Usetokenless
Hi HN, Rohit here from Tokenless (https://usetokenless.com/), which I’m building alongside co-founders Andrew and Kev. We’re building an API gateway which routes agent traffic dynamically turn-by-turn between different models to save on AI spend. The cost of AI tokens is top-of-mind for many. Companies like Uber and Salesforce have been complaining about blowing their yearly AI spend faster than expected. Frontier models are amazing for dev work, but are so expensive. Open-source models are cheap and rapidly improving, closing the gap with frontier models, but aren’t quite there yet. Tokenless gets you the best of both worlds–routing harder turns to smarter models only when needed, which keeps costs low. Before Tokenless, I was doing a PhD at Princeton. While using coding/other agents, I constantly agonized over model choice, to make sure my AI spend was going as far as possible on my academic Cursor account. At the same time, I was doing LLM research, and a small technique I developed while in recovery from NeurIPS submission season seemed to hit SOTA pretty fast. I was surprised that such simple ideas could do routing well. We’ve been able to develop a version of the router that matches the performance of Claude Fable 5 at half the cost. The blog post on our website explores the technical details on how we did this (https://usetokenless.com/blog/building-tokenless/). Highlights: - Our approach queries multiple models at once and uses their progress to make decisions (this technique is novel AFAIK, let us know if you know anyone else doing this). - Switching models doesn’t destroy the cache if the routing algorithm is aware of when the cache is hot/cold. To come: - Adding Kimi K3, all other GPT efforts and more to the router Go ahead and sign up on usetokenless.com and try using Tokenless with your agent, you’ll get $20 of free credit. Here’s a demo on how to use it: https://youtu.be/sjZWriclcls Tokenless provides frontier-level intelligence for cheaper, so we’d love some feedback on how it feels to use, any corner cases that the router routes incorrectly, and whether you find the routing problem interesting!
A free curl API for IP data (we scan the IPv4 space in <24h)
The curl API for WorldIP is now live and completely free to use. You can hit it right from your terminal: curl worldip.io — returns information about your requesting IP. curl worldip.io/8.8.8.8 — returns details on any specific IP. The main differentiator here is that we aren't just wrapping another provider's API and reselling their data. We built and run our own global infrastructure capable of scanning the entire IPv4 space in about a day. Happy to answer any questions about the scanning infrastructure or the stack!
CheapFoodMap
I was recently laid off after 18 years, and gave myself 100 days to build soething useful in public. CheapFoodMap is a crowdsourced map of meal under $10, excluding franchises, local good eats only. It's inspried by 거지맵 (Begger's Map) a Korean crowdsourced map students use to find cheap eats. Ocverage is heaviest in Texas, since I live in Dallas, but have 1200 meals across 15 US cities. Seed data came from Google Review, 4.2 star or higher with at least 500 reviews, and verified price under $10 per menu item. Things I would love feedback on : whether the price-freshness model makes sense, and what would make you trust the price on a site like this. How to encourage people to update prices, since inflation is making food price very frequent. https://cheapfoodmap.com Any and all suggestion will be super helpful. Thank you!
Free weather map with 25 model layers, live lightning and storm cells
Show HN: Free weather map with 25 model layers, live lightning and storm cells
The Federalist Papers, typeset as the 1787 newspapers they ran in
Show HN: The Federalist Papers, typeset as the 1787 newspapers they ran in
Echologue
I have tried journaling many times but nothing stuck. So I decided to make my own app for myself with these features: * Voice first * Private first * AI chat * Automatic tagging, meaning extraction, and semantic retrieval using embeddings stored locally * Export to LLM the AI angle is especially interesting for me. It allows me to ask questions like: * "remind me highlights and crazy nights in the last 3 months" * "How was I feeling during my trip in Spain and how big of a problem was my breakup" * "How would you judge my overall interactions with Marc after I told him about my problems" the overall process is fire and forget. I just talk for let's say a minute every day or when there was something of interest. Everything is stored on device. The AI inference is done with Zero Data Retention Endpoints. No email or anything else is kept, you are completely anonymous, I have no idea what or how people use this. Otherwise journaling doesn't work. I can't say my secret thoughts when I know someone has a master key or can suffer a security breach. I hope you enjoy the product as much as I do.
Vimgolf.ai
Just launched my app, VimGolf.ai! As users complete the levels on the map, I introduce progressively more complicated concepts — it’s aimed at people who have never used Vim. Any feedback would be much appreciated!
Learning Rust by writing a Markdown to HTML compiler
Hi HN, I'm new to Rust and, after half of `The Rust Programming Language` I decided to delve into a project I would actually use: a markdown to html compiler that actually serves my micro-blog (I started just right after publishing the project hehe). The project is intentionally small and one-file contained: I wanted to have the full picture in mind. I'm open to comments, suggestions and PRs. If you asked me more convincing arguments to "why did you do it?" rather than "to learn Rust" I would respond with: LLMs are effectively a new type of web users today and will be more and more present in the future. Having a full, well formatted, .md interface of a website can make it easier for them to access the content.
Manim (3Blue1Brown's animation engine) in the browser via WebGPU
Grant Sanderson (3Blue1Brown) created Manim, the Python library he uses to make the math animations in his videos. We reimplemented Manim with the same Python API, but the implementation underneath is Rust, connected to Python through PyO3. The Rust code uses wgpu, so rendering happens on the GPU. To run it in the browser, we compiled the Rust parts to WebAssembly so the PyO3 extension loads in Pyodide. In the browser, wgpu targets the WebGPU API, so animations render in real time on your GPU through the browser. The editor is Monaco (the editor that powers VS Code) with a live preview: write your Manim code on one side, watch the animation update on the other. There's also a built-in AI agent if you'd rather vibe-code your animations.
Beakdown
I used to play Joust with my little brother on the BBC Micro many moons ago and have fond memories of it. So when I was experimenting with Claude Opus 5 it was a nice inspiration for this game. Did a little research and found there aren't many games out there that just work in a browser without ads, loading screens or account sign-ups. So I've put this directly on the landing page with no noise in the way - it works on any browser on any device and loads instantly. If it doesn't work at all, please tell me. And also let me know if you think it needs music - I went without it to begin with but don't know if that's what people would prefer or not. Would also love to know how far you get, my personal best is 199,000. Thanks for your interest!
Daily competitor-change briefs for local businesses
Show HN: Daily competitor-change briefs for local businesses
Loop
Loop helps you close the loop on email introductions. It is added to the CC line (loop@getlooped.cc) on any intro email and after 2-3 weeks it will follow up with each side privately to determine the status or outcome of the connection, including any follow-on intros that were made from one side to the other. Other than actively adding Loop to CC, it is permissionless. It requires no account or external app - running entirely through regular email workflow. Over 90% of the time the same etiquette that sends the connector to BCC after the intro, will do so for Loop as well - so it only has visibility on the first two emails to determine who is the connector, who the sides are, what are their roles and when to emerge with the ask. Aside from the challenge of maximum datapoint extraction with minimal data at hand, it also had to be built with more than a dozen timing, attribution and meaning guardrails so it wont act irreversibly on inferred state. Some examples include out of office messages, personal assistants, weekends/holidays, intros of 3 or more people, replies from the same person with a different email address or emails that are actually not intros at all where it was CC'd by accident. I built loop because I do about ~20 intros per month and realized that I rarely hear back on how they are going (e.g. - if a deal is on the table) or what the outcome eventually was. This visibility makes me a better connector and dealmaker, and it puts me top of mind for attribution without me needing to do awkward reach outs. Loop can also be used for intros you receive, so I use it to see who keeps opening doors for me + gather statistics. Stack: Next.js 16 (App Router) + React 19 + TypeScript on Vercel, Postgres (Supabase) via Prisma, Auth.js for login, Resend for inbound + outbound email, and Claude Haiku classifying the incoming mail. Sentry + Vercel Cron as well.