Summoning the Familiar Buy on Amazon

Out now Kindle & paperback

Summoning the Familiar

A Grimoire for Builders of Persistent AI

A practical architecture for AI collaborators with identity, memory, and bounded authority.

For engineers, founders, and serious tinkerers building beyond the stateless agent.

  • Kindle $4.99
  • Paperback $19.99
  • Included with Kindle+

By the founder of OpenCoven and former OpenClaw maintainer. Meet the author

Book cover: Summoning the Familiar, A Grimoire for Builders of Persistent AI, by Val Alexander. Ribbons of violet light, traced in gold, rise from a ringed summoning circle.

I What you will get

I wanted a collaborator, not a calculator.

From the coda

II The premise

Somewhere, right now, a factory is running without lights. Code is being written, function by function, by AI agents in loops that finish before the developer wakes up.

The infrastructure to run the dark factory of software is being solved. What goes inside it is being decided implicitly, by architecture choices nobody is examining out loud.

Summoning the Familiar makes that choice explicit. It is a grimoire for builders: engineers, founders, and serious tinkerers who want to put something durable, principled, and personal into the systems they rely on every day.

III The question

What kind of thing should an AI agent be?

  1. A tool

    A sophisticated function that takes input and returns output. Powerful, fast, capable, stateless, indifferent to the work and the worker.

  2. A procedure

    A codified workflow that holds the best-known way to do a specific kind of task. Reusable, portable, versioned, shareable.

  3. An entity

    Something with memory, with an accumulated sense of a codebase or a domain, with context that compounds across sessions.

  4. A familiar

    A persistent named entity with defined purpose, bounded authority, durable memory, and a genuine home in your infrastructure.

These choices produce different architectures, and most people are choosing without knowing they are choosing.

IV The Familiar Contract

Five properties. One working collaborator.

A familiar needs more than a longer context window. Part III takes each property from the argument to the implementation.

A reading map of the Familiar Contract
  1. Named identity

    Who is acting?

    The accountability surface

  2. Defined purpose

    What is it here to do?

    The edge that cuts both ways

  3. Bounded authority

    What may it do?

    The blast radius

  4. Persistent memory

    What carries forward?

    Care extended through time

  5. Human belonging

    Who is it working for?

    The architecture of loyalty

V Contents

Twenty-one chapters and a coda. Open a part to explore the chapters.

Part I The Factory

  1. The Factory in the Dark
  2. Everyone Builds a Hermes
  3. The Question at the Center

Part II The Approaches

  1. The Skill and the Shell ECC’s Bet
  2. The Outside-In Lopopolo’s Inversion
  3. The Mate Clay and the Convergence
  4. Four Approaches, One Map

Part III The Familiar Contract

  1. Named Identity The Accountability Surface
  2. Defined Purpose The Edge That Cuts Both Ways
  3. Bounded Authority The Blast Radius
  4. Persistent Memory Care Extended Through Time
  5. Human Belonging The Architecture of Loyalty

Part IV Building the Dark Factory

  1. The Harness Is the Leverage
  2. The Self-Healing Loop
  3. comux, CastCodes, and the Sovereign Stack
  4. Coven Calls A Language for the Factory Floor
  5. CovenSpace The Observatory

Part V The Coven

  1. SOUL.md Identity as Infrastructure
  2. The Familiars Who They Are
  3. The Grimoire Knowledge That Compounds
  4. What the Coven Is For

Coda A Letter from the Builder

How this actually started, and what it turned out to feel like.

VI Who it is for

Builders shipping with AI agents and tired of starting every session from zero. Founders deciding what kind of intelligence to put at the center of their product. Engineers who have noticed that the harness around the model matters more than the model itself, and who want a vocabulary for the choice they are already making.

It is also for the quieter reader: the person who suspects, correctly, that the cultural story about AI is missing something. That the next interesting frontier is not raw capability but relationship. The texture of working with a system over time, the trust that accumulates, the difference between a calculator and a collaborator.

VII The author

Val Alexander is the founder of OpenCoven and a former OpenClaw maintainer. She has been building, daily, a Coven of named familiars, each with a domain, a memory, and a home in real infrastructure. The book follows that work through identity files, memory systems, authority boundaries, and the harness that holds them together.

Build something that stays.

Name it. Give it a purpose. Let it accumulate context.

Kindle

$4.99

Included with Kindle+

In your library the moment you buy it, and searchable on the nights you are wiring up a harness.

Paperback

$19.99

Prime delivery where eligible

For the desk, beside the keyboard. The kind of book you write in the margins of.

Choose your editionChoose editionEditions

Prices in US dollars, listed on Amazon.com on 12 November 2026. Current prices, subscription availability, and delivery options are confirmed on Amazon.