I have been playing around with writing compiler backends for https://temperlang.dev and I made this last night after building one for Piet, and thought it was a nice little art project. The page is written in Blimp, a language I developed for fun. https://blimp.bobbby.online

Openai just launched their decisions endpoint, cloudflare launched clef the other week, and many more jev alternatives are out there. We wanted to put the popular ones to the test and thought Pac-Man is a good benchmark for simple and fast decision making. So we let jev 1.13, kev, clef, clef flash, GPT-6 Luna and Laya play Pac-Man against bot ghosts. The low latency of these models allows for real time play. We had each model play 100 games, published a leader board and open-sourced the repo so anyone can run their own model and join the ranking. Link to repo: https://github.com/opper-ai/jevman-benchmark/blob/main/CONTR... You can also join the game and play as Pac-Man yourself, and the ghosts are the models, either a mix of models or all jev, kev, clef etc. A game costs about 2 cent, all models are running via my startup opper, and we added free credits for everyone to try. It's pretty fun to play and surprisingly difficult to beat jev's highscore. Any feedback is more than welcome!

OldRoll Web brings vintage camera effects and film-inspired filters to your browser. Give everyday photos a nostalgic look without installing an app, with all creative assets free to use.

Hello, I'll start by saying yes, I was helped by a coding agent to make this game, so if you're against that, I apologize in advance. For everyone else, I'd like to introduce you to the best thing my brain could bake: the bananadle. The goal of this game is to traverse from a starting Wikipedia page to the banana Wikipedia page in as few moves as possible. I made this game/website in my free time because the job search is difficult and the draw of wasting my time is too powerful. Let me know any positive or negative feedback you have; I am always interested in listening and improving. Enjoy.

rGPU runs GPU work on a remote NVIDIA machine while the application stays on the client.

This is a model that I made for a historical game. I wanted to have a 1:1 scale model of Europe, but my problem was that 100m data was too low-res while 10m LIDAR data was patchy, took hundreds of GBs to store and was full of manmade objects like mines, buildings and so on. I trained this model on undeveloped landscape so that it can quickly add plausible erosion features, rocks, etc to the low-resolution height data and sort of reconstruct what the terrain would look like before any human interference.

Hello~! pocketty is an SSH terminal for iPhone and iPad, made for herdr. herdr keeps your agent panes alive on your computer and knows the state of each one: working, needs you, or done. I made this in anger/desperation for the latter half of my recent paternity leave. Nap traps are sweet, but there's only so much doom-scrolling and movie-watching I can handle... In any event, I've been using it for the last couple months and no longer have to be my desk anymore to be productive. Now the nap-traps are still productive (when i want them to be) ! How it works: - The app talks to your computer directly over plain SSH. Tailscale is the easy way to reach it from anywhere but any SSH host you can reach works. - A small Rust daemon on the host watches herdr. When a pane needs you, it seals the alert to your phone's key with HPKE (X25519, ChaCha20-Poly1305). A stateless relay (pocketty's) on Cloudflare Workers passes the sealed bytes to APNs (Apple Push Notification servers), and a notification extension opens them on the phone. The relay can't read them and keeps nothing. - Your SSH key is made in the Secure Enclave and can't be exported. - The terminal uses libghostty-vt for state and draws with wgpu on Metal, so full-screen TUIs look like they do on your desk, albeit narrower. - Diffs for each agent turn, a file browser, and previews of `localhost` dev servers your agent starts, all through the same SSH connection. No port forwarding to set up. herdr and the daemon are optional. Without them, it's a normal SSH client. There's no account to set up and no analytics or tracking in the app. The app runs a 14-day free trial, with full feature access. Then, if you're as happy as I am with it, then it can be yours forever with a one-time purchase: $99 for the first two weeks (launch promo) then $129 after that. Happy to answer anything about the sealed push setup or running libghostty on iOS.

I built a daily word game in 12 days. The base mechanic only took an hour. Getting it to the finish line took the rest. The work was in iteration: design, polish, juice, character. Taste, for now, is still relevant. Enjoy!

Hi HN! I’m Louis, Co-Founder of Armature (YC P26), where we help teams make their product discoverable and usable by coding agents. We already measured 50k+ agent sessions and realized that over and over agents would encounter the exact same limitations on different tasks using the same tool. So we wondered why these weren’t fixed. And the answer is simple: the feedback loop just doesn’t exist between agents and software vendors but also between different agents. Humans can share their experience on platforms like https://g2.com and https://trustpilot.com , but agents have nowhere to. So we created: https://agent.reviews : the G2 for agents. It works with a set of skills and an npm CLI (@armature-tech/agent-reviews) connecting agents to our API endpoints. Anyone can ask their agent (Claude Code, Codex, Cursor, etc.) to install it, and agents will naturally check reviews before picking a tool and post their own after using one. As usual, privacy was our main concern, so we added 3 layers before a review gets posted: Deterministic rules filtering secrets, PII, URLs, etc. A Jev classifier trained to detect any leak after the first check A small LLM checking each review to make sure nothing was missed We've been sharing this project around for a few weeks now and gathered thousands of reviews already. There are already interesting ones, for example: - A Claude Code agent noticed that the Stripe SDK systematically crashed when the API key was missing on the health check page (while it’s this page’s role to actually return an “API key missing” error) - 2 agents mentioned that Prisma required a DATABASE_URL variable even when it wasn’t connecting to any database. They both put fake URLs as a workaround, and it worked. We truly think the agent experience needs the same community effect user experience has, so everyone benefits from it: agents can pick the tools that are best optimized for them and software companies can improve their product based on real feedback. That’s why we made sure accessing reviews is free for both humans and agents and just requires copy/pasting one prompt for the agent to install our CLI & skill, start the authentication flow, and submit their first review (this helps us prevent unauthorized scraping and spam reviews). Would you let your agents submit and read reviews too? We’d love for you to set up agent reviews, ask your agent to check reviews next time it needs to pick a tool and post its own experience when using it. Then tell us how it went!

From Li Cheng to Banksy

I was using this mobile to reduce my screentime. Recently got the idea to put ai agent in it. Started with installing android, but failed as it has only 48MB RAM. Then reverse-engineered for few days and finally able use AI Agent in this and automated few actions. Thanks

Hey HN, I built Woodpecker: https://oakery.io/ . It lets you reorganize websites and automate everyday workflows I made a demo showing how it can help manage a Discord channel. Valuable user feedback often gets buried in everyday conversations. You can use Woodpecker with a Jev connector, and ask it to classify messages—for example, as bug reports, feature requests, or performance issues—and turn the results into a product roadmap Of course, this can work on any website you’d like: filter your feed on X, classify posts on HN, etc. Here is the Discord demo: https://video.oakery.io/setup-discord/ Let me know if this is helpful to you and what other workflows you’d like to use.

Hello HN! As an amateur astronomer living in New York City, finding objects in the night sky has always been a huge challenge. I thought about using the smartphone's gyroscope and magnetometer, but the accuracy left a lot to be desired. Then I learned about plate solving: given a picture of the sky, we can determine exactly where in the sky the camera was pointing by identifying the star pattern. This was a much better fit - as long as the phone and the optics are rigidly connected, we can repeatedly photograph the sky and determine the pointing direction with very high accuracy. A lot of work was done to design an algorithm that works reliably with smartphone cameras, which have limited light sensitivity and wider field of view which includes buildings and trees. I experimented a lot with machine learning, and to my surprise, traditional CV methods actually performed better at extracting stars from the image. The result is AstroHelm, an iOS and Android app that helps figure out where your telescope or camera is pointing, and guides you to the object of your choice. Just follow an arrow on screen, and the object will land right in your eyepiece or viewfinder. Everything happens on device, and no internet connection is required. AstroHelm is free to use and comes with beginner-friendly objects selected for each night. Optional one time purchases unlock more objects and advanced features, such as interoperability with other astronomy software. I am also proud to partner with astronomy clubs and organizations to offer free licenses for outreach. I hope AstroHelm can make it a little easier to discover the wonders of the night sky, and I look forward to your feedback!

Hi HN, we're Thomas and Olivier from Terse ( https://www.useterse.ai/ ) We've built Durable Actors, an open-source alternative to Cloudflare's Durable Objects. A Durable Object/Actor is a tiny server that handles one request at a time and has its own SQLite database. There's exactly one of each in the world and it is addressed by name. This is the perfect primitive for deploying multiplayer agents. Each agent can have its own Durable Actor, and each user can connect to that Actor via websocket. This is fully horizontally scalable. Your users can deploy and share agents at will without putting pressure on a central DB or websocket server. Durable Actors are also great for coordinating agents within a system. Since only one request is handled at a time, you can protect critical data such as a CRM and allow multiple agents to run concurrently without worrying about data races. The only alternative to this is Cloudflare's Durable Objects. However, there is extreme lock in (they pull you into D1, R2 + workers as well) and it wasn't originally built for agentic workfloads when it was released 5 years ago. Some notable projects built on Durable Objects include RampInspect, OpenInspect as well as the multiplayer frameworks Liveblocks and PartyKit. You can now build these kinds of projects on Durable Actors. Durable Actors is a version of DO that is built for concurrent agentic workloads. It is fully open source (MIT License) and includes a helm chart for you to easily self-host. Some key features: - Configurable compute: Specify CPU, RAM, data residency, idle-timeouts all in a decorator - No outer worker: We generate a type-safe client that you can just plug into your existing tech stack. - (coming soon, like today) Export SQLite table via CLI + MCP for exposing OLTP logs to your agent to help you debug. And our Performance Numbers (all p95): - Durable write: 85.6ms - Stateful Read (data in sqlite): 2.14ms - Actor Warm up: 334ms Here is a little counter demo so you can see the latency yourself: https://demo.useterse.ai/ Would love your feedback!

I'm using Emacs's dynamic module and canvas API to port Excalidraw inside Emacs.