Live VNC for web agents
debugging native captcha on Cloud Run
Details
- External ID
- 46496065
- Source
- HN
- Company
- —
- Product
- Live VNC for web agents
- Website domain
- rtrvr.ai
- Launched
- Jan. 5, 2026
- Cohort
- —
- Upvotes
- 12
- Upvotes percentile
- 0.5586297760210803
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
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 instance2. A separate relay service that pairs viewer↔runner by short-lived tokens makes attach deterministic3. Runner stays clean: concurrency=1, one browser per container, no mixed trafficWould 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?
Enrichment
- Theme
- Claude integrations and coding agents
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- vnc debugging for web agents
- Manually corrected
- False
Could you build this?
No Developing DOM-native agents that bypass cross-origin iframe security boundaries and solve anti-bot systems like Google reCAPTCHA without CDP/Playwright requires deep browser engine and security exploitation knowledge.
What it would actually take: The architecture requires custom-patched browser engines (Chromium forks) capable of violating SOP (Same-Origin Policy) to inspect arbitrary nested shadow DOMs and cross-origin iframes. It also needs low-latency WebRTC/VNC streaming infrastructure hosted on container platforms like Cloud Run, paired with adversarial ML models trained to evade dynamic bot-detection fingerprints.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 24 launches clear the similarity bar, closest 8 shown.
Attention rank: #8 of 25 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 65 days after the earliest competitor.
- FCaptcha · ph · 2026-09-22 · 2 upvotes · similarity 0.36
- AgentKanban for VS Code · hn · 2026-05-13 · 5 upvotes · similarity 0.36
- Rtrvr.ai · hn · 2025-11-12 · 6 upvotes · similarity 0.35
- Chatcode · hn · 2026-06-04 · 9 upvotes · similarity 0.35
- Superserve · hn · 2026-07-21 · 9 upvotes · similarity 0.34
- We built a <60ms, open-source alternative to E2B using RustVMM and KVM · hn · 2026-04-22 · 7 upvotes · similarity 0.32
- ServerKit · hn · 2026-06-30 · 5 upvotes · similarity 0.32
- LightTwist - Record and stream in a realistic virtual studio, even if your guests and co-hosts are remote · yc · 2026-06-30 · 6 upvotes · similarity 0.32
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.