Aura – Like robots.txt, but for AI actions
Hi, I've been watching the rise of AI agents with a mix of excitement and dread. We're building incredible tools that can browse the web, but we're forcing them to navigate a world built for human eyes. They scrape screens and parse fragile DOMs. We're trying to tame them to act like humans. I believe this is fundamentally wrong. The goal isn't to make AI operate at a human level, but to unlock its super-human potential. The current path is dangerous. When agents from OpenAI, Google, and others start browsing at scale and speed, concepts like UI/UX will lose meaning for them. The entire…
In plain words
Aura is an open protocol that allows website owners to define how AI agents can interact with their sites, similar to how robots.txt controls search engine crawling. It addresses the challenge of AI agents navigating web interfaces designed for humans by providing a standardized way to communicate agent-compatible instructions directly to AI systems. The tool is intended for website owners who want to maintain control over their site usage as AI agents become increasingly capable of autonomous web browsing at scale.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi, I've been watching the rise of AI agents with a mix of excitement and dread. We're building incredible tools that can browse the web, but we're forcing them to navigate a world built for human eyes. They scrape screens and parse fragile DOMs. We're trying to tame them to act like humans. I believe this is fundamentally wrong. The goal isn't to make AI operate at a human level, but to unlock its super-human potential. The current path is dangerous. When agents from OpenAI, Google, and others start browsing at scale and speed, concepts like UI/UX will lose meaning for them. The entire model of the web is threatened. Website owners are losing control over how their sites are used, and no one is offering a real solution. The W3C is thinking about it. I decided to build it. That's why I created AURA (Agent-Usable Resource Assertion). It's an open protocol with a simple, powerful idea: let website owners declare what an AI can and cannot do. Instead of letting an agent guess, the site provides a simple aura.json manifest. This gives control back to the site owner. It's a shift from letting AIs scrape data to being granted capabilities. We get to define the rules of engagement. This allows us to increase what AIs can do, not by letting them run wild, but by giving them clear, structured paths to follow. A confession: I'm not a hardcore programmer; I consider myself more of a systems thinker. I actually used AI extensively to help me write the reference implementation for AURA. It felt fitting to use the tool to build its own guardrails. The core of the protocol, a reference server, and a client are all open source on GitHub. You can see it work in 5 minutes: Clone & Install: git clone https://github.com/osmandkitay/aura.git && cd aura && pnpm install Run the Server: pnpm --filter aura-reference-server dev Run the Agent: (in a new terminal) pnpm --filter aura-reference-client agent -- http://localhost:3000 "list all the blog posts" You'll see the agent execute the task directly, no scraping or DOM parsing involved. The GitHub repo is here: https://github.com/osmandkitay/aura I don't know if AURA will become the standard, but I believe it's my duty to raise this issue and start the conversation. This is a foundational problem for the future of the web. It needs to be a community effort. The project is MIT licensed. I'm here all day to answer questions and listen to your feedback—especially the critical kind. Let's discuss it.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca