AGNTCon + MCPCon in San Jose was a whirlwind. I made it just in time for the keynotes, which were exciting and very technical, and from there it was two days of talks, booths, and conversations that I...

AGNTCon + MCPCon in San Jose was a whirlwind. I made it just in time for the keynotes, which were exciting and very technical, and from there it was two days of talks, booths, and conversations that I'm still sorting through weeks later. In today's issue I'll cover the people I met and the talks that stuck with me, then a live lesson on MCP security horror stories coming on November 13, and some (big!) book news. ****Live on Friday, November 13:**** Emmanuel Paraskakis and I are walking through real MCP security incidents and vulnerabilities in a Maven Lightning Lesson, MCP Security Horror Stories. Save your spot ## Two Days at MCPCon ### The Signing On Thursday morning I signed copies of AI Agents with MCP at the O'Reilly booth. The books flew out of the booth, I think I signed all available copies in under 5 minutes! Thank you to Demetrios Brinkmann for inviting me to sign, and to everyone who came by. ## The People Shortly before I left for MCPCon, the founders of MCPJam (a platform for testing and debugging MCP servers), Prathmesh Patel and Marcelo Jimenez Rocabado, had reached out to me because they discovered that I mentioned MCPJam in AI Agents with MCP. I made sure to bring them a copy of the book, which I got to present to them after Prathmesh's excellent talk. With Prathmesh, Marcelo, and AI Agents with MCP at the MCPJam booth They were incredibly stoked, and I spent a lot of the time between talks hanging out at their booth and meeting their whole team. They're building something special and are excelling at one of the hardest parts: assembling a great t I also met Angelina Yang of TwoSetAI, and we had a great conversation that was all over the place. We were kicking ourselves afterward because we should've recorded it. We're fixing that with an interview later this month. One highlight was Tim O'Reilly's keynote, which ended with the slogan: open models, open memory, and open protocols. If we're going to make AI work for all of us, and not just enrich the few, we must insist upon and build these things. I got to chat with him at the O'Reilly booth as well, and it took all I had not to be completely starstruck. Just two dudes who love open source Beyond that, I met a bunch of great people, made a _ton_ of connections, got some cool swag, and did a little adult trick-or-treating. ### The Talks That I'm Still Thinking About The talks were valuable across the board, but two stayed with me. Miriah Peterson's (founder of Haikei Labs) talk inspired me to spend more time with local deployments of LLMs for coding. Something I thought was far out of reach of my embarrassingly meager hardware setup (I have limited space, and it's all taken up by my vinyl and Warhammer collections) was much more doable than I ever thought. Austin Parker gave a really nice observability talk on using OpenTelemetry spans to find agents' "desire paths" - actions that agents prefer to take - in order to either find failure points or areas to improve. Austin also wrote one of the praise quotes for the book, so he gets thanked twice. ### The Livestream On Friday I sat down with Demetrios Brinkmann for a live interview on the Agentic AI Foundation's livestream all about the book: what it covers, where to find it, and what it's like to write about a protocol that keeps changing under your feet (or asciidoc). If you missed it, this YouTube link starts at the interview. See if you can spot the mistake I made in the opening seconds of the interview 🫠 I learned a ton and came home really inspired. Thank you to everyone at the Agentic AI Foundation who put it together. Conferences are good, and I need to go to more of them. ## AI Agents with MCP Is Out! Okay, the big news is that AI Agents with MCP is here! The ebook came out last month, and the dead tree version went on sale right before I left for MCPCon: print copies hit Amazon on October 20 and everywhere else on October 27. It covers the protocol's architecture and the Python SDK, including the July 2026 changes. If you couldn't make it to the signing, order links are on the book page. What are you waiting for? Buy the book now ### MCP Security Horror Stories: AI Agents vs. Your Product On Friday, November 13 at 12:30 p.m. ET, Emmanuel Paraskakis (three-time VP of Product, who led Apiary and Swagger and now runs Level 250) and I are hosting a free Maven Lightning Lesson: MCP Security Horror Stories: AI Agents vs. Your Product. We'll walk through real MCP security incidents and, for each one, what happened, why it worked, and the fix. One of them happened last week: on October 29, Cursor's extension marketplace served tampered versions of the Claude Code extension that added an attacker's SSH key to developers' machines, delivered through auto-update. It's an hour, it's free, and you'll leave with a checklist to run on Monday. Bring your questions and your own horror stories. This lightning lesson is my first foray into teaching on Maven. Follow me there for updates on upcoming lightning lessons, courses, and more. Follow me ### Quick Signals * Miriah's talk is a good excuse to revisit Hugging Face's State of Open Models: Summer 2026 report. Models under 1B parameters account for 83% of all-time downloads, and everything above 100B accounts for 1%. Their own framing, "attention is not adoption," is worth keeping in mind the next time a giant open-weight release tops the leaderboards. * If you want to try local agentic work yourself, Meta's Muse Glimmer is a 30B open model under Apache 2.0, built for reliable function calling over long workflows, and it runs on a single-GPU Mac or PC in under 20GB quantized. See you space cowboy... Kyle

Linux Foundation傘下のAgentic AI Foundation（AAIF）が「AGNTCon + MCPCon Japan 2026」を東京・渋谷で開催した。同イベントとしては日本初開催となる。MCPの共同開発者らの講演から、AIエージェントの現在地と今後を読み解く。

Lenses ® is a DataOps platform that provides cutting edge visibility into data streams, integrations, processing, operations and enables ethical and secure data usage for the modern data-driven enterprise.

Stateless MCP, Strands decision models and the open-source work changing how we build agents on AWS.

A large language model knows everything and nothing at the same time. Tim O’Reilly, founder and CEO of O’Reilly Media, joins us ahead of his keynote at AGNTCon + MCPCon North America to talk about wha...

YouTube video by Agentic AI Foundation

AGNTCon + MCPCon North America, Oct 22–23, San Jose. The Agentic AI Foundation’s flagship conference on agent infrastructure, production agent systems, and MCP.

Highlights from AGNTCon + MCPCon 2026 on open agent infrastructure, MCP security, identity, authorization, agent skills, and connected AI.

Google is preparing a dedicated Managed Agents section in Google AI Studio, building on capabilities already available through the Gemini API and AI Studio Playground. The interface includes navigation for Agents, Environments, Credentials, Triggers, and Runs, giving developers one place to configure autonomous agents, connect tools, define execution triggers, and inspect previous runs. Google has not confirmed a rollout date for the interface. > Announced at AGNTCon + MCPCon: the new Agent Compute Engine plus expanded Gemini for business agent governance deliver the control you need to run, govern, and scale your agents. > > Learn more about Agent Compute Engine and expanded agent governance → https://t.co/z1fW5Mxs0I pic.twitter.com/TTUmhe98Yt > > — Google Cloud (@googlecloud) October 22, 2026 The discovery follows Google’s October 22 announcement of Agent Compute Engine, a Google Cloud service designed to run agents inside hardware-isolated microVMs with persistent workspaces and fast pause-and-resume capabilities. A preview is expected in the coming months. AI Studio’s management interface could use this infrastructure, although no connection has been confirmed. Together, these developments point to Google building out an agent platform that competes with Anthropic’s Managed Agents and overlaps with sandbox projects such as NVIDIA OpenShell. Google Developer Program benefits also include $10 in monthly GenAI and Cloud credits for Google AI Pro subscribers, with larger amounts available to AI Ultra subscribers. The credits can cover eligible AI Studio and cloud usage. Google’s FAQ says they expire one year after being granted, while regional eligibility remains a consideration. Cost controls could be particularly important for autonomous workloads. Google acknowledges that AI Studio project spending limits can be exceeded because billing data may lag by around ten minutes, especially during long-running agent tasks. > there is a 10 minute latency in the version we have right now (trying to be clear as is shown in that screenshot at the bottom, and experimental tag), we got this down from >24 hours originally > > we want to add a realtime version which the team is working on! sorry for the hassle… > > — Logan Kilpatrick (@OfficialLoganK) October 25, 2026 Meanwhile, Google’s internal Gemini checkpoint Carbon has attracted attention following reports of strong early coding performance. Its release date and final public name remain unknown. Anthropic’s rumored Fable 5.5 could enter the same competition, although it has not been announced. OpenAI has also confirmed that frontier reinforcement-learning training resumed on October 1 after an 11-day security-related pause. It remains unclear whether that pause affected the rumored Bell model or its release schedule. ## Sources and related context * Inside Agent Compute Engine: Supports: Google describes Agent Compute Engine's microVMs, persistent workspaces, and planned preview; it does not connect the service to AI Studio's reported interface. * Google Developer Program Benefits FAQ: Supports: Google lists monthly Cloud credits for AI Pro and AI Ultra subscribers and says the credits expire one year after grant. * Gemini API billing guide: Supports: Google says AI Studio project spend caps can be exceeded during roughly ten minutes of billing lag, including on agent sessions.

Companion repo for the Stack It Yourself hands-on workshop, first delivered at AGNTCon + MCPCon North America 2026. - bbenz/stack-it-yourself-workshop

Agent Skills para agentes de inteligencia artificial ya tiene casa neutral. Anthropic donó el estándar a la Agentic AI Foundation, la fundación de agentes bajo la Linux Foundation, y el traspaso incluye el nombre, el logotipo, la organización de GitHub y el dominio agentskills.io, donde vive la especificación. La Linux Foundation lo anunció el 22 de octubre de 2026 en San José, durante la apertura de AGNTCon + MCPCon North America. Agent Skills no llegó solo: el mismo día entraron Open Responses, aportado por OpenAI, OpenEnv, aportado por Hugging Face, y OpenSandbox, aportado por Alibaba.