How Maestro + AgentSH Bring Execution-Layer Security (ELS) to App Factories

There’s a running joke in the AI agent world:

“I told the LLM not to delete anything important. It understood perfectly. Then it deleted everything important.”

It’s funny because it’s true. And it’s true because we keep making the same mistake: treating instructions in context like security controls.

But the instruction layer isn’t a safety boundary. It’s content inside a moving context window. Rules get truncated, summarized away, retrieved incorrectly, or overridden by prompt injection and tail-risk behavior.

Today we’re excited to announce the first general release of Maestro App Factory.

Maestro App Factory is a framework for building, composing, and operating AI-native applications by organizing models into structured, collaborative teams rather than treating a single model or agent as the system.

You can find the repository here: https://github.com/SnapdragonPartners/maestro

The Big Idea Behind Maestro

Large language models are trained on human artifacts and exhibit recognizably human behaviors: reasoning, creativity, bias, blind spots, and occasional overconfidence.

How different approaches to the “context problem” reveal fundamental trade-offs in AI system design

The context window limitation of large language models has spawned an entire subfield of research. How do you get an LLM to reason about information that doesn’t fit in its working memory? A recent paper on Recursive Language Models (RLMs) proposes an elegant solution: let the model recursively examine and decompose long inputs. Meanwhile, in the trenches of building production AI coding agents, we’ve taken a completely different path with “knowledge packs”—curated, graph-structured knowledge delivered at exactly the right moment.