🎉 We've surpassed 10,000 stars! A huge thank you to our community! Now, we're launching Midscene v0.27! 🚀 Building on 0.26's Rslib integration, 0.27 makes a major refactor, making it incredibly easy to add new devices & AI operations. Now is the perfect time to contribute!
Midscene 0.24 is released 1. 🚀 MCP for Android Automation 2. 🌐 Web Optimization 3. 🔧 Development Experience BTW, The new report now supports viewing the AI token consumption(Pic 2) #AI #Automation #Playwright #Puppeteer #BrowserUse #VibeCoding #AIAutomation #Midscene
We're hiring a Web Architect to shape the future of TikTok.com. If you're passionate about large-scale systems, performance, and elegant architecture (React / TS / Node), we want to hear from you. Let’s build the best web platform, together. DM is open. cc…
新版报告超酷的，执行任务每一步花了多少 token， GUI 自行回放动画也更精细了！
Midscene 0.23 is released 1. 📊 New Report Style 2. ⚙️ YAML Script Ability Enhancement Changelog: midscenejs.com/changelog.html Star the GitHub for timely updates: github.com/web-infra-dev/… #AI #Automation #Playwright #Puppeteer #BrowserUse #VibeCoding #AIAutomation #Midscene
Qwen 团队太赞了，有效打破 claude 模型在 code 领域的垄断地位，开发者狂喜😍
>>> Qwen3-Coder is here! ✅ We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves…
习惯用 ts、tsx 开发后，改用 js、jsx 和 vibe coding，感觉开发效率提升了很多。相比之下，ts 的类型限制有时会影响模型效率，而用 js、jsx 开发更灵活顺畅。
支棱起来了，参数太大了不然自己部署个玩玩
🚀 Hello, Kimi K2! Open-Source Agentic Model! 🔹 1T total / 32B active MoE model 🔹 SOTA on SWE Bench Verified, Tau2 & AceBench among open models 🔹Strong in coding and agentic tasks 🐤 Multimodal & thought-mode not supported for now With Kimi K2, advanced agentic intelligence…
用 Claude code Cli 这类 Agent 开发新项目，等到项目的逻辑复杂度到一定规模后碰到 bug，然后它又死活改不对，你就会发现你对项目失去掌控力了，要重新花很多时间梳理项目逻辑😂
有没有人对 Midscene 的浏览器插件和整个 Agent 设计比较感兴趣的，我在考虑后续对于 Midscene 的开发是不是采用 Build in Public 的方式
如果不想花 $200 刀，体验 Perplexity Comet 浏览器的能力，可以考虑一下用 @midscene_ai 和 @agent_tars ，除了他们自己的搜索数据源上和 产品交互类型上更丰富一些其实不会比 Midscene 和 Agent_tars 做的好太多，因为现在 SOTA 的 GUI agent 模型还是 doubao1.5 VL!
如果不想花 $200 刀，体验 Perplexity Comet 浏览器的能力，可以考虑一下用 @midscene_ai 和 @agent_tars ，除了他们自己的搜索数据源上和 产品交互类型上更丰富一些其实不会比 Midscene 和 Agent_tars 做的好太多，因为现在 SOTA 的 GUI agent 模型还是 doubao1.5 VL!
目前应该是开源 Chrome extension 里 LLM 控制浏览器执行做的最好的，赶紧来试试，体验一下 LLM 在 GUI 操作上到底到什么水平了😍
🎉 The Midscene 0.21 update is here! 🎨 The Chrome extension has been upgraded 🌐 Web 1️⃣ New Chrome extension interface 2️⃣ Increased flexibility in timeout configuration 3️⃣ Unified Puppeteer and Playwright configurations 4️⃣ New data export callback mechanism
🎉 Midscene 0.20 Released 🌐 Web 1️⃣ New aiAsk Method 2️⃣ Passing XPath to Locate Elements 📱 Android 1️⃣ Playground Tasks Cancellable 2️⃣ Enhanced aiLocate API 📈 Report Memory occupancy optimization #AI #Automation #Playwright #Puppeteer #BrowserUse #VibeCoding #AIAutomation
doubao 新出的几个模型都挺不错的，特别在 GUI agent 上多项指标都处于 SOTA 水平，但是关注度都挺低的😅。不知道是不是公司在 PR 上做了比较多的限制，避免被多关注...
Announcing Midscene v0.16 with Midscene MCP 🤖 Use Cursor / Trae to help write test cases. 🕹️ Quickly implement browser operations akin to the Manus platform. 🔧 Integrate Midscene capabilities swiftly into your platforms and tools. Read more: midscenejs.com/mcp.html
United States 트렌드
- 1. Flacco 62.3K posts
- 2. Bengals 66.7K posts
- 3. Bengals 66.7K posts
- 4. Ramsey 16.4K posts
- 5. Tomlin 16.2K posts
- 6. Chase 99.9K posts
- 7. Chase 99.9K posts
- 8. #TNFonPrime 4,694 posts
- 9. #WhoDey 5,095 posts
- 10. Teryl Austin 1,785 posts
- 11. #HereWeGo 9,729 posts
- 12. #PITvsCIN 6,155 posts
- 13. Max Scherzer 11K posts
- 14. Andrew Berry 2,188 posts
- 15. Zac Taylor 2,185 posts
- 16. DK Metcalf 3,600 posts
- 17. Cuomo 68.8K posts
- 18. Darnell Washington 2,364 posts
- 19. Ace Frehley 83K posts
- 20. Cincy 3,717 posts
Something went wrong.
Something went wrong.