN: Steal-a-GIF – A browser tool to export GIFs from locked down platforms https://ift.tt/owR2TZQ

Show HN: Steal-a-GIF – A browser tool to export GIFs from locked down platforms Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this! https://vorpus.github.io/steal-a-gif/ June 15, 2026 at 10:28AM

Show HN: Track trending GitHub repos on HN https://ift.tt/VarmE3u

Show HN: Track trending GitHub repos on HN I used to go back and forth between HN and Github and look for trending repos. Now i can see them all in one space. And it auto-updates. https://hn-github-reader.vercel.app/ June 15, 2026 at 11:32AM

Show HN: Mood https://ift.tt/SLRoaqf

Show HN: Mood Hey HN, I've had this idea stuck in my head ever since I published Year in Pixels [1]. I've been adding a little thing here and there to this app, and now it feels nice enough to share. It's very interesting what daily tracking does to one's mind. While I already have apps to track everything else like sleep, heart rate, etc., I was still missing something to track my mood. The simple act of thinking about how you feel a couple of times a day already changes things. A moment of reflection. I opted to add Astrology, Checks (habits), and other goodies. Hope you like it as much as I do. Best, @kinduff [1]: https://ift.tt/fg7G5zb https://ift.tt/gIk8yC9 June 15, 2026 at 10:59AM

Show HN: CriteriaBot – A Universal Customizable Classifier https://ift.tt/MRWa2wS

Show HN: CriteriaBot – A Universal Customizable Classifier I needed a classifier for nuanced, subjective buckets that fell outside of typical ML use-cases (e.g., "is this a spoiler?", "is this factually correct?", "is this user being mean?"). I ended up really happy with the architecture I built to solve it, so I rolled it out as a standalone API and service called CriteriaBot. WHAT IT DOES: You give it content and plain-English criteria. It gives you a true/false verdict on whether the content meets those criteria. HOW IT WORKS: In addition to a traditional classifier, the classification request is routed through a pool of small, open-weight LLMs to achieve a consensus verdict. I built a pre-vote factorization machine that selects a sub-pool of LLMs optimized for signal strength based on the embedding of the subject/category. A second factorization machine then reads the votes and the embedding to arrive at a single verdict. That verdict is dynamically modified based on the user's history of agreement/disagreement with the models in semantically similar evaluations. The models are also hooked up to Wikipedia and Wolfram to support edge cases requiring current information or mathematical grounding. FINDINGS: * With the same harness and sample set, Gemma 4 26B's accuracy is only ~1 percentage point below Opus 4.8. * Pure oracle is theoretically very good - currently ~98% accuracy for the datasets. I'm using the second factorization machine as a combiner as it can theoretically push past oracle results, but it's an interesting fallback. * The single most useful LLM surprised me - LFM2 24B contributes the most to the consensus, despite being the worst individually (of the current pool of LLMs). It correlates the least with the other models (perhaps due to its unique architecture?) which makes it a useful signal for some of the problems. * The legal obligations of handling user-submitted images are... involved. I've disabled image support for non-me users while I sort that out (in case you were hoping to try out "Hotdog, Not Hotdog"). * Rails singularizes "criteria" as "criterium" and I didn't realize that was incorrect until it was kind of a lot of work to fix. WHY I'M POSTING: I’d been dealing with burnout for a while, and getting this running has been incredibly rewarding. The majority of people in my personal life are non-technical so it's been hard to get reactions to it beyond "what is it?". Would be thrilled with whatever honest feedback you have. https://criteriabot.io/ June 15, 2026 at 10:48AM

Show HN: PIM – app blocker that inconveniences you instead of locking you out https://ift.tt/PqCosfY

Show HN: PIM – app blocker that inconveniences you instead of locking you out https://ift.tt/T1CVLIA June 15, 2026 at 09:05AM

Show HN: Kage – Shadow any website to a single binary for offline viewing https://ift.tt/zCjvSig

Show HN: Kage – Shadow any website to a single binary for offline viewing https://ift.tt/TjX4Zi8 June 14, 2026 at 01:25PM

Show HN: 3D print Z reinforcement via injected loops https://ift.tt/cwxC56T

Show HN: 3D print Z reinforcement via injected loops Commodity FDM print strength is limited by poor Z-axis layer bonding. Parts crack along Z under stress. MAGMA tries to fix this in software that works on any FDM 3D printer. It's a fork of OrcaSlicer with a new infill type that creates paired U-shaped vertical channels inside the print, plus G-code that injects molten plastic into those channels to bridge Z layer interfaces with continuous plastic. Big caveat: I have a junky Ender 3 and haven't gotten a clean physical print yet. Don't expect this to work out of the box! After months of tinkering, I'm releasing the software so the 3DP community can experiment with nozzles, multi-material, weird hardware, and other print parameters I can't. There's around 40 MAGMA-specific settings to fiddle with, plus some general quality-of-life features (e.g. printing thin infill sections as solid, and a "dual infill shell" feature that applies MAGMA only to the outer shell to save print time). THIS CODE IS ALPHA. Around 50 prints old. The injection G-code is novel. Some printer firmware won't like extruding without movement. In extreme cases it could damage your printer or start a fire. DON'T WALK AWAY WHILE PRINTING. Why MAGMA? "Lava tubes" is a misnomer. Molten rock is magma underground, lava only after it surfaces. The injected tubes are buried inside the print, so "magma tubes" is the correct term. https://mgunlogson.github.io/magma/ June 9, 2026 at 09:17AM

Show HN: Dual YOLOv8n UAV Detection on RK3588S at 42 FPS Using NPU https://ift.tt/RiwZyqu

Show HN: Dual YOLOv8n UAV Detection on RK3588S at 42 FPS Using NPU https://ift.tt/Tth1u7H June 14, 2026 at 10:37AM

Show HN: Öcha – A minimalist, Kindle-style RSS and newsletter reader https://ift.tt/D9kRyaB

Show HN: Öcha – A minimalist, Kindle-style RSS and newsletter reader https://readocha.com/ June 14, 2026 at 10:49AM

Show HN: Afterburner – Capability-Sandboxed JavaScript/TS Runtime in Rust https://ift.tt/eCqDy6r

Show HN: Afterburner – Capability-Sandboxed JavaScript/TS Runtime in Rust Hey everyone! I've been working on something called Afterburner: a fast, embeddable JS/TS runtime written in Rust, with a capability sandbox baked right in. Scripts run locked down by default: no network, no filesystem, no environment variables. You explicitly grant whatever access a script actually needs, and every call gets hard caps on CPU, memory, and time. The goal isn't to replace your existing stack. It's to fit cleanly into it: Embed a JS/TS engine in your Rust app with a single crate. Run user scripts, plugins, business rules, or edge logic, each call fully sandboxed. Wrap the tools you already use. Commands like `burn node app.js`, `burn npm test`, `burn bun`, `burn deno run`, and `burn npx tsx` run your existing toolchain under the sandbox. Take an unmodified Express, Fastify, or Hono app and run it with zero ambient I/O and a memory ceiling. No code changes needed. Use the built-in registry at registry.afterburner.sh. Publish with `burn publish`, install with `burn install` or `burn add` dependencies are pinned by content digest. Every package ships with a capability manifest, so installed code is sandboxed by default. It also interops with npm, so you can still pull in npm libraries as needed. Since nothing gets ambient authority, it's also just a clean, practical way to run untrusted code without having to cross your fingers and hope. Repo: https://ift.tt/rE2MIzY Site: https://afterburner.sh Registry: https://ift.tt/4tWByZ8 The full walkthrough like how it works, what it can do, and benchmarks hitting up to ~16.8M rows/sec is all in one post. It's the best place to start: https://ift.tt/93CYkLd One licensing note: it's source-available under BSL-1.1, which automatically converts to Apache-2.0 four years after each release. Free to use for your own projects so go build something. https://ift.tt/rE2MIzY June 14, 2026 at 09:01AM

Show HN: Verso – A $14.99 Mac word processor with no subscription https://ift.tt/Ebvkzaw

Show HN: Verso – A $14.99 Mac word processor with no subscription https://ift.tt/SwKjPH6 June 13, 2026 at 01:43PM

Show HN: Lightweight C++23 S3 client with no extra deps (just curl and OpenSSL) https://ift.tt/BLkFSOq

Show HN: Lightweight C++23 S3 client with no extra deps (just curl and OpenSSL) Attached is my attempt at making a small toy S3 client without any other dependency besides libcurl and OpenSSL. Was tested mainly on MinIO (RIP) locally, so I would expect some bugs when using it against AWS, although I was able to play with it on some open access buckets Be aware that I am not a C++ programmer and this project was indeed done to learn a bit of C++ myself :') Feedback on any of the code, either on gtest, or the benchmarking section or the core itself is welcome! https://ift.tt/WAMLXx0 June 13, 2026 at 12:40PM

Show HN: Feed-Repeat, a Tool to Repeat Old Posts from Web Feeds https://ift.tt/V34CU0e

Show HN: Feed-Repeat, a Tool to Repeat Old Posts from Web Feeds feed-repeat is a small CLI/service that repeats entries from RSS/Atom feeds into new feeds. It fetches posts from a source feed, selects a random subset preferring older posts, and inserts them in an output feed. I made feed-repeat for myself. I wanted a tool to send me old blogposts written by my favourite authors so that I could enjoy them again, but also not be overwhelmed by a wall of hundreds of unread old posts. feed-repeat does just that. It can be self-hosted easily using the provided NixOS module or systemd service. It can also be made to run entirely serverless on GitHub Actions/Pages using the provided workflow. The website contains detailed docs and guides. https://abhin4v.github.io/feed-repeat/ June 13, 2026 at 11:27AM

Show HN: Portfolio simulator using trend-following indicators and rebalance API https://ift.tt/wr6y7O4

Show HN: Portfolio simulator using trend-following indicators and rebalance API https://ift.tt/meABKho June 13, 2026 at 09:34AM

Show HN: I am building a map of people who lived in the Roman Empire https://ift.tt/RdpNW8U

Show HN: I am building a map of people who lived in the Roman Empire Driving home from work one day, I wanted to know how many people we knew the names of who lived during the Roman era. Searching around, I found lists of Consuls and officials, but nothing that covered ordinary people or even most people like freedmen and slaves. So I ended up building a pipeline to process the more than 500k Latin inscriptions in the Epigraphic Database Clauss-Slaby https://ift.tt/mQJZ1yK and extract the names of people (and attempt to cluster them, but this is a work in progress). There are databases where Classicists have done this manually for specific regions, Trismegistos https://ift.tt/TK2QCLw and Latin Inscriptions of the Roman Empire (LIRE) https://ift.tt/t1Zdfzr... are two major efforts I found. But there doesn't seem to be a project that did what I set out to do, although I have read in some places that it was believed to be possible. I am not a classicist or a web developer, but I have Claude and Gemini and I can sort of read basic Latin - so I set to work. I used LIRE and another database as ground truth and built a pipeline to extract and process the inscriptions to recover the names. The process I developed uses a high end LLM like Sonnet or Gemini Pro to supervise the extraction and tuning process on a regional basis until the obvious error rate is reasonable. For this, so far, reasonable to me means less than 1-2% in the smaller initial samples of 100-500 and no observed systemic issues. The different regions often need different prompts, so this basically became an exercise in letting the higher level AI tune the prompt for the lower level AI. The extraction when measured against LIRE produces an F1 score between 0.64 and 0.87, but take this with a grain of salt. Once I had done a few regions, I wanted to see the work, so I threw together a pretty crude website but as I am not a web developer, it was crude in how it accessed its data. It does look cool and I also added summarization, and machine translation to each entry. I wanted to eventually get feedback from an actual team of classicists and make the website work better, so I am rewriting it as we speak but it is broadly functional now with a few extra bugs but substantially improved performance compared to the old one. All entries link back to the proper sources, and the old web app linked to several additional sources where the data was present, but I haven't gotten that working again just yet on the new one. (The old web interface is still available at https://roman-names.com , but I will warn you it is clunky and not mobile friendly at all) Key findings so far: AI supervised AI extraction saved me time. I was manually tuning things for a while and then the runbook became an idea that I feed my instructions in and let the big AI go with sparse oversight from me. The extraction improved significantly (by about 10 F1 points) when I fed the model the raw text including the markers, vs a cleaned up version of the text. I just thought it was a cool little project and wanted to share. If you happen to work in any adjacent space and there is something I could do better etc let me know. https://ift.tt/re62FlJ June 10, 2026 at 03:28PM

Show HN: Cortex – local-first encrypted memory for AI agents (Rust, MCP) https://ift.tt/yNT8FUZ

Show HN: Cortex – local-first encrypted memory for AI agents (Rust, MCP) https://ift.tt/E5lAG1W June 13, 2026 at 10:00AM

Show HN: SharkClean MCP https://ift.tt/Z4rNLUe

Show HN: SharkClean MCP This is nothing special but it has been very very nice to kick off cleaning jobs remotely via MCP. Working towards a genuinely smart home and this was a useful step in the right direction. https://ift.tt/Ae3ywLi June 12, 2026 at 12:09PM

Show HN: 800x faster Linter and TypeScript-Go toolchain for plugins like typia https://ift.tt/290xmoW

Show HN: 800x faster Linter and TypeScript-Go toolchain for plugins like typia As a developer of typia, have to alive in the new typescript-go era, I made a new toolchain for tsgo. Making the ttsc, I understood that the new plugin toolchain system can dramatically reduce lint rule checking time by integrating into the typescript-go. So made `@ttsc/lint`, and its time is 600x to 1600x faster than eslint. From now on, when you compile TypeScript, lint violations would be caught in the same time. No more need to run both `tsgo` and `eslint` independently. > This repository is not v1 yet because the typescript-go has not been released yet, but if you wanna experience superfast lint, or keep using typia in typia era, you can do it right now. https://ift.tt/U32ukSz June 12, 2026 at 08:47AM

Show HN: StackScope – I crawled over 40k indie launches to see what they ship https://ift.tt/jMeqaoE

Show HN: StackScope – I crawled over 40k indie launches to see what they ship Hey all, I built StackScope, a crawler/catalogue that looks at new product launches and shows what they were built with. It watches launches from Product Hunt, Show HN, and PeerPush, then crawls the public site behind each one. The goal is to show what people actually launched with: hosting, frameworks, analytics, DNS, security headers, legal pages, AI-builder signals, and other public clues. I started building it because most stack-detection sites look at the web as a whole. I was more interested in the current indie launch scene: what people are choosing right now, at the point they first put something in public. A few implementation details: it runs on .NET, uses Playwright for rendered pages, and has a first-party fingerprint catalogue rather than one copied from Wappalyzer/etc. robots.txt is honoured, and the bot identifies itself. Frustratingly, I am still waiting for verified bot status from Cloudflare and currently that knocks out about 10% of all sites. There is also a private readiness check: paste a URL, get the same style of report, fix things, and recrawl. No account or email needed. I'd be interested in feedback on the usefulness of this, the methodology, and any obvious false positives. Jonathan. https://stackscope.dev/ June 12, 2026 at 11:26AM

Show HN: I had Fable clone a game, it turned it into an arena combat AI trainer https://ift.tt/H4pevjB

Show HN: I had Fable clone a game, it turned it into an arena combat AI trainer I started off with a simple goal: port the game Soldat to Typescript. I ended up not only with the game, but with a full system to train AI bots to play my own game, building a neural net to train new bot AIs from tens of thousands of simulated matches with different strategies. It also runs live all the time on my website and has a news dashboard and you can replay any game exactly. It all was a very fun way to dig into Fable's capabilities. The bill if I had done this with API billing? Nearly $2000. https://ift.tt/G3YdanD June 12, 2026 at 10:55AM

Show HN: Script to bulk delete Claude chats from the web UI https://ift.tt/jBQ6ekG

Show HN: Script to bulk delete Claude chats from the web UI I haven't found a way to delete all chats in bulk like you can on Chatgpt. With Claude, you have to scroll to the bottom, select everything, and delete. The problem is, if you have a lot of chats, it becomes impossible. I created this script. It does it alone. I hope it helps someone. (conversations disappear from the UI slowly, over several minutes, and remember to keep the tab open until the console shows "Finished", refreshing away from the page can stop the deletion process.) https://ift.tt/3ouGXNt June 12, 2026 at 11:08AM

Panasonic Arc5 Pro Review: Our Verdict After One Month of Testing

Does the latest version of one of the best electric razors available live up to the hype? 

Show HN: A police department for your Claude Code agents https://ift.tt/IyKqpa6

Show HN: A police department for your Claude Code agents https://ift.tt/e0qchKQ June 11, 2026 at 01:47PM

Show HN: AI Pair Programmer for Emacs https://ift.tt/75TLgUf

Show HN: AI Pair Programmer for Emacs I built a pair programmer, using AI, but now am trying to go slow with new languages and paradigms using this package. I have noticed a decline in my programming skills, and wondered why I couldn't use AI as a pair programmer. Why can it watch what I'm doing over my shoulder and suggest changes? That way I can struggle through problems still and actually learn something. Results have been good so far :) https://ift.tt/hQqfGpH June 8, 2026 at 02:34PM

Show HN: CambiOS – a new Rust-based, sovereign identity, zero-trust OS https://ift.tt/OtplDn6

Show HN: CambiOS – a new Rust-based, sovereign identity, zero-trust OS I've been working on this for a couple of years and coding earnestly for months. Would love to get your human eyes on it. Looking for feedback and would LOVE to find collaborators. I saw a hole in the OS landscape and am working to close it - the closest other alternative I could find is Google's Fuschia (not sovereign by any stretch.) Anyway - I'm Jason, here for questions if they come up.. cheers! More info here: https://ift.tt/xYharTN https://ift.tt/kfa631t June 11, 2026 at 11:17AM

Show HN: RadioPal – a somewhat intelligent layer over Liquidsoap https://ift.tt/GubEIzh

Show HN: RadioPal – a somewhat intelligent layer over Liquidsoap https://ift.tt/d5RsS6H June 11, 2026 at 10:41AM

Show HN: Open-source API Key server written in Go by Ory https://ift.tt/WFC0P2a

Show HN: Open-source API Key server written in Go by Ory https://ift.tt/9oxIYRH June 11, 2026 at 11:09AM

Show HN: Brooks-Lint – AI code reviews grounded in 12 classic engineering books https://ift.tt/nqVAh7C

Show HN: Brooks-Lint – AI code reviews grounded in 12 classic engineering books I once managed a small team and hired an intern to develop the backend services for a software system. He used AI tools to write the entire project; while it ran correctly and produced the right results, the directory structure was atrocious upon review. Typically, a FastAPI service is organized into components like routers and services, but he had created an unnecessarily deep, multi-layered structure within the service layer—logic that should have simply been split across two or three files. The code lacked elegance. Recalling concepts from books on software project management, code structure, and architecture—such as The Mythical Man-Month —I decided to codify these architectural principles into a reusable "skill" to optimize my project's structure. I used Claude Code to create a skill called `brooks-lint` and employed it to refactor the project, resulting in a much clearer and more logical architecture. I encourage everyone to use this skill, identify issues, submit pull requests, and collaborate on improvements, thereby benefiting the projects you are currently developing. https://ift.tt/QfcnRtN June 11, 2026 at 10:08AM

Show HN: Extend UI – open-source UI kit for modern document apps https://ift.tt/agtZCDi

Show HN: Extend UI – open-source UI kit for modern document apps We're open-sourcing 14 components & examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It's MIT licensed and fully customizable. Demo video here: https://ift.tt/QLgVqcT When we started, we tried every file viewer and document component library we could find. Unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for https://extend.ai/ . It was only ever meant to be internal, but enough customers kept asking for it that we decided to open source it. It's useful for building document processing agents, real-time user facing document intake flows, or all kinds of internal tooling. We naively thought this would be a solved problem. Turns out, making PDF/XLSX/DOCX viewers that work at scale is not trivial...we use and maintain it for Extend ourselves, so we've fixed a lot of edge cases that came up while running millions of pages / day through our own system. Our hope is that with our resources + community support, it'll keep getting better over time. https://ift.tt/u3N2Btr June 10, 2026 at 12:09PM

Show HN: Social network where inviting someone makes you accountable for them https://ift.tt/BcJeKCd

Show HN: Social network where inviting someone makes you accountable for them Chirpper is invite-only. When you vouch someone in, they join your TrustChain. Their behavior affects your TrustRank, and that propagates up the lineage. No moderators. The accountability is architectural, not policy-based. You can be pseudonymous, but you can't be unaccountable. Happy to get into the mechanics in comments. https://chirpper.com June 10, 2026 at 11:09AM

Show HN: Camel Mono – a monospace font that makes camelCase easier to read https://ift.tt/YhO6CfT

Show HN: Camel Mono – a monospace font that makes camelCase easier to read https://ift.tt/GrS3aem June 10, 2026 at 10:02AM

The 10 Best Face Washes for Men in 2026, Tested by Grooming Editors

Soaps from Kiehl’s and Tower 28 came out on top in our testing.

Show HN: A curated collection of simple datasets for machine learning https://ift.tt/YETjNwS

Show HN: A curated collection of simple datasets for machine learning https://ift.tt/kNPXUJK June 10, 2026 at 10:10AM

Show HN: Construct SQL from table records by breaking down decision tree https://ift.tt/8JduRtK

Show HN: Construct SQL from table records by breaking down decision tree Create SQL by over fitting decision tree on data Then I simplify the boolean representation. The demo is hosted in streamlit ( https://ift.tt/DPmwWOZ ). Sorry if this is a repost, my previous post had the wrong tag. https://ift.tt/lBc3z5E June 10, 2026 at 10:04AM

Show HN: Built Open-Source Version of Anthropic's Internal Analytics Engine https://ift.tt/elXKPIC

Show HN: Built Open-Source Version of Anthropic's Internal Analytics Engine Hey HN, here's the repo if you'd like to try it out: https://ift.tt/poAxYDc Would love your feedback. https://ift.tt/QJPLAlR June 9, 2026 at 12:17PM

Show HN: A terminal writing environment with Git, E2EE sync and temporal search https://ift.tt/e0wq496

Show HN: A terminal writing environment with Git, E2EE sync and temporal search I am a 40 years old jobless sys-admin with no cs degree and no development experience and 25 yeras of system knowledge. I built a fully encrypted writing environment where I can write with focus forgetting about the application. Here ai was my code translator while I strictly was the architect and instructor. It all started when i asked myself that "why and how i remember any past memory instantly without searching inside my head". This became the design principle of my app. Thus I solved a fundamental git problem of tracking a single note throughout the history by embedding uuid in every commit. Its responsive data-as-UI based interface keeps the app (nearly) learning curve free. Navigating deep hierarchies is easy using numbered fisheye jump system without forward button. Every operation is in one or two keystroke like v(view), c(create), d(delete), r(rename), (j)ump s(sync), (s)earch, b(back) or v1, d1, j1, jb etc. It is built using python standard library (no other dependency), Git, cryptography standard primitive (embedded). I used git-filter-repo programaically for permanent item erasure using uuid from inside the application. It has full timeline for each item (note, file, subnotebook) to see the entire life cycle from create to erase with tombstone. Its subnotebook hierarchy can be upto any depth. It supports 80 file types with syntax highlighted editing with export feature for files. It has activity viewer inside every notebook or subnotebook. It shows your last 50 activities in the notebook. Searching is easy like "s files* file.md date* 02-04-2026 in* notebook/subnotebook_name", "s note_name date* 01-04-2026 05-04-2026", "s edited* any_text thisweek " "s in notebook/subnotebook_name" or just "s anytext". Notebook can be encrypted using 8-24 words BIP-39 phrases and use password for regular lock/unlock. It is encrypted using standard AES-GCM and also portable. It can show password change log in each notebook management screen. Key vaults are hardware bound yet portable and a usb drive can act as TPM like security. It means when the keys are not reachable, notebooks can't be accessed. The application architecture and data structure is decoupled. Where app architecture allows the app, notebook and key vault can be in three different locations or even in different systems and data architecture allows metadata and content remain separated in different files inside each notebook folder linked via UUID. Git is implemented for doing item level (not file level) versioning and temporal search with uuid based commit metadata. Here commit metadata is not encrypted, though doable modifying the existing code if required. Every notebook is self contained in just a movable single folder. The architectur also enables optional e2ee conflict free sync using github and other platforms. It does not need someone to be a git expert to use the application and cloud vendor cannot see the data even with public visibility. I will request respected HN people to go through the documents and the story_n_constraint.md file, that will explain the what, how, why in details. I also put a couple of abstract ideas inside the repo (what_can_be_done files). I want to thank the creators of Python, Git, cryptography, nvim, micro and git-filter-repo. Their tools came together and turned a concept into a working application. The post, the GitHub repository, and all source code and documentation are part of the prior art with appropriete license (Public + timestamped + enabling) repo: * https://ift.tt/xh6tPdZ * requirement: linux/mac/win/docker, python 3.13, git, nvim/micro or any terminal based editor (can be configured from config.json inside root folder),internet for using github sync example - python3 terminal_notes_ui.py (from linux) * tested on debian 13 only git clone https://ift.tt/u1g0qcA && cd terminal-notes && python3 terminal_notes_ui.py sys-ronin June 9, 2026 at 10:59AM