The platform: Doppelganger
One harness. Twelve modules.
Doppelganger is a modular harness for digital twins. Each module is its own building block with its own memory — it runs what you turn on, and nothing you don't. The core five come with every install; the rest are yours to add.
Core — in every install
Local Runtime Bridge
The hands. Controls exactly what your twin is allowed to touch on your machine.
Rules & Approvals
The safety switch. Everything that matters asks it first; no answer means no action.
Marketplace
1,000+ connections to your tools, with permissions as narrow as you want — allow "send message" without allowing "delete channel".
Operator Inbox
Your decision queue. Approvals, escalations, and sign-offs stack here while work continues.
Remote Setup
Handles installation on your server — every service, connection, and safety check.
Work & knowledge
Work
Projects, goals, and tasks on a board your twin works from.
Knowledge
The memory — documents, research, and recall built from everything your twin sees. Growing fast.
Observer
Watches WhatsApp and Telegram, flags what's urgent, remembers the rest.
Workflows
Things you do repeatedly become routines — suggested by the system, approved by you.
Autonomy & trust
Mesh
Lets your twin talk to other people's twins — carefully limited, fully logged, off by default.
Open Design
Brings your design projects into your twin's world.
Live Artifacts
A board where your twin's work lands, gets reviewed, and goes live.
Quick answers.
What is a digital twin of a business?
Software that learns how a specific person or team works — their channels, patterns, and decisions — and does that work the same way. Unlike a general chatbot, a digital twin is built from your work, runs on your machines, and answers to your rules.
Do I need all twelve modules?
No. The core five come with every install; the rest switch on when you need them. Each module is its own program, so what's off simply isn't running.
Can the AI engine be swapped?
Yes. The harness is the permanent layer; the engine underneath is your choice and can change without rebuilding anything you've set up.
What does self-hosted mean here?
Every module, database, and memory runs on your own server, behind a private network. Nothing lives in our cloud.
Modules work best together — Observer leans on Knowledge; Workflows lean on Work. A forward-deployed engineer installs all of it on your server — see how a deployment works →
Last updated: July 24, 2026