DreTech.ai
Architecting the Agentic Enterprise
DreTech.ai builds the loop that trains agents: a tool-portable Agent OS that defines what an agent is, and Personal OS Studio, a macOS trainer that compiles it into live harnesses, measures how they behave, and refines the spec.
New portfolio-advisor, an open-source agent for Claude and ChatGPT that reviews your own portfolio →
Thesis
AI-native architecture is not optional
Most enterprise AI efforts bolt models onto legacy workflows. Copilots assist. Wrappers abstract. But none of them restructure. The next generation of enterprise systems must be designed from the ground up — with agency, context, and autonomy as first-class primitives.
Beyond copilots
Copilots are a transitional pattern. They optimize human workflows without changing the underlying architecture. Agentic systems operate independently within defined constraints, executing multi-step reasoning across organizational boundaries.
Beyond wrappers
API wrappers commoditize model access but add no structural intelligence. Real enterprise AI requires orchestration layers that manage state, enforce policy, and route context — not just forward prompts.
Context as infrastructure
Enterprise decisions depend on context that lives across systems, teams, and timelines. An agentic enterprise treats context as a first-class infrastructure layer — indexed, versioned, and accessible to autonomous agents.
Architecture over automation
Automation replaces tasks. Architecture replaces paradigms. DreTech.ai focuses on the structural patterns that make autonomous enterprise systems reliable, auditable, and composable at scale.
Focus Areas
Core build areas
Each focus area maps to a concrete system under active development — and to the training loop that ties them together.
01
Portable Agent Definitions
The Agent OS — a tool-portable system of Markdown files defining an agent's identity, context, skills, memory, and connections. Canonical source lives once; per-tool adapters compile it for Codex, Claude Code, OpenClaw, and others.
02
AI Harness Training
Shipped: Personal OS Studio, a native macOS app that compiles Agent OS definitions into live harnesses — OpenClaw, Hermes, Codex, Claude Cowork — authors, validates, versions, and vaults them, harvests runtime learning back, measures compiled behavior with an evals layer, and shares the enterprise-grade parts through a curated team library. The loop is closed — and now it scales beyond one person. Open source (Apache-2.0) at github.com/dretech-ai/personal-os-studio.
Current Direction
Training the harness
Personal OS Studio closes the loop between the spec and the tools that run it — compile → measure → refine is complete and in daily use.
The Agent OS already captures what an agent should be — identity, context, skills, memory, and connections — in tool-neutral Markdown. The tools that run agents — OpenClaw, Hermes, Codex, Claude Cowork — each read their own instruction format.
Personal OS Studio is the connector, shipped as a native macOS app with its full roadmap complete. A pluggable adapter framework compiles canonical definitions into the exact files each harness reads — OpenClaw workspaces, Hermes instruction files, Codex's repo-scoped AGENTS.md, Claude Cowork paste blocks — with data designations (PII / Enterprise / Public) enforced at every destination. The definitions are authored by agent interview, validated against their schema checklists, versioned with diff review, and protected by an encrypted vault for the PII that deliberately never enters git. And the return arc is live: harness drift flows back as human-reviewed canonical proposals, while an evals layer — cases generated from the spec itself, deterministic assertions before an LLM judge, regression history, failures feeding refine interviews — turns the written specification into measured, reliable behavior. The loop in the diagram above is no longer aspiration; it's the product.
Built in public. Every entry on the Lab reflects an active line of work — refined through iteration, not theory.