Agents Hour

A lot happened in eight days. 

Meta acquired Moltbook, a social network built entirely for AI agents, not humans. 

OpenAI dropped GPT-5.4 Thinking and GPT-5.4 Pro, Codex got forks for multi-agent workflows and Windows support, and there are rumblings of OpenAI building a GitHub alternative. Anthropic fired back hard — multi-agent PR code review for Claude Code, while loops via /loop, the Claude Marketplace, and a way to pull your context from other AI tools. Plus: voice mode for CLI coding is apparently real, and people are using it.

This episode also covers the explosion of coding agents: Theo's T3 Code, OpenAI's Symphony orchestration layer, OpenCode workspaces, and swyx's thesis that this is the Year of the Subagent.

Donald Knuth is making headlines for being impressed by Opus 4.6, solving a long-standing math conjecture.  TypeScript is overtaking Python and JavaScript on GitHub. Gemini 3.1 Flash-Lite drops. AMI raises $1B. 

OpenClaw is getting government-backed adoption in China. Stanford's paper on RAG breaking at 10K documents, Karpathy's autoresearch project, Justin Poehnelt on why your CLI needs to be rewritten for agents. Plus: Raycast Glaze, Google Workspace CLI, Copilot Cowork, Exa Deep, Expo Agent, and a discussion on whether humans should be reviewing code at all.

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 RESOURCES

MASTRA?

CHAPTERS

Ismail Pelaseyed from Superagent is back on Agents Hour, and this time he's talking about something most builders aren't thinking about yet — supply chain attacks on AI agents. Guardrails protect against what you tell your agent to do. But what about everything your agent reads, fetches, and installs on its own? That's the gap Brin is built to fill.

Brin is a free, open-source credit score for agent context. Before your agent acts on an external package, MCP server, skill, or web page, Brin scores it — identity, behavior, and content — and returns a verdict in under 10ms. No signup, no auth, one GET request.

Ismail walks through how supply chain attacks actually work in production, the three-tier scoring model behind Brin, how the Cline NPM incident illustrates exactly this problem, and why securing the context — not the agent — is the right mental model.

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 RESOURCES

MASTRA?

00:00 — From guardrails to supply chain attacks

This week in AI saw geopolitical turmoil, major funding news, and a shift in software development. Missile strikes in the UAE and Bahrain disrupted AWS and Claude services. Meanwhile, after Anthropic banned its models from autonomous weapons and mass surveillance, the Trump administration banned Anthropic from government contracts—posing a major supply chain risk. On the same day, Sam Altman secured a deal with the Department of War as OpenAI announced a $110 billion funding round, highlighting a sharp contrast in approaches.

AI coding is evolving rapidly. Andrej Karpathy noted that coding agents, ineffective before December, now work well with improved quality and coherence. Yet, perfect accuracy remains elusive. New tools emerged: Cursor demos code, Linear markets itself as an AI coding assistant, and Perplexity Computer offers an all-in-one system for managing AI projects. Smaller models like Qwen 3.5 grow faster and more efficient for edge use. Other highlights include Anthropic acquiring Vercept AI, Claude's remote coding controls, and Stanford confirming major AI firms use user conversations to train models.

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 RESOURCES

MASTRA?

CHAPTERS

00:00 – Intro

Yujohn from Mastra explains why datasets and experiments are essential for building production-grade AI agents.

If you're building an agent, you need a way to verify it's working correctly before and after you make changes. Datasets provide that baseline. You create a collection of test cases (ground truth) that represent the scenarios your agent should handle. Then you run experiments: pass each test case through your agent and measure the results. This is error analysis in practice. You start by identifying where your agent fails, then build scorers to quantify those failure modes over time. Smaller teams often ship first and add datasets later, once they have user feedback. Larger teams need them earlier. But eventually, every production agent needs this.

The demo shows how Mastra makes this accessible. You can create datasets through the UI, add items manually or import from CSV, and run experiments with a single click. The results show you exactly what went wrong: which tool calls failed, what the agent output was, and how it compared to ground truth. You can also compare experiments side by side to see if your prompt tweaks actually improved things. And because all the data lives in your own database, you can write your own agents to analyze the results, dig into traces, and iterate. The SDK makes it easy to integrate into CI/CD: run experiments on pull requests, gate deployments on eval scores, or just collect data from production and curate datasets later.

🔗 RESOURCES

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 RESOURCES

MASTRA?

00:00 – Intro

Abhi walks through Mastra Code, a new open-source coding agent with observational memory that compresses context without losing it.

When we built Observational Memory, we needed a way to test it in production. Instead of a standard bot, we dogfooded it: we built a coding agent and used it ourselves. Writing code every day quickly revealed whether the memory actually worked.

Eventually, something clicked. Long, multi-day coding sessions ran smoothly, without hitting the compaction limits that trip up other agents. The agent actually seemed to understand the conversation. That gave us confidence to release Observational Memory... and the agent itself also

The core innovation is the Harness primitive. Rather than just a coding agent, Harness can power any type of agentic workflow: customer support, design tools, electrical engineering, and more.

In this demo, you’ll see the Mastra Code CLI, a production-ready coding agent, and how Corbin from Artifact used the Harness to create an in-app agent for electrical engineering. Same primitive, completely different use case.

🔗 RESOURCES

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 RESOURCES

MASTRA?

CHAPTERS

Shane and Abhi break down the biggest AI news from the past few days. 

Anthropic identified industrial-scale distillation attacks on Claude by DeepSeek, Moonshot AI, and MiniMax. Anthropic also released a groundbreaking report analyzing millions of AI agent interactions using Claude. Software engineering makes up ~50% of all agentic tool calls, but there's emerging use across back office automation, marketing, finance, and more. Claude Code Security launched in a limited research preview.

Stripe is shipping 1,300+ AI-generated PRs per week. And they're made by... Minions?

Code Mode for MCP is becoming a standard part of the MCP ecosystem. Amp claims the coding agent is dead. We also cover skills benchmarks (smaller models with high-quality skills beat raw Opus), trajectory explorer for agent traces, Vercel AI Gateway video support, Taalas custom silicon for AI inference, Google's Pomelli Photoshoot feature, and the GitHub Star Party pick: superpowers framework.

🔗 RESOURCES

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 RESOURCES

MASTRA?

CHAPTERS

Shane and Abhi welcome Charlie Holtz from Conductor to AI Agents Hour. Charlie shares how frustration with managing multiple Claude Code instances led to building Conductor. They discuss Conductor's July 2025 launch as the first agent orchestration Mac app, early design choices, and its impact on the market.

Charlie outlines a future in which agents run 10x longer and require less supervision, along with new tools such as Kanban boards and a CEO dashboard. The conversation covers multi-agent coordination, designing for both humans and AI, and the importance of user feedback.

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.

🧰 RESOURCES MENTIONED

📚 MASTRA RESOURCES

MASTRA?

00:00 Origin Story of Conductor

It's time for another AI News roundup with Shane and Abhi! This week was absolutely massive. Matt Shumer's viral article about AI automation, which describes his own job being automated in real time, has reached 84 million views. Anthropic raised $30 billion at a $380B valuation (one of the largest private raises in tech history). Claude Sonnet 4.6 launched with a 1M token context window. And the Chinese model tsunami is real: Qwen 3.5, GLM 5.0, MiniMax M2.5 (nearly Opus-level at 1/8 the cost), and DeepSeek v4 rumors.

We also cover Google's Gemini 3.1 Pro, WebMCP native browser support in Chrome 146, OpenAI's agent workflow tips, Peter Steinberger joining OpenAI, Lyria 3 music generation, Kimi Claw integration, and the explosion of agent platforms (Oz, Browserbase Functions, and a former GitHub CEO raising $60M for "version control for agents").

Plus: Real production stats from Ramp (57% of merged PRs from background agents), Letta's context repositories, and why Mastra's Observational Memory is becoming the reference implementation for agent memory.

🧰 RESOURCES MENTIONED

Matt Shumer's article: https://x.com/mattshumer_/status/2021256989876109403

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 RESOURCES

MASTRA?

Tyler Barnes, founding engineer at Mastra, introduces Observational Memory. It is a new memory system for AI agents that achieves state-of-the-art results on LongMemEval with a completely stable context window.

Unlike semantic recall (which uses RAG and invalidates prompt caching), Observational Memory compresses conversations into dense observations while maintaining a stable, fully cacheable context.

The result: 94.87% accuracy on LongMemEval with GPT-5 mini. This is the highest score recorded by any memory system to date.

In this conversation, Tyler explains how the system works, why it outperforms raw context, and how you can integrate it into your agents in under 20 minutes. We also dive into the research, the benchmarks, and what's next for Observational Memory.

🧰 RESOURCES MENTIONED

Observational Memory Launch Blog: https://mastra.ai/blog/observational-memory

📚 MASTRA RESOURCES

MASTRA?

00:00 – Intro

Shane and Abhi cover top AI stories. This week was absolutely massive! Anthropic aired Super Bowl ads mocking OpenAI's decision to put ads in ChatGPT, Opus 4.6, and GPT-5.3-Codex launched within 15 minutes of each other, and then ClawHub dropped a bombshell: 11.9% of the entire marketplace is malware.

We cover everything: Anthropic's competitive jabs, the model war benchmarks, Claude's 1M token context, OpenAI's Frontier platform, the security crisis that's reshaping how people think about agent marketplaces, Kimi K2.5's domination on OpenRouter, ElevenLabs' $500M raise at $11B valuation, and the explosion of AI video generation tools.

Plus: Perplexity's Model Council, Roblox 4D generation, Mistral's Voxtral Transcribe 2, and why Swyx finally admits evals actually help. 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.

🧰 RESOURCES MENTIONED Anthropic Super Bowl ads: https://x.com/tomwarren/status/2019039874771550516 Opus 4.6 launch: https://x.com/claudeai/status/2019467372609040752 GPT-5.3-Codex launch: https://x.com/sama/status/2019474754529321247 ClawHub malware report: https://x.com/aakashgupta/status/2019885557221061026 Kimi K2.5 #1 on OpenRouter: https://x.com/openrouterai/status/2020199664746971195 ElevenLabs $500M raise: https://x.com/elevenlabsio/status/2019048384011854087 Perplexity Model Council: https://x.com/perplexity_ai/status/2019444886114824219 📚 MASTRA RESOURCES Mastra: https://mastra.ai Learn Mastra in the world's first MCP-Based Course: https://mastra.ai/course Principles of Building AI Agents (Book): https://mastra.ai/book Patterns 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.