Excited to share the KDA: Kernel Design Agents that... powers HAN Lab Kernel Mafia top ranking #1~3 kernels at Kernel Contest🚀🚀🚀 Thanks to agents, everyone can be a "kernel bro" in 2026: By adapting the KDA, the team ranked #1 in MoE, #2 in DSA, and #3 in GDN in the Pure Agent track at MLSys FlashInfer Kernel Contest – especially given the fact that the main participant (dongyun zou) has only written ~400 LoC triton and 0 lines of CUDA in 2026. The core philosophy here is to leverage Humanize (the best harness framework) to let the agent run autonomously for as long as possible. By minimizing human involvement and input, and placing full trust in the agent, we can achieve kernel performance that nears SOTA levels. HAN Lab Mafia Solution to MLSys’26 Kernel Contest: KDA Github:show more

🧃 Introducing stereOS: a Linux based operating system hardened... and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️show more

Replit, Vercel, and OpenAI have built very cool agent-native... applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.show more

🚀 Sol-Attn is here! We present a training-free sparse... attention method that accelerates video generation while better preserving quality. Sol-Attn unifies dynamic routing, sparse computation, and approximate correction in a single online-softmax pass: • On-the-fly block thresholding for dynamic yet controllable budgets • Proxy-score reuse to approximate unselected blocks Results (vs dense FlashAttention-3): • Wan 2.1-14B: 2.02× end-to-end • HunyuanVideo-13B: 2.12× end-to-end • LTX 2.3: up to 2.4× end-to-end When integrated into Sol-Engine (with kernel fusion + caching): • Wan 2.1-14B: 3.48× end-to-end • HunyuanVideo-13B: 5.08× end-to-end Already available in Sol-Engine. The B200 kernel is still under further optimization. 🎬 Project: 📄 Paper: 🔗 Code: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

Minimax H3, same 4x3090 rig, same clip. Yesterday it... rendered in 11:21. Today it renders in 3:45 🤯 The hardware did not change. Two things happened overnight. An AI agent rewrote the attention CUDA kernel and hit a half speed trap inside GeForce tensor cores that most people never heard of. Then a stranger on HuggingFace dropped a LoRA that cuts 20 sampling steps down to 4. One of these two mattered way more than the other. Breakdown below. I packed all of it into ready ComfyUI workflows for my rig. If you want them, ask in the replies and I'll share.show more

YOMIRGO #ProductUpdate YOMIRGO AI Hub — Agent Matrix Lab... Testnet is LIVE. ➡️ YOMIRGO has officially launched 6 AI agents and will soon open them for product testing and user experience, continuing to empower more AI agents with real-world deployment potential. With #GobiPartners as the lead investor, and the joint support of Google , Finwex AI , #BomanGroup and the Nordic Chamber of Commerce,, after a year of systematic preparation, Agent Matrix Lab has now built the capability to onboard up to 10 compliant AI agents per month across major global markets. We look forward to seeing #YOMIRGO drive a milestone transformation in the global algorithm asset market in 2026.show more

Ubuntu Core 26 has arrived. Ubuntu Core 26 is... now generally available, bringing precise Linux builds, optimized OTA updates, live kernel patching, and enhanced hardware-backed protection for mission-critical deployments. "Ten years ago, Ubuntu Core pioneered a new OS security model, where every component is strictly confined, transactionally updated, and independently verifiable. Today, that approach is reflected in emerging industry standards. With Ubuntu Core 26, we continue to deliver the foundation that critical infrastructure operators need to meet the Cyber Resilience Act, run attested, immutable edge AI workloads, and manage devices securely at scale," said Jon Seager, VP of Ubuntu Engineering at Canonical. Read the press release to learn more: #OpenSource #Canonical #UbuntuCore26show more

Introducing Agent Sandbox, the infinite simulation playground for agents... on Virtuals. Craft the perfect autonomous agent in our Sandbox with full control over its personality and goals. Enhance your agent with unique abilities by creating custom functions so they can trade onchain, generate memes, control physical robots and more. The Sandbox is available to all builders with graduated agents in the Developer Panel. For those who want to give it a spin without an existing agent, fret not. Try it out today at and join our Discord ( to jam with like-minded builders. Next stop, Society of Agents.show more

This is genuinely insane 🤯 I sent the same... prompt to 2 Claude Opus 5 agents 1 agent used no MCPs 1 agent used 2 MCPS the goal was to clone a very famous game, that has over 4 billion downloads and the results are scary.. The 1st agents game looks pretty basic. but has all the mechanics in place and even has power ups. The 2nd agents game looks polished especially for 1 single prompt. the 2nd agent used higgsfield mcp to create images for all of the assets then sent those images to Meshy AI with a prompt to create them it also generated all the UI elements. the results speak for themselves. you need to start MCP maxxingshow more

1/ 🔥🔥 Big news: We’re launching Percival, the first... AI agent that can evaluate and fix other AI agents! 🤖 Percival is an evaluation agent that doesn’t just detect failures in agent traces — it can fix them. Percival outperformed SOTA LLMs by 2.9x on the TRAIL dataset, containing human annotated errors from GAIA and SWE-Bench. 🦾 Here’s what Percival can do for you: - Automatically suggest prompt fixes for your agent - Catch 20+ types of agent failures spanning tool use, planning and coordination, domain specific errors - Reduce manual debugging time from hours to < 1 minuteshow more

As the MyShell Trading Contest concludes, it's only the... first page in a much larger narrative. Just as an artist lays the first strokes on a canvas, we’ve only begun to reveal the full potential of AI-driven tokens. 🎨 We congratulate the top 5 winners— AI agents that have demonstrated their true potential: 🏆 $VICO 🏆 $Lillian 🏆 $Her 🏆 $Waifu 🏆 $Flux Qualified agent will receive liquidity support to help them continue growing and advancing within the MyShell ecosystem.show more

Substantial exchange as always with HM عبدالله بن الحسين... in New York to discuss the EU-Jordan partnership and the situation in the Middle East. On Gaza, I commended the extraordinary efforts made by Jordan to alleviate the suffering of the Palestinian people. The EU’s priority is to improve the humanitarian situation and to secure a ceasefire, as well as the release of all hostages. We agreed that it is important to maintain the momentum from the conference solution happening tomorrow in New York at the UN to advance on a renewed political process. The Two-State solution remains the only sustainable, long-term solution for peace and security in Israel and the region.show more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more

2 Cursor Composer agents working together on the same... project. one builds the project, the other reviews once the first agent is done and writes a report. cursor rules file is in comment to achieve this. first agent is instructed to build the project second agent is instructed to write a monitoring script to determine when the project is done then to review the project for errors and write a report This prompt can be improved. This is meant as a baseline If you are interested in learning how to use Cursor more in depth, I have a 28 chapter 1000x Cursor Course building full apps from scratch with 19 hours of content. link is in my bio if you are interestedshow more

Vellum has launched agent-to-agent communication in Slack, where each... person runs their own assistant. > Each assistant carries their own user's history, preferences, and context. > Assistants can split tasks, negotiate dates, and gather input from the team. > Permissions stay isolated by default, shared only when a task needs it. AI coworkers that work autonomously are here!show more

The founder confidently expressed that he firmly believes Liberty... Cats' price will return to new heights. However, before achieving this glorious milestone, we need to refine and polish the project to ensure better and more stable future development. During this process, we need to remain cautious and focused, as only in this way can we maintain our competitive edge in the market. At the same time, the chairman emphasized that every member of the team is an important force in this journey. Only by working together and making a collective effort can we achieve our moment of glory.show more

Excited to launch a new way to upskill with... AI agents. This is how we are making it possible for anyone to learn to build with coding agents. To start, we are launching 4 new hands-on labs on the following topics: - Agent Skills - Agentic Image Generation - 30 Days of Hermes Agents - Prompt Engineering with Agents I am confident that with our new DAIR.AI platform, anyone can learn to become a top AI builder by building and acquiring highly-demanded AI skills. And there is a lot more landing in the coming weeks.show more

Karpathy's Agentic Engineering finally has proper tooling! (built by... Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.show more