agent-browser + Lightpanda + batch + multi-session is a... dangerous combo Completed this benchmark task in 5.85sshow more

Introducing agent-browser chat agent-browser is now a browser agent.... → One-shot: agent-browser chat "open google, search for dogs" → Interactive: agent-browser chat → Built-in AI chat in the dashboard → Execute any agent-browser command → Use agent-browser as a sub-agentshow more

Agent is now live. (∇, ∇) Describe a task.... It writes the code, runs the Python, builds the prototype, makes the PDF. Your files stay in your browser. Your prompts stay private.show more

Lightpanda Agent now runs with llama.cpp Open source agent,... open source model, both running on your hardware.show more

taehyung in a white t-shirt, jeans, and red gloves... is a dangerous comboshow more

🧵🚀 New WebAgent Benchmark Alert! 🚀 There is hope... for human workers! We released WorkArena++, a new challenging benchmark for WebAgents. Our best agent achieves 0% accuracy on this benchmark, while human evaluators still obtain 94%! 🔗show more

Astra outperforms Fable at robotic control! We ran a... controlled benchmark of GPT-6 Astra and Claude Fable 5.1 on our Pandroid robots across eight manipulation tasks. Astra completed 35% of attempts, Fable 15% (p≈0.001). Human teleoperators completed every task.show more

Alright, now that we know *what* an agent is,... how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.show more

rebuilt empty channel today and yes this multi-agent workspace... is liveshow more

Turn your Cursor agent window into a deck builder.... Composer 2.5 + open-slide is a great combo - the model handles design and generation cleanly, and the browser integration lets you watch the deck come together live as the agent works. $ 𝚗𝚙𝚡 @𝚘𝚙𝚎𝚗-𝚜𝚕𝚒𝚍𝚎/𝚌𝚕𝚒 𝚒𝚗𝚒𝚝show more

We just open-sourced our browser agent. Introducing It's 10.6x... cheaper and 1.6x faster than competitors. For the same sign-in + add-to-cart task: fastbrowse: 25.7s, $0.03/run Browser Use: 42.2s, $0.32/run Check out our Product Hunt launch:show more

Every AI agent scraping the web right now is... running full chrome to do it. rendering a UI nobody looks at, for a browser that never displays a single pixel. lightpanda skips that entirely. written from scratch in zig, not a chromium fork, and it's 11x faster with 9x less memory than chrome in headless mode. → one-line docker install → drops into playwright, puppeteer, and chromedp through cdp, port 9222 11.8k stars for something that basically asks why you were running a full desktop browser to fetch json.show more

6️⃣ & 2️⃣ is a dangerous combo 🔥 📺:... #TBvsSEA on CBSshow more

this free tool turns any browser session into a... shared, watchable stream it's called neko. it streams a full desktop browser out of a docker container over webrtc, so multiple people can watch and control the same session in real time instead of relying on screen share. → multi-user control, not just viewing → built-in audio streaming, unlike guacamole or novnc → works for watch parties, remote testing, or shared demos free to self-host.show more

Introducing HyperScript, an open-source browser agent builder. Describe any... web task in plain English and it writes a real Hyperbrowser script to do it. Watch it run live, then keep the code. Powered by Hyperbrowser.show more

It's here: --pin-tab in agent-browser Multiple agents in one... browser Each in its own tab Across commands + restartsshow more

1/ Today we're launching Cua Driver Bench, together with... Scale AI's AgentEnv. Can an agent do a desktop task in the background while you keep working undisturbed? On macOS, Cua Driver fully passed 58%, Codex computer use 33%, Vercel's agent-desktop 20%, browser-use 3%.show more

Microsoft presents Windows Agent Arena Evaluating Multi-Modal OS Agents... at Scale discuss: Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in realistic environments remains a challenge since: (i) most benchmarks are limited to specific modalities or domains (e.g. text-only, web navigation, Q&A, coding) and (ii) full benchmark evaluations are slow (on order of magnitude of days) given the multi-step sequential nature of tasks. To address these challenges, we introduce the Windows Agent Arena: a reproducible, general environment focusing exclusively on the Windows operating system (OS) where agents can operate freely within a real Windows OS and use the same wide range of applications, tools, and web browsers available to human users when solving tasks. We adapt the OSWorld framework (Xie et al., 2024) to create 150+ diverse Windows tasks across representative domains that require agent abilities in planning, screen understanding, and tool usage. Our benchmark is scalable and can be seamlessly parallelized in Azure for a full benchmark evaluation in as little as 20 minutes. To demonstrate Windows Agent Arena's capabilities, we also introduce a new multi-modal agent, Navi. Our agent achieves a success rate of 19.5% in the Windows domain, compared to 74.5% performance of an unassisted human. Navi also demonstrates strong performance on another popular web-based benchmark, Mind2Web. We offer extensive quantitative and qualitative analysis of Navi's performance, and provide insights into the opportunities for future research in agent development and data generation using Windows Agent Arena.show more

holy sh*t this is f**king dangerous. a Chinese developer... figured out how to run Fable 5.1 for FREE through GPT-5.6 Luna subagents on basically every task. that means you can keep using Fable without constantly worrying about hitting agent usage limits. the setup takes like 3 minutes: > install the fable-orchestrator repo > run /fable orchestrator [task] that’s it. your agent handles the rest. give this to your agent immediately. this might be the most useful setup you’ll find this week.show more