Hacker News: quarkcarbon279

New comment by quarkcarbon279 in "Tailscale Traces Database Corruption to 16y/o SQLite WAL-Reset Bug"

quarkcarbon279 — Thu, 13 Aug 2026 02:36:45 +0000

love the simplicity of this article. Reminds me so much of foundational software engineering. i love databases def not cosmosdb

New comment by quarkcarbon279 in "The hive mind for your product"

quarkcarbon279 — Sun, 02 Aug 2026 10:11:13 +0000

"These weirdos have eyes up above. They can read lips from space." from Pluribus. Watched Pluribus and couldn't shake one idea: Everyone knows Carol. Whoever she calls has the full context and just does the thing.

Isn't that the best customer experience every product should provide?

The hive mind for your product

quarkcarbon279 — Sun, 02 Aug 2026 10:11:13 +0000

Article URL: https://www.rtrvr.ai/rover/blog/hive-mind-for-your-product

Comments URL: https://news.ycombinator.com/item?id=49142951

Points: 2

# Comments: 1

New comment by quarkcarbon279 in "Show HN: Reverse-engineering web apps into agent tools"

quarkcarbon279 — Sat, 11 Jul 2026 01:39:13 +0000

I'm so surprised you didn't add your agent on your own website? And the same fundamentals of a browser agent why you can't achieve everything with APIs alone apply here too inside a website. What's your take?

We have been building in the space balancing both with priority to GUI tools currently building on top of the great GUI experiences of a product, rtrvr.ai/rover

New comment by quarkcarbon279 in "I used Claude Code to get a second opinion on my MRI"

quarkcarbon279 — Sun, 28 Jun 2026 20:12:12 +0000

As a developer I have many times seen Claude's models confidently hallucinate, jump into conclusion. Fable though I used just for 2 days, didn't experience it much in the short-term.

New comment by quarkcarbon279 in "Show HN: AI Subroutines – Run automation scripts inside your browser tab"

quarkcarbon279 — Sun, 19 Apr 2026 03:42:46 +0000

The reason we open our client side code is to bring in the trust in putting rtrvr's DOM intelligence in your web apps - https://github.com/rtrvr-ai/rover/tree/main . Our monetization is super straight forward with subscription - https://www.rtrvr.ai/pricing . The experiences of some extensions shipping anything or selling user data comes in when people build them as side-gigs not when we pour more than year in building the highly accurate automation engine. We have cloud sandboxes too if you prefer executing with the same intelligence on cloud and not on your own device.

PS: Also, our data policy if you are interested: https://www.rtrvr.ai/blog/rtrvr-ai-privacy-security-how-we-h...

Show HN: AI agents should browse your site, not call your API

quarkcarbon279 — Fri, 17 Apr 2026 23:14:00 +0000

We compared four architectures for putting AI agents on websites — RAG bots, API-tool agents(WebMCP), code-writing sandboxes (Cloudflare Agent Lee), and DOM-native execution. Three of them force you to maintain a parallel engineering surface. The DOM already has live state, user auth, and permissions baked in. A structural breakdown of why.

Comments URL: https://news.ycombinator.com/item?id=47811609

Points: 2

# Comments: 0

Show HN: MCP is for tools. A2A is for agents. What's for websites?

quarkcarbon279 — Sun, 12 Apr 2026 05:30:17 +0000

HTTP lets agents fetch pages. Cloudflare's Markdown for Agents lets them fetch more efficiently. MCP (Anthropic) connects agents to developer-defined tools. A2A (Google) lets agents delegate to other agents. But there's a missing layer: how does an agent execute a multi-step task on a website -- add to cart, fill a form, complete a checkout - with the site owner's consent and visibility?

Today's agents either scrape (no consent, no structure) or the site builds a separate API (expensive, doesn't cover the long tail). The web's original protocols assumed someone is looking at a screen. That assumption is breaking.

We wrote a whitepaper mapping the full protocol landscape - Cloudflare's Pay Per Crawl and Web Bot Auth (RFC 9421), MCP, A2A, x402, llms.txt - and categorizing 5 distinct agent architectures (text-based, CUA/screenshot, DOM-based, API-calling, hybrid). Each needs different discovery, execution, and identity mechanisms. We think MCP, A2A, and execution protocols are complementary layers, not competitors. The paper draws parallels to TCP/HTTP design decisions.

Rover is our attempt at the execution layer. It's a DOM-native SDK the site owner installs. The Agent Task Protocol is one HTTP endpoint: POST /v1/tasks with { url, prompt }. Agents get back a task URL supporting JSON polling, SSE, or NDJSON. The site controls what agents can do and gets analytics on what they actually did. We're probably wrong about some of this -- would appreciate the feedback.

Paper: https://www.rtrvr.ai/blog/agent-web-protocol-stack Code: https://github.com/rtrvr-ai/rover (FSL-1.1-Apache-2.0)

Comments URL: https://news.ycombinator.com/item?id=47736402

Points: 5

# Comments: 0

Show HN: RoverBook – PostHog for AI Agents

quarkcarbon279 — Tue, 24 Mar 2026 03:53:29 +0000

Article URL: https://github.com/rtrvr-ai/rover/tree/main/packages/roverbook

Comments URL: https://news.ycombinator.com/item?id=47498429

Points: 4

# Comments: 0

New comment by quarkcarbon279 in "Show HN: Rover – turn any web interface into an AI agent with one script tag"

quarkcarbon279 — Sat, 21 Mar 2026 01:22:17 +0000

PageAgent doesn't have the strong page understanding - semantic tree representation of the pages - it's just a flat DOM basic stripping of HTML - which makes it hard to navigate shadow DOMs, even same origin iframes for that matter or diff frameworks. And also they do element marking - CUA style not sure if they use it in the actual calls to Qwen. And yeah, as arjun takes 30 steps to even do a basic task of find some info.

What we strengthened building agents working on 2M+ web workflows in the past 4 months - is our representation of pages that seamlessly helps agents go through any page old to new iframes, shadow-DOMs and more. Best part of Rover if you as website owner enable cross-origin reqs, say Doordash has Rover and a merchant be like get my restaurant menu from my website and update in Doordash. Rover agent determines the 3P website need, launches our cloud browser to securely execute 3P site actions gets the menu and updates the merchant menu on Doordash so your users never have to leave your site to do a task - one of a kind enabling cross-site interactions

Show HN: Rover – turn any web interface into an AI agent with one script tag

quarkcarbon279 — Sat, 21 Mar 2026 00:58:30 +0000

Article URL: https://github.com/rtrvr-ai/rover

Comments URL: https://news.ycombinator.com/item?id=47462936

Points: 8

# Comments: 5

New comment by quarkcarbon279 in "Show HN: Rover – Embeddable web agent"

quarkcarbon279 — Sun, 15 Feb 2026 06:55:42 +0000

Hey, we have various configurations available even in this very early preview: https://rover.rtrvr.ai/docs/configuration and you can turn off telemetry so we don't collect the data . As a website you can also configure to host the script on your preferred endpoint and our 'apiBase' helps with that pointing to custom domains. And based on project data needs we are also open to tighter data policy rules.

New comment by quarkcarbon279 in "Show HN: Rover – Embeddable web agent"

quarkcarbon279 — Fri, 13 Feb 2026 22:49:40 +0000

We have seen people hire consultants to build RAG pipelines, maintain them only to be QA Agent when the world is shifting losing traffic to the likes of ChatGPT and Google comes up with a protocol that makes you do more work with WebMCP essentially maintain a lot of APIs for your UI and DBs. Rover is the answer to these painpoints. No RAG pipelines, just one script tag your users engage, retain, get work done on your website without ever leaving it and fully conversational.

New comment by quarkcarbon279 in "Show HN: BrowserOS – "Claude Cowork" in the browser"

quarkcarbon279 — Fri, 23 Jan 2026 00:23:04 +0000

what permissions are you talking about? No user permissions/any insecure permissions are needed to navigate cross origin iframes, shadow DOMs and likewise. It comes down to your architecture choices and capabilities - rtrvr can navigate these diff realms without ever taking debugger or such insecure permissions

New comment by quarkcarbon279 in "Show HN: Vibe scrape with AI Web Agents, prompt => get data [video]"

quarkcarbon279 — Wed, 14 Jan 2026 00:41:38 +0000

Let's start the year of vibe scraping! Curating websets and powering apps and sales pipelines from data curation to data entry all in one prompt. Also, if you got hot takes/ideas on accessing the web: Security, Public info Vs Bot Blocking, and more chime in!

Show HN: Live VNC for web agents – debugging native captcha on Cloud Run

quarkcarbon279 — Mon, 05 Jan 2026 07:08:56 +0000

Hi HN, Bhavani here (rtrvr.ai).

We build DOM-native web agents (no screenshot-based vision, no CDP/Playwright debugger-port control). We handle captchas natively including Google reCAPTCHA image challenges by traversing cross-origin iframes and shadow DOM. The latency is high on this one currently.

The problem: when debugging image selection captchas ("select all images with traffic lights"), logs don't tell you why the agent clicked the wrong tiles. I found myself staring at execution logs thinking "did it even see the grid correctly?" and realized I just wanted to watch it work.

So we built live VNC view + takeover for serverless Chrome workers on Cloud Run.

Key learnings:

1. Session affinity is best-effort; "attach later" can hit a different instance

2. A separate relay service that pairs viewer↔runner by short-lived tokens makes attach deterministic

3. Runner stays clean: concurrency=1, one browser per container, no mixed traffic

Would love feedback from folks who've shipped similar:

1. What replaced VNC for you (WebRTC etc) and why?

2. Best approach for recording/replay without huge storage?

3. How do you handle "attach later" safely in serverless?

Comments URL: https://news.ycombinator.com/item?id=46496065

Points: 12

# Comments: 0

New comment by quarkcarbon279 in "Show HN: Rtrvr.ai – Remote Control Your Browser with an AI Web Agent and MCP"

quarkcarbon279 — Wed, 12 Nov 2025 09:28:03 +0000

let's go!! after a long time

New comment by quarkcarbon279 in "Trying Out Claude for Chrome Research Preview"

quarkcarbon279 — Wed, 27 Aug 2025 22:47:19 +0000

Yeah when building for consumers on their devices, security is of outmost importance. I tried on couple use cases too. They currently use Sonnet and this is very initial version so it sometimes fails on picking the right tools. Some actions fail, for example I used their calendar template it failed to Save in the end.

Would love to see if they have cost breakdown for the task haha. It took so many actions, can be optimized + screenshots for one task.

New comment by quarkcarbon279 in "Fast"

quarkcarbon279 — Thu, 31 Jul 2025 03:33:24 +0000

World of LLMs or not, development should always strive for being fast. In the LLM World, users should always have the controls on accuracy Vs speed. (Though we can try for improving both and not one way or other). For eg at rtrvr.ai we use Gemini Flash as our default and did benchmarking on flash too with 0.9 min per task in the benchmark still yielding top results. That said, I have to accept there are certain web tasks on tail end sites that needs pro to accurately navigate at this point. This is the limitation given our reliance on Gemini models straight up, once we move to our models trained on web trajectories this hopefully will not be a problem.

If using off the shelf LLMs always have a bottleneck of their speed.

New comment by quarkcarbon279 in "Show HN: rtrvr.ai – New Free SOTA AI Web Agent Beats Even Operator"

quarkcarbon279 — Sun, 22 Jun 2025 20:26:20 +0000

How did you keep your costs so low? Eval costs especially with Agents can go up a lot and what did it cost for other agents?