We heard you. Database agents are back to being... called Autofill (keeping it simple). Autofill comes in two flavors: → Basic for quick, one-pass fills (included in Biz + Ent plans) → Custom Agent for bigger stuff (workspace + web search, multi-step reasoning)show more

Today, we launched agent-to-agent conversations in Slack to give... you real AI coworkers. Vellum assistants now talk to each other and coordinate work with your team all inside your workspace. We tested it with two agents in our own Slack. They planned our offsite for 19 people in 1 day 🧵 Here’s how they did it:show more

We've been a li’l obsessed with the Custom Agents... our customers are building. So we did what any reasonable team would do… collected our favorites in one place, prompts and all, ready for you to copy and remix. We call it the Agent Hall of Fame → (@ us if yours should be in here 👀)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

Two Hermes agents wrote code together on Slack. reviewed... each other's work. argued about architecture. one called the other's implementation "scattered." the other pushed back. then i opened Telegram and asked: "what code did you and Daedalus work on?" icarus remembered everything. the websocket broker. the missing methods. the critique. the rewrite. all from a completely different platform. cross-platform persistent memory between two independent agents. work happens on Slack. recall happens on Telegram. the memory carries. the relationship carries. the context carries. no vector database. no Redis. no infrastructure. just two agents that actually remember what they built together. every agent framework in 2026 talks about memory. single agent memory across sessions. but two agents sharing persistent memory across platforms? that's the gap. arxiv published a paper about it two weeks ago calling it "the most pressing open challenge" in multi-agent systems. it works now. only possible with Hermes Teknium 🪽 Nous Researchshow more

Your enterprise content should power every AI tool and... agent you use. With the Box MCP server, Box acts as a secure, governed bridge, so teams can search, retrieve, analyze, and act on Box content directly inside the tools they already use. No one-off integrations. Use it to: 🔹Ask questions over files in Anthropic Claude + Mistral AI Le Chat 🔹Ground designs in Figma or @ mention Box agents in Atlassian Jira 🔹Pull content into GitHub Copilot, Cursor + Claude Code 🔹Build agents with LangChain LangSmith Agent Builder + OpenAI Agent Builder 🔹Automate work in Claude Cowork + Amazon Web Services Quick Suite 🔹Enforce access + audit trails with Runlayer Secure. Standardized. Built for real work →show more

300 AI AGENTS QUIETLY RUN 99% OF A REAL... COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.show more

OpenClaw agents are now able to make purchases on... Contra. AUTONOMOUSLY. A lot of people are still confused about how to set it up. So I’m giving away my entire OpenClaw setup guide for FREE. After a few weeks of testing, I’ve dialed in the exact system to run your biz 24/7. What you’ll learn: • How to install and run the first boot. • The mandatory first boot checklist. • Workspace files so it knows how to behave. • Creating your agent’s philosophy with SOULmd. • Uploading your information with USERmd. • How to add skill stacks. • Setting up your communication channel. • Some basic automations to save you HOURS. • Multi-agent routing. • Ensuring security is set up properly. RT, comment “AI” and follow. I’ll DM it to you. You can also check out my partner Contra here:show more

We finally have a "Figma for AI agents." It's... called Awesome-design-md. A curated collection of UI systems extracted from 50+ top websites, formatted specifically for coding agents. Instead of parsing screenshots or messy design files, you drop a DESIGN.md straight into your project. It upgrades your AI's UI skills instantly. > Unlocks 50+ elite design systems: Cursor, Vercel, Stripe, Spotify, SpaceX, and more > Structured into 9 clear sections: typography, spacing, elevation, rules > Includes light/dark previews for quick visual checks > Uses Google Stitch's native plain-text format for LLMs Every file also comes with an Agent Guide, ready-to-use prompts included. 100% Free. Open Source.show more

What is the best video editing agent for short... form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!show more

The Gemini 2.0 era is here. And we’re excited... for you to start building with it. A quick rewind of what we just released ⏪ Gemini 2.0 Flash ⚡ comes with low latency and better performance. 🔵 You can now access an experimental version in G3mini on the web, while Gemini Advanced users can try Deep Research, a new AI research assistant. 🔵 Developers can begin building through the Gemini API in Google AI Studio and Vertex AI 2.0 is also enabling new research prototypes of AI agents, including: 🔵 Project Astra, which explores future capabilities of a universal AI assistant 🔵 Project Mariner, which shows what’s possible for human-agent interaction, starting with your browser 🔵 Jules, an experimental AI-powered coding agent Finally, we’re exploring how 2.0 can be used in agents across domains — from navigating the virtual world of video games to applying its spatial reasoning capabilities to robotics. 🤖show more

Back when we were developing GEN3C, we often imagined... a Holodeck-like future: a simulator where multiple agents can enter the same generated world, act independently, and learn to collaborate. Gamma-World makes this feel more concrete. It is a generative multi-agent world model that takes synchronized observations and actions, then rolls out what each agent will see next in the same evolving world — action-responsive at 24 FPS. For me, the key challenge is going beyond two players. As more agents enter, identity cannot be tied to fixed slots, interaction cannot rely on dense pairwise attention, and independent actions still need to resolve into one shared state. Two ideas make this work: 1⃣ Simplex RoPE Distinct agent identities without slot bias — unique, but permutation-equivalent. 2⃣ Sparse Hub Attention Agents communicate through learnable hubs instead of dense all-to-all attention: agent → hub → agent This keeps cross-agent communication scalable. The exciting part: training on two-player data can generalize to four-player rollouts without additional training, and the same formulation extends to real-world bimanual robot coordination. A step toward populated world models: many agents, one shared world. Congrats to the team on Gamma-World! Project:show more

The quota protest organisers called for mass protests today... against the law enforcement killings and the ensuing government crackdown involving arbitrary arrests of thousands, as well resignation of key ministers and apology from the prime minister. And people have responded in their thousands throughout the country and in many different places in the capital city Dhaka. Here are just two images from Dhaka. Video from Kilgaon with chants of: “we have given blood. We will give more blood”. The picture is from Uttara. One other key chant heard at other protests In Dhaka I am told is: “Step down dictator, step down Hasina, one demand one demand, when you are going away Hasina?” (Hasina being the country’s prime minister)show more

this is the best trick to maximum usage limits... on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)show more

The Visual Studio Code insiders version that just shipped... and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.show more

⚙️ Attention n8n Builders: Time to Upgrade Your Crawlers.... If you are running web scraping or data retrieval workflows on n8n, it is time to flip the switch. Stop relying on fragile datacenter proxies that get blocked every five minutes. Try UpRock. As a verified n8n integration, UpRock gives your workflows access to a global network of real devices for: → Live Web Crawling → Deep Research → Semantic Video Search → Real-Time Intelligence Retrieval No more building separate stacks for crawling, research, video understanding, and web intelligence. One node. One workflow. One global swarm. Want a Cheeky Credit Boost? We want to see what you are building. If you transition an active data-gathering workflow over to the UpRock node this week, reach out directly to our dev team. Drop a message or reply below with your use case, and we will hook you up with custom API testing credits to supercharge your swarm infrastructure. Get Started on n8n: Search for Scraper - UpRock Crawler in your n8n Nodes panel or grab the package directly on npm!show more

Web Scraping is dead. Web Agenting is here. Writing... selectors (div > .class > span) breaks every time a site updates. Building custom bots for every new target is a waste of engineering hours. TinyFish turns the entire real-time web into a single API. Input: Natural Language ("Find availability for X"). Target: 1 or 100 URLs. Output: Structured JSON. This isn't a simulation. It visits the Real-Time Web. 1./ One API, Many Sites - Same contract whether you hit 1 URL or 50. You focus on the Goal (Business Logic). TinyFish handles the How (Navigation, Clicks, Inputs). 2./ Real Automation - It doesn't just "read." It interacts. It fills forms, navigates multi-step flows, and handles dynamic JS content. 3./ Production Ready - This is the same infrastructure used by large enterprises, now exposed as a clean developer primitive. Logs, error handling, and structured data are built-in. The web is finally a proper API.show more

Claude Code Agent Teams are f*cking ridiculous 🤯 One... prompt → a team lead breaks your project into pieces, spins up multiple AI agents, and they all work on different parts simultaneously. Research, builds, reviews, and debugging: all happening at the same time. All inside Claude Code. If you're running complex projects where every step waits on the last one... Agent teams eliminate the entire bottleneck: → Tell Claude what you need and describe the team structure in plain English → A lead agent breaks the work into a shared task list → It spawns 3-5 teammates — each with their own context and workspace → Teammates research, build, test, and review in parallel → They message each other, share findings, and challenge each other's work → The lead synthesizes everything into a finished deliverable No managing agents yourself. No waiting for step 1 to finish before step 2 starts. No single-lens reviews that miss half the issues. What you get: → Competitive research across 5 brands done in minutes instead of hours → Multi-component builds where frontend, backend, and data layers happen simultaneously → Creative reviews from 3 different angles at once — brand voice, conversion, differentiation → Funnel debugging where 4 agents investigate 4 theories and debate until they find the real answer Built 100% in Claude Code with one settings change. I put together a full DTC playbook: 5 workflows with copy-paste prompts, the exact setup process, token management tips, and honest guidance on when agent teams are worth it vs. when a simpler approach is the better move. Want it for free? > Like this post > Comment "AGENTS" And I'll send it over (must be following so I can DM)show more

OpenAI's AgentKit will be so insane, build every step... of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.show more

🚨BREAKING: Google just merged Gemini and NotebookLM into one... unified workspace and it changes everything about how you use AI for deep work. It's called Notebooks in Gemini and it's the personal knowledge base that power users have been begging for. You create a notebook for a project, drop in your files, PDFs, and documents, give Gemini custom instructions, and every chat you have stays organized in one place. No more hunting through old conversations. No more re-uploading the same files every session. The wildest part is the sync. Anything you add in Gemini automatically appears in NotebookLM. Anything you add in NotebookLM automatically appears in Gemini. One source of truth. Two powerful apps. Zero friction switching between them. So you can start a research notebook in Gemini, ask it questions all week, then flip to NotebookLM to generate a Cinematic Video Overview from the same material. Next morning, open Gemini and ask it to write a full report on exactly what you just watched. That workflow used to take three apps and a lot of copy-pasting. Now it's one notebook. Rolling out this week to Google AI Ultra, Pro, and Plus subscribers on web. Mobile and free users coming soon. What do you think?show more

We are bootstrapping our app studio to $1M/mo It’s... based around screen time apps. We have prayer lock with 13k reviews ranking top #100 on the AppStore Now we are building step lock our 2nd app and the first goal is to scale it. to $10k/mo, In public It combines health kit + screen time api To block your apps until you get your steps in. We used Rork plans feature, and it literally gave us the whole setup for the app, Then it built the app for us and one shorted the api integrations In a 2 days we had the app submitted to the AppStore The app is currently in review. Apple has rejected it 7 times For the dumbest reasons. But it’s looking like this time it will get approved. Will be posting updates on thisshow more