NVIDIA just made secure agent runtimes real. Here's why that makes portable proof the next missing layer.
NVIDIA just made something very real. With NemoClaw, the conversation around AI agents shifted. We are no longer only talking about whether agents matter. We are now talking about how to run them …
Read more →Building trust infrastructure for the agentic web
AI agents are starting to act autonomously. They browse the web. They execute code. They manage files. They make API calls. They interact with databases. Some are beginning to hold wallets and …
Read more →A working governance plane for AI agents that integrates with multiple frameworks
Today we shipped an important milestone for Substr8 Labs. A working governance plane for AI agents that integrates with multiple frameworks using MCP. Not a pitch deck. Not a design doc. Actual code …
Read more →A proof-of-concept with running code, real test outputs, and real failures we learned from
We’ve been building something we think the agent ecosystem is missing: A provable lifecycle for AI agents — where identity, capabilities, actions, and memory are auditable and tamper-evident …
Read more →Why we built a unified toolkit for verifiable agent infrastructure
Last week, our AI agent went dark for six hours. Not a crash. Not a network issue. A corrupted context — an orphaned tool call that the API couldn’t parse. The session was bricked. Six hours of …
Read more →We benchmarked lexical (BM25), semantic (embeddings), and hybrid retrieval on agent memory at scale.
There’s a common assumption in AI agent systems: Combining keyword search with embeddings should outperform either alone. We tested that assumption under realistic noise. 30 needles (technical, …
Read more →Introducing Git-Native Agent Memory (GAM): Cryptographically verifiable memory for AI agents
Every AI agent you’ve ever used has the same dirty secret: their memory is unverifiable. When ChatGPT “remembers” something about you, can you: Prove when it learned that fact? See …
Read more →Introducing Agent Capability Control (ACC): Capability-based security for autonomous AI
You gave your AI agent access to: Your email (to send messages for you) Your calendar (to schedule meetings) Your code repos (to write software) Your databases (to query data) Your social media (to …
Read more →Introducing ACC — Agent Capability Control
Your AI agent can post tweets, send emails, and deploy code. But should it? Traditional permission systems were built for humans. Humans who take coffee breaks. Humans who read error messages. Humans …
Read more →The 4-tier verification pipeline that catches malicious code before it runs
Would you let a stranger run code on your computer just because they promised it was safe? That’s what happens every time an AI agent loads a “skill” or “tool” from the …
Read more →Introducing File-Driven Agent Architecture (FDAA)
Today we released our first piece of research: a pattern for building AI agents that are portable, persistent, and provable. We’re calling it File-Driven Agent Architecture. The Problem Most AI …
Read more →Introducing FDAA — File-Driven Agent Architecture
What if everything about your AI agent — its identity, memory, capabilities, and personality — lived in a single folder of markdown files? That’s FDAA. File-Driven Agent Architecture. The …
Read more →Most AI tools suggest. Control Tower builds.
Most AI tools suggest. They advise. They give you a starting point. Control Tower does something different: it builds. This weekend, we shipped a pipeline that takes a plain-English brief and outputs …
Read more →Why I'm betting everything on agents — and why you should pay attention
I drive a bus for a living. And I build AI systems at night. Seven years ago, I did not know what HTML was. I did not know what a landing page was. I did not know what CSS was. I was a blank slate. …
Read more →