OTACONSKEEP // PUBLIC INDEX STATUS // ACTIVE

Field Dossier // Public Index

Build your own Keep.

Local AI agents that remember, speak, use tools, work together, and run on hardware you control.

Your agents. Your hardware. Your data. Your Keep.

CREATED BY: Antonio G. Garcia · Built for the Keep.

Show me

This is OtaconsKeep

Agents, Codec, KeepRoute, the desk, voice, and the engineering behind it. Watch the machine before you install it.

What is a Keep?

One private system, not one chatbot

A Keep is agents, tools, and services on hardware you control. KeepRoute keeps the work alive when a model changes. You already own the machine it runs on.

L1 system → L2 domains → L3 services as their own blocks. The whole Keep hierarchy is on the board.

The ecosystem

Build, learn, prove, and follow

Foundation · Free

Otacon Lite

Build persistent local AI agents.

Learn more →

Orchestration · Free

KeepRoute

Keep AI missions alive across models.

Learn more →

Command · Free

Keep Desk

Why hand your computer to Meta Muse or Grok? Local, Grok & Muse-class computer-using AI teammates, on hardware you own.

Learn more →

Agents · Free

Expansion

Five-agent hierarchy, culture learning, REX, and deeper Keep capabilities.

Learn more →

Search · Free

Otaconskeep Search

A private search page with a local AI answer box that cites its sources.

Learn more →

Learn · Free

Classroom

Homelab, Linux, and Systems Engineering: the infrastructure under the Keep.

Enter Classroom →

Keep Blueprint · Free

FOXDIE

Automated media-library integrity. Real safety model, reversible-only deletion, self-verifying.

Learn more →

What makes it different

Local, persistent, modular, verified

Local first

Your hardware

Run it on machines you control. Your data stays in the Keep.

Persistent

Identity that stays

Agents keep identity, history, and state instead of starting over every chat.

Modular

Swap the model

Models, GPUs, and services can change without rebuilding the agents.

Verified

Evidence, not a demo reel

Requirements, architecture, implementation, testing, and the record of what is still unproven. Open Engineering →

Real Reference Keep // Live System

This is not a concept UI.

These are screens from Antonio G. Garcia's running Otaconskeep reference environment, not product mockups. OtaconsKeep Lite provides the foundation; the Reference Keep shows how far that foundation can be taken.

Reference Keep: not every system shown here ships with OtaconsKeep Lite today

Inside the Keep

A tour of the real rooms

Ten of the strongest, safest surfaces from the live Keep. Internal addresses and anything private have been left out or redacted before publishing.

The Keep doesn’t wait for you to check in.

When something matters, the right agent can bring it to you.

Discord Relay // Agent-Initiated // Asynchronous Operations

Keep in the Loop

Agent notifications delivered where you already are.

Otaconskeep doesn’t require you to constantly watch a dashboard. Agents can push useful updates directly into Discord: morning briefings, appointments, completed AI jobs, security and media alerts, and operational status from across the Keep. The goal is simple: important information finds you instead of you having to go looking for it.

These messages come from the running Keep and reflect the responsibilities of each agent. Naomi can surface upcoming appointments, Otacon can deliver system and intelligence briefings, and agents such as Albedo can report changes in queues, automation, and Project REX activity. Routine work stays quiet; useful changes get surfaced.

Screenshots from the running reference Keep. Discord relay is not a Lite installer feature

Take the Keep Tour

Step through it yourself

War Room: Situation View

Hear the Keep

Real voices trained for the agents that live here

Four agents, four trained voices, one welcome. Press play when you're ready. Nothing here plays on its own.

Chnl Codec · Ghost Pastel · Personnel Voice Archive Standing By

Voice Link Standby

Otaconskeep

Press play to begin

Otacon
Otacon
Systems / Engineering
Mei Ling
Mei Ling
Operations / Records
Naomi Hunter
Naomi Hunter
Research / Continuity
Halister Black Cloak
Halister Black Cloak
Project REX / Governance
0:00
0:00

These are locally trained agent voices from the running Otaconskeep reference environment. Voice Models // Local // Self-Hosted

Learn

Don’t just install it. Learn it.

Otaconskeep Classroom teaches the infrastructure underneath the Keep across three academies: Homelab (Linux, Docker, networking, ARR, Home Assistant, voice, automation), Linux from Desktop to Homelab, and Systems Engineering. 57+ lessons, labs, homework, and mastery gates.

Engineered, not just demoed

328+

Public verification cases, from requirements through architecture, traceability, V&V, risk, benchmarks, and evidence. Pass requires a record. What is still blocked stays marked blocked.

… reqs · … verified · … risks open

Choose your path

Which part is for you?

The person behind it

Built by Antonio G. Garcia

Engineer. Homelab builder. AI tinkerer. Three years building the computer he wanted since childhood.