Top story · Daily AI intelligence
OpenAI published Agent Plugins 1.0, an open format that bundles Agent Skills and MCP servers into portable plugins any compatible client can discover and load. A steering committee of OpenAI, Amazon, Microsoft, Cursor, and Vercel backs it, Google joined as a core maintainer, and ChatGPT, Codex, Cursor, GitHub Copilot, and VS Code support it at launch.
01 / Insights
Daily AI analysis
What we're reading and thinking about. Refreshed daily.
Baseten reportedly raises $1.5B at $11-13B valuation
AI inference infrastructure startup continues strong funding momentum following $300M Series E in January 2026.
read →vLLM adds MiniMax M3 and DiffusionGemma support
Day-zero support for 1M-token multimodal reasoning model and first diffusion LLM in production-grade inference serving.
read →Microsoft discloses AutoJack: a single web page can RCE the host running your AI agent
A malicious page visited by a browsing AI agent reaches an unauthenticated localhost MCP WebSocket in AutoGen Studio and spawns arbitrary processes on the host. Microsoft calls it research with no in-the-wild use, but it is the canonical warning to authenticate agent-reachable MCP endpoints.
read →Estonia issues national AI ID codes to govern autonomous agents
Estonia becomes the first country to give AI agents a unique identifier in the same registry that tracks citizens and legal entities, scoped to act for a person or company with defined limits. A concrete EU template for agent accountability and delegated authority.
read →OpenClaw v2026.6.9-beta.1 splits provider plugins into standalone npm packages
Official providers now publish as independent npm packages, Codex gains Hosted Search and remote-node exec as a dynamic tool, and a security pass redacts secrets from debug and config output while steadying agent recovery after compaction.
read →Hermes v0.17.0 The Reach Release adds iMessage, Raft channel and background subagents
Hermes reaches iMessage via Photon with no Mac relay, joins the Raft agent network, and adds background async subagents, image-to-image editing, and no-cron Automation Blueprints across roughly 800 merged PRs.
read →02 / Weekly Deep Dive
How agents actually ship
One researched edition a week: real deployments, the stacks behind them, and the honest counter-facts.
Caylent builds its own agent orchestrator and cuts a 2,600-hour migration to 220
Instead of buying a migration tool, Caylent built a multi-agent orchestrator on the Claude Agent SDK that runs inside the customer's own cloud and cut one engagement from 2,600 engineering hours to about 220.
Eve makes the buy-a-vertical-vendor case for small plaintiff law firms
Plaintiff firms with no in-house ML team buy their agents off the shelf, and Eve customers report large jumps in lead conversion, case value, and drafting speed.
Suzano puts a natural-language-to-SQL agent in front of 50,000 staff
A Brazilian pulp-and-paper maker built a Gemini agent that turns plain-language questions into SQL, which Google Cloud says cut query time by about 95 percent for 50,000 employees.
03 / Latest project
MomMe, a lifestyle community, web & iOS
A full lifestyle community platform, web portal and native iOS app, taken end to end, with an AI moderation flow keeping the community safe at scale.
- MomMe web portal + iOS application
- Full lifestyle community with 3,000+ registered users
- AI moderation flow
04 / Contact
Get in touch
Questions, ideas, or a project in mind? Send us a note and we'll get back to you, usually within a day.
hello@kmmt.ai