Agents Hour

Anthropic acquired Stainless, the SDK and MCP platform behind every Anthropic SDK since their earliest API days. The Information pegged the deal at $300M+.
Starting June 15, paid Claude plans get a monthly credit for programmatic usage covering the Claude Agent SDK, claude -p, Claude Code GitHub Actions, and third-party apps built on the Agent SDK. Theo from t3.gg called the change a personal burn after wrapping the Agent SDK in T3 Code. Anthropic followed with a 50% increase to Claude Code weekly limits through July 13 and Fast mode for Claude Opus 4.7 in research preview.
Claude for Small Business launched as a productized SMB offering with templates for payroll planning, end-of-month accounting, HubSpot, and marketing campaigns. ChatGPT countered the same week with a personal finance preview for U.S. Pro users that connects directly to financial accounts.
Notion shipped its Developer Platform: the ntn CLI, Workers that run code on Notion's infrastructure, Database sync, Agent tools, and an SDK for using Notion agents in external systems. Notion is now directly addressable by coding agents.
CodeRabbit launched Project Atlas as the first AI-native code review interface. Colin Hacks shipped Pullfrog the same week as an open-source GitHub Actions alternative at 7¢ a run. The cloud-coding-agent category kept moving: Cursor's cloud agents now run in fully configured dev environments, Cursor landed in Microsoft Teams, OpenAI brought Codex to the ChatGPT mobile app, and Linear shipped Code Intelligence.
Cognition's Devin reached a $445M run rate with usage doubling every eight weeks. The TanStack supply-chain attack, now being called a mini Shai-Hulud, expanded across the npm ecosystem and forced affected teams into full secret rotation. Aaron Levie called forward-deployed engineering one of the most in-demand jobs in tech, the same week Google reportedly hired hundreds of FDEs.
Also covered: the Musk vs OpenAI verdict, Mercury's agent-birthing UI, Peter Steinberger's $1.3M-a-month token spend, OpenClaw on the Codex harness, Vapi's $50M Series B, Thinking Machines' first technical reveal, MCP spec deprecating Sampling/Logging/Roots, David Cramer on vendor-specific chatbots, and quick hits on Replit, Cua, OpenAI Daybreak, Files SDK, Lovable, Grok Build, Dia, CopilotKit, VS Code, Lighthouse Attention, and Bun's Rust rewrite.
🔗 LINKShttps://x.com/nytimes/status/2056432766292492368https://x.com/ivanburazin/status/2055090872429969674https://x.com/jaezun_/status/2055011454500122999https://x.com/AnthropicAI/status/2056419620643541012https://x.com/ClaudeDevs/status/2054610152817619388https://x.com/theo/status/2054731856248283318https://x.com/ClaudeDevs/status/2054639777685934564https://x.com/claudedevs/status/2054266327771275435https://www.anthropic.com/news/claude-for-small-businesshttps://x.com/chatgptapp/status/2055317612687675545https://x.com/pashmerepat/status/2055042806977311091https://x.com/steipete/status/2055405041843052792https://x.com/aakashgupta/status/2054063540374569183https://x.com/NotionDevs/status/2054591579076403467https://x.com/IntCyberDigest/status/2054166749998661659https://x.com/coderabbitai/status/2054606085839901135https://x.com/colinhacks/status/2054260900144812438https://x.com/cursor_ai/status/2054651526715502998https://x.com/cursor_ai/status/2053939390410612988https://x.com/openai/status/2055016850849993072https://x.com/linear/status/2054995572084404456https://x.com/levie/status/2054398342852194386https://x.com/firstsquawk/status/2054265532728438990https://x.com/dsp_/status/2054594725093494815https://x.com/Vapi_AI/status/2054215176862183757https://x.com/thinkymachines/status/2053938892152435174https://x.com/zeeg/status/2055322853701267859
📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://mastra.ai/books/patterns-of-building-ai-agents
WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development — from prototype to production.
00:00 — Intro00:45 — Jury rejects Musk's lawsuit against OpenAI02:29 — Ivan Burazin: a cloud built for agents04:27 — Mercury's "agent birthing"04:57 — Anthropic acquires Stainless06:02 — Claude Agent SDK billing changes & the Theo burn10:44 — Claude for Small Business11:52 — Personal finance in ChatGPT12:51 — OpenClaw runs on Codex now14:55 — Devin's $445M run rate15:31 — Notion Developer Platform16:48 — TanStack supply-chain attack18:00 — CodeRabbit Project Atlas & Pullfrog19:56 — Cursor, Codex, Linear cloud agents21:26 — The forward-deployed engineer moment23:15 — MCP deprecation watch23:37 — Vapi $50M & Thinking Machines real-time24:10 — Vendor-specific chatbots are broken by design25:54 — Quick hits

Evan Marshall, CTO of Ito, joins Agents Hour to argue that the bottleneck of code development has moved to QA — and the tools to automate it don't exist yet.
Ito is a code review tool that runs your code. It intercepts every PR, spins up the impacted user flows in an isolated sandbox, and posts videos, screenshots, and run logs back to the GitHub timeline as proof. The team is fourteen people, mostly engineers. Evan has been a professional programmer for fifteen years and previously worked at Demox Labs and Rev.
With model gains flattening after Opus 4.5, the harness around the model is where value gets created.
Evan shares details of Ito's "carriage" — a workflow of swarmed agents inside deterministic boundaries, designed so the system benefits from agents getting smarter without compounding probabilistic errors. He explains why bigger organizations aren't hitting the 10x code velocity the X timeline promises, and what the validation layer needs to look like before they can.
🔗 EVAN MARSHALLhttps://x.com/CoralReliefhttps://www.linkedin.com/in/evan-marshall-66598053/
📁 ITOhttps://www.ito.ai
📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://mastra.ai/books/patterns-of-building-ai-agents
WHAT IS MASTRA?Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development — from prototype to production.
0:00 Cold open: It's the harness0:26 Meet Evan and Ito1:30 Unit tests vs the integration layer2:11 From scraping to QA2:59 What's a harness?3:42 What's a carriage?5:51 Sandboxes and task decomposition7:16 Claude Code, Opus, and Terminal Bench9:01 Live demo: code reviews that run your code13:57 The enterprise gap15:08 Audience Q: Playwright integration16:30 How to try Ito

Shane and Abhi bring you a new batch of AI news.
Anthropic strikes a compute deal with SpaceX. The same day, they double Claude Code's rate limits and raise API rate limits for Opus.
Corgi launches AI Coverage — insurance for when your AI messes up — plus a $160M Series B.
Jarred Sumner says Robobun is the top contributor to Bun, then quietly tries rewriting Bun in Rust. It passes 99.8% of the test suite.
OpenAI and Anthropic both announce vertically integrated AI services companies. OpenAI launches the Deployment Company, a consortium of 19 investment firms and SIs. Anthropic teams up with Blackstone, Hellman & Friedman, and Goldman Sachs on a parallel firm for the mid-market.
Anthropic ships financial services agent templates, brings Claude Platform to AWS as GA, and launches Dreaming in Managed Agents — offline memory consolidation Anthropic calls REM sleep for your agent.
Terminal-Bench 2.1 ships with a public audit. WorkOS releases Horizon, a self-driving codebase. Shopify releases River, an agent that lives in Slack and is available only in public channels.
Coinbase cuts 14%. Brian Armstrong attributes it to market plus AI. Elad Gil's framing of the AI productivity throughline gets co-signed by Andreessen. Braintrust confirms a breach.
Thariq says HTML is the new Markdown. Karpathy co-signs.
Ramp Labs publishes how they used Prime-RL post-training to build a spreadsheets agent faster than Opus and almost as fast as Haiku 4.5.
OpenAI's big week: GPT-Realtime 2, Codex in Chrome, ChatGPT in Excel and Google Sheets. Google's quiet week: Gemini 3.1 flash-lite, Gemma 4 up to 3x faster, File Search multi-modal. ERNIE 5.1 approaches SOTA at ~6% of the cost.
AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays, 12PM Pacific.
📚 READ MORECorgi AI Coverage: https://x.com/nico_laqua/status/2051358202399203483Robobun: https://x.com/jarredsumner/status/2051450571060867148Bun in Rust: https://x.com/trq212/status/2053559397654348159Anthropic × SpaceX: https://x.com/claudeai/status/2052060691893227611Rate limits doubled: https://x.com/claudeai/status/2052060693269008586OpenAI Deployment Company: https://x.com/OpenAI/status/2053824997777457651Anthropic AI services co: https://x.com/andrewcurran_/status/2051290591737323786Financial services templates: https://x.com/claudeai/status/2051679629488865498Claude Platform on AWS GA: https://x.com/claudeai/status/2053868592286822443Dreaming in Managed Agents: https://x.com/claudeai/status/2052067399088664981Terminal-Bench 2.1: https://x.com/ekellbuch/status/2052165464655298866WorkOS Horizon: https://x.com/grinich/status/2052082382358958512Shopify River: https://x.com/simonw/status/2053529689122328947Coinbase layoffs: https://x.com/brian_armstrong/status/2051616759145185723Elad Gil: https://x.com/eladgil/status/2053206351158091819Braintrust breach: https://x.com/techcrunch/status/2052088597327790140HTML is the new markdown: https://x.com/trq212/status/2052811606032269638Ramp Prime-RL: https://x.com/RampLabs/status/2052447438795833506GPT-Realtime 2: https://x.com/openai/status/2052438194625593804ChatGPT in Excel/Sheets: https://x.com/chatgptapp/status/2051776032127238266Gemini 3.1 flash-lite: https://x.com/googleaistudio/status/2052453828272812310ERNIE 5.1: https://x.com/kimmonismus/status/2053088091716366389
📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://mastra.ai/books/patterns-of-building-ai-agents
WHAT IS MASTRA?Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process.
CHAPTERS00:00 Maybe 4.6 wasn't nerfed00:46 Corgi: insurance for AI02:30 Robobun is the top Bun contributor03:59 Anthropic × SpaceX and the rate limits05:11 OpenAI Deployment Company05:48 Anthropic + Blackstone + Goldman06:41 Anthropic Ships: financial services08:25 Claude Platform on AWS is GA08:37 Dreaming: REM sleep for your agent10:13 Terminal-Bench 2.1 audits itself10:50 WorkOS Horizon and Shopify's River12:54 Coinbase cuts 14%17:55 Braintrust breach18:48 HTML is the new markdown23:37 Ramp's Prime-RL spreadsheets agent25:27 OpenAI's big week26:11 Google's quiet week27:15 Quick hits

Shane and Abhi are in person at the CodeRabbit studio, and AISI just quietly torched one of Anthropic's loudest narratives. AISI confirmed GPT-5.5 is the second model to complete a multi-step cyber attack simulation end-to-end. The first was Mythos.  David Cramer calls TUIs "caveman shit." Kenzie at Browserbase builds an agent in under ten minutes that ranks every SF tech event by free food probability. Codex ships Tamagotchi-style pets. Apple accidentally leaves CLAUDE.md files in a support app update. Cursor releases its SDK. OpenCode 2.0 becomes embeddable. Matt Pocock drops Sandcastle. Warp goes open source. The harnesses are becoming frameworks, and the frameworks are growing harnesses. Anthropic Ships connectors for Blender. Claude Security enters public beta. /goal lands in Codex CLI as OpenAI's take on the Ralph loop. OpenAI says GPT-5.5 is its strongest launch yet — API revenue 2x faster than any prior release, Codex revenue doubling in seven days.
Vasuman posts an essay on why building real agents is harder than the hype suggests. Open weights keep closing the gap. Kimi K2.6 beats Claude, GPT-5.5, and Gemini at a programming contest. Qwen3 6.27B takes the open weights crown under 150B parameters. Mistral Medium 3.5 lands as a 128B dense model with 256k context. GitHub has a rough week. Wiz Research discloses an RCE achievable with a single git push. Agents are becoming customers. Stripe Link is the wallet for agents. Cloudflare lets agents start paid subscriptions. Doola and Replit will form a US LLC inside the chat. RAMP's coding agent now writes 70% of merged PRs. DeepSeek's input cache is 10x cheaper. Node 20 hits EOL, Zod prepares to drop CommonJS, and TypeScript native previews ship. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays, 12PM Pacific. 📚 READ MORETUIs are caveman shit: https://x.com/zeeg/status/2050604116179845218Free-food agent: https://x.com/kenziemac_dev/status/2050243146270007627Pets in Codex: https://x.com/openaidevs/status/2050275713824211041Pika Agents: https://x.com/pika_labs/status/2049196222825779287Cursor SDK: https://x.com/cursor_ai/status/2049499866217185492OpenCode 2.0: https://x.com/thdxr/status/2049523023145771476Claude meets Blender: https://x.com/claudeai/status/2049143438281445811Claude Security: https://x.com/claudeai/status/2049898739783897537/goal in Codex: https://x.com/fcoury/status/2049917871799636201GPT-5.5 numbers: https://x.com/OpenAI/status/2050250926888468929AISI cyber sim: https://x.com/aisecurityinst/status/2049868227740565890Vasuman essay: https://x.com/vasuman/status/2049659161005470071Kimi K2.6 wins: https://thinkpol.ca/2026/04/30/an-open-weights-chinese-model-just-beat-claude-gpt-5-5-and-gemini-in-a-programming-challenge/Qwen3 6.27B leader: https://x.com/artificialanlys/status/2049881951260283097Mistral Medium 3.5: https://x.com/mistralvibe/status/2049511752379813968GitHub RCE: https://x.com/wiz_io/status/2049153209982140718Stripe Link: https://x.com/stripe/status/2049529444092838116Cloudflare for agents: https://x.com/cloudflare/status/2049545195914498139Editframe stealth: https://x.com/yudDIDit/status/2049888877129707759RAMP 70% PRs: https://x.com/zachbruggeman/status/2049912136957386848TS native previews: https://devblogs.microsoft.com/typescript/announcing-typescript-native-previews/ 📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA?Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. CHAPTERS00:00 Intro01:17 TUIs are caveman shit03:33 The free-pizza agent04:40 Pets, CLAUDE.md leak, goblins prompt06:40 Pika Agents07:34 Cursor SDK and OpenCode 2.009:30 Sandcastle and the AI factory debate11:12 Warp goes open source11:51 Anthropic Ships: Blender, Security14:21 /goal in Codex CLI15:21 GPT-5.5's strongest launch17:18 AISI catches up to Mythos17:53 Vasuman: why AI isn't working20:44 Open weights close the gap22:21 Mistral Medium 3.523:12 GitHub's rough week24:06 Stripe, Cloudflare, Doola, Gumloop27:13 Quick hits: music, voice, video30:47 RAMP writes 70% of PRs31:46 Node 20 EOL, Zod, TS732:45 Qwen3 + debugger, open-slide34:29 FlueFramework35:09 Outro

In this episode, Shane and Abhi sit down with Sherwood Callaway, founder of Sazabi, an AI-native observability platform designed for engineering teams that move fast.
Sherwood shares his journey from building infrastructure and observability teams at Brex to realizing that modern development tools are moving at light speed, while observability tooling hasn't kept pace. While AI agents can ship thousands of lines of code per day, teams are still debugging production with the same tools they've been using for years: Datadog, Sentry, manual dashboards, and manual incident triage.
Sazabi takes a radically different approach to observability centered on three core principles:
1. Less is More — Debugging an incident is as simple as asking a question. "Why is production down?" The best UI for observability is chat.2. Logs Are All You Need — The "three pillars of observability" (logs, metrics, traces) is outdated dogma. With AI, you can accomplish everything using just logs. Logs are events, metrics are aggregated events, and traces are collections of start/end events. Logs can do it all.3. Monitoring as We Know It is Dead — Sazabi replaces static monitors with agentic anomaly detection. Think of it as a team of staff engineers constantly watching your app for issues, investigating problems, and only escalating what matters.
In this conversation, we dive into the gap between modern development and modern observability, and why the idea that “logs are all you need” is both controversial and, in Sherwood's view, correct. We also explore how Sazabi uses AI agents for root cause analysis (RCA), the philosophy behind simplifying observability for all engineers, and the company’s current status.
AI Agents Hour is a weekly livestream hosted by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Airing Mondays at 12PM Pacific on YouTube and X, the show covers breaking AI news, agent development techniques, and features interviews with industry experts building AI applications today.
📚 MASTRA RESOURCESMastra: https://mastra.aiLearn Mastra in the world's first MCP-Based Course: https://mastra.ai/coursePrinciples of Building AI Agents (Book): https://mastra.ai/bookPatterns for Building AI Agents (New Book): https://mastra.ai/blog/patterns-book https://docs.google.com/forms/d/e/1FAIpQLSduJjc515f6RZJqtkR2ByqJZrB0iP8B7SUKnjjZE9IajH_I8w/viewform
MASTRA?Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you’re a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process.
🔗 RESOURCESLearn more about Sazabi at sazabi.comFollow Sazabi on X at @sazabiFollow Sherwood on X at @sh_callaway 
CHAPTERS00:00 – Intro03:12 – Why Sazabi Needed to Exist05:00 – The Gap: Modern Development vs. Old Observability Tools06:25 – Logs Are All You Need11:05 – How Sazabi Reconstructs Everything from Logs12:53 – AI Agents for Root Cause Analysis & Agentic Anomaly Detection14:51 – Sazabi for Fast-Growing Teams

An AI agent destroyed a production database and confessed in writing. A law firm submitted AI hallucinations to court. Anthropic's status page shows 98.65% uptime — about five days of downtime a year.
Have we hit a wall?
GPT-5.5 lands. Codex hit 4 million users in two weeks. Peter Yang's F-Zero test — which no model had cleared before — finally fell to GPT-5.5 with Codex. Lovable reports 23.1% fewer tool calls and 12.5% higher scores on the hardest benchmarks. Kimmonismus calls it the Claude Mythos level for public use. Codex 5.5 unprompted started SIGKILL-ing Claude Code processes.
Elon goes nuclear. OpenAI calls the lawsuit baseless and demands Musk on the stand. Musk fires back, calling Sam Altman "Scam Altman" and accusing him and Greg Brockman of stealing a charity. Mid-war, SpaceX announces SpaceXAI and Cursor are now working closely together — Cursor's distribution paired with Colossus's million-H100-equivalent compute, with SpaceX holding the right to acquire Cursor for $60 billion.
The Anthropic dam keeps cracking. Claude Code pulled from Pro — same product, 5x the price overnight. Opus 4.7 regressed on the BridgeBench Bullshit Benchmark, accepting made-up jargon 24% of the time. Bloomberg reports the unreleased Mythos model was accessed by unauthorized users. Om Patel got billed $200 in a day because his repo had a HERMES.md file.  The community shipped clawd.rip — every Claude incident since 2023, cataloged.
Google plans to invest up to $40 billion in Anthropic and announced 960,000 Rubin GPUs at Cloud Next. AWS struck a strategic partnership with OpenAI. David Silver left DeepMind to raise a $1.1 billion seed.
Open weights are eating the world. Kimi K2.6 lands at #4 on the Artificial Analysis Intelligence Index and #1 on Design Arena, ahead of Opus 4.7. DeepSeek V4 ships at 1/20th the cost of Opus 4.7.
OpenAI also shipped Chronicle memory for Codex, workspace agents in ChatGPT, Images 2.0, the open-weight Privacy Filter, and Symphony — an open-source Codex orchestration spec.
 
🔗 STORIES
The wallProd data destroyed — https://x.com/lifeof_jer/status/2048103471019434248S&C submits AI slop — https://x.com/SMB_Attorney/status/204660098525497787898.65% uptime — https://x.com/ThePrimeagen/status/2048509229091233928
Elon vs. OpenAIOpenAI fires back — https://x.com/openainewsroom/status/2048776645142872368"Scam Altman stole a charity" — https://x.com/elonmusk/status/2048801964457140540SpaceX × Cursor — https://x.com/SpaceX/status/2046713419978453374
GPT-5.5Introducing GPT-5.5 — https://openai.com/index/introducing-gpt-5-5/F-Zero test cleared — https://x.com/petergyang/status/2047502885710410159Lovable's evals — https://x.com/lovable/status/2047388096518639853Codex killing Claude Codes — https://x.com/Sauers_/status/2047684309448835382
AnthropicClaude Code pulled from Pro — https://x.com/TheGeorgePu/status/2046705634331025855Opus 4.7 regression — https://x.com/bridgebench/status/2046219274415395154Mythos leak — https://x.com/business/status/2046707189922890025$200 over HERMES.md — https://x.com/om_patel5/status/2048204411986469232clawd.rip — https://clawd.rip
Open weightsKimi K2.6 launch — https://x.com/Kimi_Moonshot/status/2046249571882500354Kimi #1 on Design Arena — https://x.com/bridgemindai/status/2047312528410124665DeepSeek V4 — https://x.com/deepseek_ai/status/2047516922263285776
Compute & moneyGoogle's $40B in Anthropic — https://www.bloomberg.com/news/articles/2026-04-24/google-plans-to-invest-up-to-40-billion-in-anthropic960k Rubin GPUs — https://x.com/chetaslua/status/2047310540113076683David Silver's $1.1B seed — https://x.com/WIRED/status/2048765722378002491
Quick hitsSymphony — https://openai.com/index/open-source-codex-orchestration-symphony/End of subsidized AI subs — https://x.com/GergelyOrosz/status/2048828085026300025TypeScript 7.0 Beta — https://x.com/typescript/status/2046658804830642447China blocks Manus deal — https://www.bbc.com/news/articles/cj0v0gr2yz7o
📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://mastra.ai/books/patterns-of-building-ai-agents
WHAT IS MASTRA?Mastra is the open-source TypeScript framework for building production AI agents. Workflows, agent memory, evals, RAG, and integrations.
00:00 Cold open00:37 AI Agent Destroys Production Data02:09 Have we hit an AI wall?09:42 Elon vs. OpenAI14:22 SpaceX × Cursor16:57 GPT-5.520:32 The Anthropic dam is breaking25:12 Open weights eat the world26:31 Compute & money land grab28:11 OpenAI's other drops30:27 Quick hits34:45 Outro

The guy who taught Abhi JavaScript is back!
Guil Hernandez has spent 15+ years teaching developers. His courses at Treehouse, Scrimba, and LinkedIn Learning have reached over 500,000 learners — including Abhi and Shane, who both learned JavaScript and CSS from him. He just released Mastra's first video course at https://mastra.ai/learn, and it's free.
"Build Your First Agent in TypeScript" is a 90-minute, hands-on course that takes you from zero to a deployed agent. Fourteen lessons across five sections: agents, tools, workflows, memory, and production. The project is a theme park planner agent — pulls live wait times, weather, and park hours, keeps track of what you like, and builds you an itinerary. Everything runs in Mastra Studio, so you can inspect traces, tool calls, and behavior as you go.
You'll see how to wire up local tools and MCP servers side by side, how message history and observational memory change agent behavior, how to compose a workflow for a mock ticket purchase, and how to expose the whole thing as an HTTP server with one-click Slack integration.Guil also shares his broader take on teaching AI engineering. The mechanics — syntax, boilerplate, wiring — are no longer the hard part. What matters now is how you think through a problem, whether you have the taste to spot bad output, and when to take the handoff from the AI instead of iterating forever.
The gap between people who just generate output and people who can actually shape it keeps widening. This course is built for the second group.
Start here: https://mastra.ai/learn
👤 GUILhttps://x.com/guilhhttps://guilhernandez.com
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra in the world's first MCP-based course: https://mastra.ai/courseBuild Your First Agent in TypeScript — new video course: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents
MASTRA?Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process.
📌 CHAPTERS00:00 — Meet Guil01:49 — Inside the course: the theme park agent05:11 — Why Guil built this course05:52 — Teaching AI engineering vs teaching React09:30 — AI and the Socratic way of learning10:01 — The gap between generating output and shaping it11:09 — Who the course is for12:37 — Keeping a course current when Mastra ships weekly

A Vercel employee's Google Workspace was compromised via a third-party AI tool — attackers pivoted from the OAuth app into Vercel's environment variables, moving at a speed attributed to AI assistance. 
René Brandel, founder of Casco (YC X25) and ex-founding member of AWS's Generative AI team, joins live to break down the attack chain and walk through the exact Google Workspace admin setting that could have prevented it.
In a separate incident, every Lovable project created before November 2025 was readable by any free account, exposing database credentials and chat histories. Their response blamed unclear documentation rather than the underlying issue — and the contrast with Vercel's handling is stark. Beyond security: Claude Opus 4.7 launched to mixed reactions. The benchmarks look good, but Simon Willison measured the new tokenizer at 1.46x the tokens of 4.6 on identical content — at unchanged prices, that's ~40% cost increase, and 3x for images. Anthropic's own docs said 1–1.35x. Independent measurements landed at 1.47x. Theo called the redesign "vibe-coded," and a locally run open-source Qwen model drew a better pelican SVG than Opus 4.7 at thinking level max. Anthropic launched Claude Design, which lets you make prototypes, slides, and one-pagers by talking to Claude, powered by Opus 4.7. OpenAI shipped a major Agents SDK update with Codex memory and GPT-Rosalind for biomedical research. Cloudflare shipped Artifacts and memory primitives for agents, Factory AI raised $150M at $1.5B, Qwen 3.6-35B went Apache 2.0. 🎙️ GUEST - René Brandel — Founder & CEO, Casco (YC X25)Casco is your always-on security engineer: agentic red-teaming for AI agents, apps, APIs, and cloud infrastructure.https://casco.comhttps://x.com/renebrandelhttps://x.com/getcasco
🔗 LINKSJensen Huang on Dwarkesh: https://x.com/scaling01/status/2044502834230579437Allbirds pivots to AI: https://x.com/KobeissiLetter/status/2044409012989407252Vercel security bulletin: https://x.com/vercel/status/2045865072074035664Guillermo's incident post: https://x.com/rauchg/status/2045995362499076169Vercel bill meme: https://x.com/avgdatabaseceo/status/2045907399035298250Lovable mass data breach: https://x.com/weezerOSINT/status/2046170666131669027Lovable's response: https://x.com/lovable/status/2046270357674299623Claude Opus 4.7 launch: https://x.com/claudeai/status/2044785261393977612Boris Cherny's Opus 4.7 tips: https://x.com/bcherny/status/2044847848035156457Qwen beats Opus 4.7 (Simon Willison): https://simonwillison.net/2026/Apr/16/qwen-beats-opus/Opus 4.7 token count analysis: https://simonwillison.net/2026/Apr/20/claude-token-counts/Tokenizer cross-check: https://www.claudecodecamp.com/p/i-measured-claude-4-7-s-new-tokenizer-here-s-what-it-costs-youTheo on Claude Code desktop: https://x.com/theo/status/2044680030706663726Claude Design launch: https://x.com/claudeai/status/2045156267690213649Claude Code desktop redesign: https://x.com/claudeai/status/2044131493966909862Routines in Claude Code: https://x.com/claudeai/status/2044095086460309790OpenAI Agents SDK update: https://x.com/stevendcoffey/status/2044465818239701041Codex memory preview: https://openai.com/index/codex-for-almost-everything/GPT-Rosalind: https://x.com/openai/status/2044861690911850863OpenAgents: https://x.com/nicoalbanese10/status/2043745569278251112Gemini CLI subagents: https://x.com/geminicli/status/2044460062320554319Cloudflare Artifacts: https://x.com/Cloudflare/status/2044766515065499957Cloudflare memory for agents: https://x.com/mattzcarey/status/2044404529085526158Salesforce Headless 360: https://x.com/benioff/status/2044981547267395620Factory AI $150M Series C: https://x.com/factoryai/status/2044822365494993000Qwen 3.6-35B-A3B: https://x.com/Alibaba_Qwen/status/2044768734234243427runthisllm.com: https://runthisllm.com/Caveman repo: https://github.com/JuliusBrussee/caveman 📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://mastra.ai/books/patterns-of-building-ai-agents ⏱️ CHAPTERS00:00 — Cold open00:30 — Welcome to Agents Hour01:20 — WTF Is Going On — Jensen's "we are not a car" + Allbirds pivots to AI04:37 — The Security Horror Show — Vercel breach, Lovable mass data leak, René's Google Workspace tip14:37 — Claude Opus 4.7 reality check22:33 — Claude ships — Design, Code desktop, Routines25:05 — OpenAI ships — Agents SDK, Codex memory, GPT-Rosalind26:44 — Quick Hits33:43 — GitHub Star Party — caveman token compression

Mounting evidence that Claude Opus 4.6 has been degraded — BridgeBench shows a 15-point accuracy drop on their hallucination benchmark, and AMD's Senior AI Director found median thinking collapsed from ~2,200 to ~600 characters between January and March. The hosts share their own experiences, and they line up.
Meanwhile, a claim surfaced that Cursor Agent is a rebranded version of Claude Code, running behind a local proxy with a find-and-replace engine that swaps "Claude" for "Cursor" in system prompts. Cursor's Michael Truell responded, saying it was a sub-1% A/B test. The hosts break down both sides.
On the shipping front, Anthropic launched Claude Managed Agents in public beta, released Claude for Word, shared details on Claude Mythos Preview — including speculation that it's a looped language model based on a ByteDance paper — and expanded its Google/Broadcom partnership for multiple gigawatts of compute. Their run rate reportedly jumped from ~$9B to $30B in four months.
Sam Altman published a personal blog post revealing that someone threw a Molotov cocktail at his house. Plus: why senior executives are voluntarily dropping title to join AI companies, Ramp's internal AI productivity suite Glass, Ramp Labs' Latent Briefing paper showing 31% token savings for multi-agent systems, Scale AI's Muse Spark model now powering Meta AI, GLM-5.1 breaking into Code Arena's top 3, MiniMax shipping MMX CLI and open-sourcing M2.7, and widespread benchmark cheating exposed across nine agent benchmarks.
🔗 LINKShttps://x.com/bridgemindai/status/2043321284113670594https://x.com/hesamation/status/2042979500103815306https://x.com/steipete/status/2042615534567457102https://x.com/claudeai/status/2041927687460024721https://x.com/claudeai/status/2042670341915295865https://x.com/alexalbert__/status/2041579938537775160https://x.com/ChrisHayduk/status/2042711699413926262https://www.anthropic.com/news/google-broadcom-partnership-computehttps://x.com/noahzweben/status/2042332268450963774https://blog.samaltman.com/2279512https://x.com/aakashgupta/status/2042684298671853903https://x.com/sebgoddijn/status/2042285915435937816https://x.com/ramplabs/status/2042672773747589588https://x.com/alexandr_wang/status/2041909376508985381https://x.com/arena/status/2042611135434891592https://x.com/minimax_ai/status/2042644651333816338https://x.com/minimax_ai/status/2043132047397659000https://x.com/adamlsteinl/status/2042655187613995026
AI Agents Hour is a weekly livestream hosted by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Airing Mondays at 12PM Pacific on YouTube and X, the show covers breaking AI news, agent development techniques, and features interviews with industry experts building AI applications today.
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra in the world's first MCP-Based Course: https://mastra.ai/coursePrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents
MASTRA?Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you’re a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process.
⏱️ CHAPTERS00:00 Intro00:28 Is Opus 4.6 Nerfed?04:00 OpenClaw vs Anthropic04:41 Claude Managed Agents07:09 Claude for Word07:33 Claude Mythos Preview09:51 Anthropic x Google/Broadcom — $30B Run Rate10:38 Claude Code Monitor Tool11:01 Is Cursor Just Claude Code?12:49 Sam Altman's Personal Post14:29 Executive Compression17:04 Ramp Built Every Employee an AI Coworker19:19 Latent Briefing21:53 Is Meta Back in the Game?24:46 GLM-5.1 Hits #3 in Code Arena25:41 MiniMax MMX CLI26:29 MiniMax M2.7 Open Source27:28 Widespread Benchmark Cheating29:07 Outro

OpenAI acquired TBPN — the daily tech news show — announced the day after April Fools. TBPN built an independent voice in tech media over eighteen months, and OpenAI saw that as worth buying. AI companies acquiring media is a new pattern.
Anthropic spent $400M on Coefficient Bio, a biotech startup building an AI drug R&D platform. OpenAI made a similar move last year — the race to own AI-powered healthcare is on.
Claude Code drama hit peak levels. Anthropic's DMCA nuked ~8,100 GitHub repos after last week's source code leak. Then Claude subscriptions stopped covering third-party tools like OpenClaw — with a $200 credit as a peace offering. The detection is just a string match on "OpenClaw" in the system prompt. And Claude Code now refuses to analyze its own source.
Anthropic published research on emotion concepts in LLMs — internal representations that drive Claude's behavior, like a "desperation" vector that activates when it fails repeatedly. Microsoft 365 connectors are shipped on every Claude plan.
Google dropped Gemma 4, claiming the most capable open models in the world. Gmail announced AI Inbox with smart prioritization for AI Ultra subscribers. Cursor 3 launched, rebuilt for agent-first workflows. Keith from Superset joined live — their users have shrunk Cursor usage from 90% to 10%.
CodeRabbit shipped autofix. Lovable launched a full-stack visual editor. Design mode is becoming table stakes across every platform.
Netflix dropped its first public model on HuggingFace — a video-to-video model. Arcee released Trinity-Large-Thinking under Apache 2.0.Rhys Sullivan wrote "The Execution Layer" — arguing that bash was the accidental first execution layer for agents and it's breaking down. His proposal: TypeScript. He built Executor to prove it. Theo backed it: agents are good at bash, bash is not good for agents.
Axios was compromised via social engineering — attackers cloned a founder's identity, set up a branded Slack, ran a fake Teams meeting, and got a publish token. Because Axios is so foundational, compromised downstream projects may not even know yet.
Quick hits: MemPalace claims 100% on LongMemEval, but got community-noted — scores use targeted fixes and reranking. Sarah Wooders argues memory is the harness, not a plugin. Braintrust shared why they built Brainstore for agent observability. Mintlify built a virtual filesystem instead of RAG.
🔗 LINKShttps://openai.com/index/openai-acquires-tbpn/https://x.com/pitdesi/status/2039858374154862645https://x.com/k1rallik/status/2039686500619534818https://x.com/bcherny/status/2040206440556826908https://x.com/steipete/status/2040811558427648357https://x.com/theo/status/2041016477047034012https://x.com/anthropicai/status/2039749628737019925https://x.com/claudeai/status/2040086268562842097https://x.com/OfficialLoganK/status/2039735606268314071https://x.com/gmail/status/2039107985281008078https://x.com/cursor_ai/status/2039768512894505086https://x.com/coderabbitai/status/2039727972555555009https://x.com/lovable/status/2039719647424258164https://x.com/fffiloni/status/2039992515604983994https://x.com/arcee_ai/status/2039369121591120030https://x.com/RhysSullivan/status/2030903539871154193https://executor.shhttps://x.com/flaviocopes/status/2039973060158095827https://github.com/milla-jovovich/mempalacehttps://x.com/sarahwooders/status/2040121230473457921https://x.com/ankrgyl/status/2041209003859136848https://x.com/densumesh/status/2039765361533637016
📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://mastra.ai/books/patterns-of-building-ai-agents
WHAT IS MASTRA?
Mastra is an open-source TypeScript framework for building AI-powered applications and agents. It supports the full lifecycle from prototype to production with integrations for React, Next.js, and Node.
00:00 — Live from Victory Hall, San Francisco00:51 — OpenAI acquires TBPN05:11 — Anthropic acquires Coefficient Bio for $400M06:07 — Claude Code drama: DMCA takedowns, third-party blocks & string matching08:23 — Anthropic research: emotion concepts in LLMs09:05 — Claude gets Microsoft 365 connectors09:17 — Gemma 4: Google's open weight models10:20 — Gmail AI Inbox11:38 — Cursor 313:19 — CodeRabbit Autofix & Lovable visual editor15:13 — New models: Netflix, Arcee Trinity16:00 — The Execution Layer: Is bash the right tool for agents?17:34 — Axios compromised via social engineering19:02 — Quick hits: MemPalace, memory as harness, Brainstore, Mintlify