AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs

Alibaba Qwen@Alibaba_Qwen·Collected 16d ago

👀108

🔥96

Alibaba Tongyi Labs Open-Sources OpenGCUA: Full-Stack Generalist Computer-Use Agent Cutting OSWorld Steps by 53%

Alibaba Tongyi Labs (Tongyi-MAI) has published and open-sourced OpenGCUA (arXiv:2610.22200), establishing a fully open software stack for Generalist Computer Use Agents. Moving beyond brittle single-click GUI paradigms, OpenGCUA introduces a 'Code-Execution-as-Action' framework combining visual screen perception, accessibility trees, bash scripts, and Playwright APIs into unified programmatic execution blocks. Evaluated across eight frontier models on OSWorld-v2, OpenGCUA boosted mean scores by +19.6 points while cutting task steps by 53.0%, releasing an Apache-2.0 macOS menu-bar harness and Cross-Device SDK.

Key Takeaways

OpenGCUA published in arXiv:2610.22200 and released under Apache 2.0 as an open generalist computer-use agent stack
Pioneers 'Code-Execution-as-Action', synthesizing loops, conditionals, and programmatic APIs into unified Python/Bash blocks
On OSWorld-v2, boosts mean score by +19.6 points across eight frontier models while reducing steps per task by 53.0%
Releases a native macOS menu-bar harness for physical execution alongside a Cross-Device SDK spanning PC, web, and mobile

Read full story

Linked Models & Agents:

⚡ Qwen⚡ Tongyi⚡ GPT-6 Astra 🤖 OpenGCUA 🤖 OSWorld 🤖 Computer-Use 🌐 Alibaba 🌐 Tongyi Labs

#OpenGCUA#Computer-Use#OSWorld#Alibaba#GUI Agent#Automation

TesterArmy@tester-army·Collected 33d ago

👀217

🔥90

TesterArmy's open-source e2e tops GitHub daily trending: natural-language agent steps for web and mobile tests, replayed with zero model calls

e2e (tester-army/e2e), an Apache-2.0 AI end-to-end testing framework, gained 1,430 stars today to top GitHub Trending (3,828 total; 60,933 npm downloads last week). Tests mix natural-language agent.act/agent.assert steps with locator assertions; verified agent steps are recorded and replayed with no model calls until the app changes. v0.17.0 adds Copilot Responses-API models, OpenCode Console sign-in, and a decision-model executor for bounded actions.

Key Takeaways

#1 on GitHub daily trending: +1,430 stars today, 3,828 total (Apache-2.0)
npm package e2e: 60,933 weekly downloads (Sep 28–Oct 4); latest 0.17.0 released Oct 4
Record & replay: verified agent steps rerun with zero model calls until the app changes
v0.16.0 cut install footprint from 117 to 29 packages (~36MB to ~31MB)
7 packages: Playwright (Chromium/Firefox/WebKit), iOS/Android, PR reporter, hosted browsers/simulators, decision-model executor

Read full story

Linked Models & Agents:

🤖 Claude Code 🤖 Codex 🤖 GitHub Copilot 🤖 OpenCode 🌐 tester-army

#E2e#AI Testing#E2E Testing#Playwright#Mobile Testing#GitHub Trending#Decision Models#MCP

OpenAI@OpenAI·Collected 68d ago

👀52

🔥94

OpenAI Operator opens developer API preview for vision-driven browser automation and end-to-end E2E testing

OpenAI opened developer API access for Operator. Moving beyond traditional DOM-locator scripts, Operator leverages multimodal vision and native browser event synthesis to explore web applications, complete multi-step workflows, and flag visual regressions without brittle test maintenance.

Key Takeaways

Vision-driven browser automation eliminates fragile XPath and CSS selector maintenance.
Natively interacts with complex Canvas graphics, dynamic charts, and Wasm elements.
API ready for seamless integration into CI/CD build gates and release pipelines.

Read full story

Linked Models & Agents:

⚡ GPT-4o 🤖 operator 🌐 OpenAI

#OpenAI#Operator#Browser agent#E2e testing#Vision agent

Browserbase@browserbase·Collected 68d ago

👀62

🔥91

View on 𝕏 ↗

Stagehand v4 Rebuilt from Scratch as a Browser-Agent SDK, Pre-Installed Across Browserbase

Browserbase launched Stagehand v4, rewritten specifically as an AI agent browser SDK rather than a test runner, delivering 2x execution speed, 80% token reduction, and pre-baked deployment in all Browserbase instances.

Key Takeaways

Decouples AI browser-agent tooling from legacy test automation suites with 80% token optimization;
Built-in self-healing actions and robust iframe traversal resolve common DOM interaction breakages;
Pre-installed across all Browserbase hosted browsers for zero-setup cloud execution.

Read full story

Linked Models & Agents: