My Name Is Alex
A personal, music-driven introduction to the builder behind the work.
Alex Merced on agentic AI
AI should be open to inspection.
I build open tools, specifications, and ideas for agentic systems that people can understand, govern, and move.
WATCH / THREE ORIGINAL FILMS
Three scene-rich music videos connect the person, the agentic platform, and the open lakehouse underneath modern AI.
A personal, music-driven introduction to the builder behind the work.
Composable agents, inspectable authority, model choice, and portable execution.
The open data foundation that makes governed analytics and AI possible.
THE THESIS
“The future of agentic AI is not one model, one agent, or one platform. It is replaceable components connected by open contracts.”
INSTALL AND RUN
Tools for brokerage, execution, memory, and governance. Every card shows the real package name, the version on the registry when this site was built, the license, and where the source lives. Each one has a full explainer in the knowledge base.
One portable agent identity across the harnesses you already use, with honest reports of what each one drops.
The governed agent harness for data and platform teams: verified identity, tamper-evident audit, lakehouse-native tools.
The memory-first personal agent: it remembers you across sessions, in Git-backed Markdown you can review.
The desktop cockpit for MagAgent: runs, approvals, graphs, and memory in one window.
Install: desktop app for macOS, Windows, and Linux, not published to npm. Latest release v1.0.0: download from GitHub releases ↗
A graph-shaped memory layer written in Rust, with Python bindings, for relationships, context, and retrieval paths.
OPEN SPECIFICATIONS
Each specification has two version numbers: the version of the specification document, and the version of the support libraries that parse and validate it. The document changes rarely. The libraries release more often.
Portable graph-shaped work with explicit tools, policy, budgets, and success criteria.
Specification: 1.0. Support libraries: PyPI 1.0.4, npm 1.0.4.
Portable agent identity, capabilities, authority, preferences, and state.
Specification: 1.0. Support libraries: PyPI 1.0.5, npm 1.0.5.
Exact, durable approval requests and decisions across CLI, web, desktop, and policy services.
Specification: 1.0 release candidate. Support libraries: PyPI 0.2.0, npm 0.1.0.
WHERE THE CODE LIVES
Alex’s personal account since 2019. It holds hundreds of older projects, learning repos, and experiments. It is also home to Merced AI, MagAgent, Mag Command Center, MagGraph, and Agentic Graph Specification.
A separate GitHub organization for open-source agent tools and specs, kept apart from the personal account. It holds Loro, Open Agent Profile, and Agent Approval Interchange Specification.
The cards above name the owner of each repository, so every install badge and stars count points at the right place.
OPEN CONTRACTS
Open software is strongest when components share durable languages for work, identity, and human authorization.
Read about open contracts →Portable graph-shaped work with explicit tools, policy, budgets, and success criteria.
Portable agent identity, capabilities, authority, preferences, and state.
Exact, durable approval requests and decisions across CLI, web, desktop, and policy services.
DESIGN PRINCIPLES
Agents, profiles, and workflows should move without being rebuilt around a single vendor.
An agent should know what it may do, what requires approval, and where its responsibility ends.
Memory, context, and execution history should be understandable rather than trapped behind a magic interface.
Useful autonomy comes from traceable decisions, observable work, and verifiable outcomes.
THE AI BOOKSHELF / 31 TITLES
Explore Alex Merced’s nonfiction books on AI engineering, agentic systems, governance, evaluation, open models, semantic context, and the data foundations beneath modern AI.
Browse the complete book catalog ↗
01A comprehensive guide to lakehouse architecture and AI.
About the book ↗
02Foundations of agentic data architecture.
About the book ↗
03Building AI-ready lakehouse systems.
About the book ↗
04A practical guide to AI-driven workflows.
About the book ↗
05A full-stack reference for AI systems.
About the book ↗
06Designing data platforms for LLMs, agents, and RAG.
About the book ↗
07Prompt engineering and agent workflows.
About the book ↗
08Connecting structured enterprise data to agentic systems.
About the book ↗
09Deploying AI agents across the modern organization.
About the book ↗
10Building the context and meaning agents need.
About the book ↗
11Testing LLMs, RAG, and agents.
About the book ↗
12Disruption, adaptation, and the changing labor market.
About the book ↗
13Practical approaches to accountable AI governance.
About the book ↗
14Taking AI from prototype to production systems.
About the book ↗
15Graphs, RAG, memory, and context.
About the book ↗
16Architecting data platforms for AI.
About the book ↗
17Patterns for building intelligent systems.
About the book ↗
18Cost, latency, and infrastructure tradeoffs.
About the book ↗
19Everyday AI tools explained without technical jargon.
About the book ↗
20Portable lakehouse architecture with open catalogs and agents.
About the book ↗
21Gemini, NotebookLM, Veo, Gemini Spark, and Jules.
About the book ↗
22Open models with OpenCode, Pi, and Hermes.
About the book ↗
23Claude.ai, Claude Code, and Claude Dispatch.
About the book ↗
24Building documents, media, websites, and applications with Codex.
About the book ↗
25SQL analytics, BI, and agentic AI for modern data platforms.
About the book ↗
26Modern data systems, engineering, analytics, and AI.
About the book ↗
27Providing meaning and context for AI.
About the book ↗
28A practical guide to building multi-agent systems.
About the book ↗
29From laptop prototypes to enterprise-scale agentic AI.
About the book ↗
30Grok, Cursor, MCP, and local-model development workflows.
About the book ↗
31The Microsoft Copilot and GitHub Copilot ecosystem.
About the book ↗Scroll to explore all 31 titles →
ABOUT ALEX
Alex Merced works across data infrastructure, developer education, and agentic AI. His focus is making complex systems legible, and giving builders open foundations they can adapt, audit, and own.