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.
Microsoft cancels Claude Code licences, mandates GitHub Copilot CLI by June 30
Microsoft's Experiences & Devices division (Windows, M365, Teams, Surface) is dropping Claude Code by June 30 due to token-cost overruns, redirecting engineers to GitHub Copilot CLI. Anthropic models remain accessible as a Copilot backend.
read →Microsoft Execution Containers (MXC): policy-driven sandboxing for Windows AI agents
MXC gives IT admins granular control over what files, network endpoints, and apps each AI agent can access on Windows — addressing enterprise security concerns for agentic workloads.
read →GitHub Copilot CLI adds rubber-duck debugger, prompt scheduling, and voice input
Copilot CLI's June 2 changelog brings a rubber-duck debugging agent, prompt scheduling, and voice input — narrowing the gap with Claude Code as Microsoft pushes internal adoption.
read →Hermes Agent v0.16.0 "The Surface Release"
Newest tagged Hermes Agent release (v2026.6.5); same-day follow-up commits add a cron-sessions sidebar and desktop/Electron bootstrap fixes.
read →OpenClaw v2026.6.5-beta.1 released
New beta fixes iMessage frame RPC framing, codex completion timeout diagnostics, provider-throttled cross-OS agent turn retries, plugin registry fingerprint hardening, and OpenAI audio API key auth.
read →OpenAI Dreaming V3: ChatGPT gets self-updating persistent memory
OpenAI replaced ChatGPT's manual saved-memories with Dreaming V3 — an autonomous background system that synthesises and self-updates memories over time. Factual recall jumped to 82.8% (from 41.5% in 2024). Live for Plus/Pro US now; free tier coming.
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