jameswebb68

jameswebb68 / vscreen

Public

Give AI agents a real browser — streamed live over WebRTC. Captures headless Chromium, encodes H.264/VP9 + Opus audio, 47 MCP automation tools with live advisor, AI-driven page synthesis, multi-instance, bidirectional input. Watch your agents browse the real internet in real-time.

12
0
100% credibility
Found Mar 06, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

VScreen runs virtual web browsers on a server, capturing and streaming their screen and audio via WebRTC or RTSP for remote viewing and control.

How It Works

1
🔍 Discover VScreen

You hear about VScreen, a tool that lets you run a web browser on a remote computer and watch it live from anywhere.

2
📥 Get it running

Download and start VScreen with a simple click or command, and it sets up a virtual screen ready for browsing.

3
🌐 Open your website

Tell VScreen which webpage to load, and it opens it in the virtual browser just like on your own computer.

4
📱 Connect and watch live

Link your phone, tablet, or another computer to see the browser screen streaming smoothly with sound in real-time.

5
🖱️ Control it remotely

Click, type, or scroll from your device to interact with the webpage as if you were sitting right in front of it.

6
Capture or record
📸
Take a photo

Grab a clear screenshot to review later.

🎥
Stream to others

Share the live view with friends or tools over the network.

Perfect remote browsing

You now have a fully controllable web browser running anywhere, streaming beautifully to your devices.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is vscreen?

vscreen streams a real headless Chromium browser to AI agents over WebRTC, capturing screen as H.264 or VP9 video with Opus audio for live viewing. Agents get bidirectional control—sending mouse/keyboard input back while watching real-time browsing on the actual internet. Built in Rust, it supports multi-instance sessions, 47 automation tools via MCP, and AI-driven page synthesis for dynamic content building.

Why is it gaining traction?

Unlike pure headless APIs that fake interactions, vscreen delivers a genuine browser feed with low-latency streaming, letting agents handle CAPTCHAs, dynamic JS, and real-world quirks. Devs dig the CLI for quick dev setups (like spawning Xvfb/Chromium) and SSE/STDIO proxies to give agents access to classification apps or wrap-up time after conversations. REST APIs lock instances per agent, preventing conflicts in multi-agent setups.

Who should use this?

AI builders crafting autonomous agents for web tasks—scraping e-commerce, form-filling workflows, or testing UIs where Puppeteer falls short on visuals. Teams giving GitHub Copilot context via browser streams or sharing repo access with agents for code review. Perfect for Rust fans wanting to give agents of soil erosion or pollination real browser eyes without cloud dependencies.

Verdict

Promising for agent devs needing live browser control, but at 12 stars and 1.0% credibility, it's early—expect rough edges in docs and stability. Try the Docker setup for proofs-of-concept; contribute to mature it before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.