







I’m thrilled to announce msgvault, a new side project I have been building over the last two months with the assistance of many coding agents and some new agentic engineering tools I created (like roborev, a continuous agentic code review system).
Open Coding Agents: Fast, accessible coding agents that adapt to any repo | Ai2
SERA is the first in our family of Open Coding Agents, achieving state-of-the-art performance at low cost.

Microsoft Agent 365, now generally available, expands capabilities and integrations | Microsoft Security Blog
We’re announcing the general availability of Agent 365, plus previews of new capabilities to discover and manage shadow AI agents. Learn more.

crawshaw - 2026-02-08
I wrote up my experiences programming with LLMs a bit over a year ago, and updated it for the world of agents eight months ago. A lot has changed since then, so here is an update.
User & Agents (@userandagents.org)
We are a community focused on shaping the future of user-agent systems. Our goal is to empower people by designing and building software that provides agency, control, and choice in our digital lives. https://userandagents.org
🚨 AI News | TestingCatalog on Twitter / X
OPENAI 🚨: Early look at an upcoming Agent Studio for building and hosting configurable, always-on 24/7 agents on ChatGPT. The "Hermes" feature is tightly coupled with the existing Workflows builder on the OpenAI Platform, and you will also be able to open your Agents in the… https://t.co/7U4m2vNS3z pic.twitter.com/tfPIGdXRAs— 🚨 AI News | TestingCatalog (@testingcatalog) April 21, 2026
Introducing MAI-Cyber-1-Flash inside MDASH | Microsoft AI
Today we’re announcing MAI-Cyber-1-Flash inside of MDASH, our multi-agent vulnerability identification and remediation harness. Together they deliver world-class performance at 50% of the cost of leading models.

Microsoft Build 2026: Securing code, agents, and models across the development lifecycle | Microsoft Security Blog
Discover how Microsoft enables fast, secure AI development with MDASH and new security capabilities.

ClickHouse welcomes LibreChat: Introducing the open-source Agentic Data Stack | ClickHouse
We are excited to announce that ClickHouse has acquired LibreChat, the leading open-source AI chat platform.

Andrej Karpathy on Twitter / X
Wow, this tweet went very viral!I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the… https://t.co/4UAmYYFzCw— Andrej Karpathy (@karpathy) April 4, 2026
Securing our future: July 2026 progress report on Microsoft's Secure Future Initiative | Microsoft Security Blog
Microsoft’s latest Secure Future Initiative report outlines progress on secure foundations, AI-powered defense, and future-ready cybersecurity.

AgentBox · Free In-Browser AI Agent OS | Strukto
A free, privacy-first in-browser AI agent OS that connects to Google Drive, Dropbox, Slack, GitHub, etc. No server-side data storage.

How to Train Your Agent: Building Reliable Agents with RL — Kyle Corbitt, OpenPipe
Enterprise MCP: lessons from GitHub's MCP server launch
GitHub's Engineer shares lessons from developing GitHub's MCP server. An Arcade MCP MVP interview.

The next user agent
Hey, Rupert here from Unternet. We're building a new, intelligent client for the web — and I'll be posting a little update about our progress here every week.

Our newest project is taking flight: meet codename goose! 🪶 Today, we launched an open source on-machine AI Agent. It’s modular, works with your preferred LLM, and integrates seamlessly with developer tools and other software via MCP. Developers, check it out! block.github.io/goose/blog/2025/01/28/introdu…
Introducing codename goose
block.github.io