Self-hosted

DecentAI: AI agents you run yourself.

Runs on your own computer or in your own environment. Every agent is reviewed before it is installed, checked on every call, and recorded. It ships with no agents; you add the ones you need.

Available on request: write to ahmed@decentai.io. Made by DECENT INTELLIGENCE ARTIFICIAL SERVICES, Abu Dhabi.

What DecentAI is

A platform for running AI agents under your control.

The model proposes; the platform decides.

Ships empty

On day one the platform has people, groups and an audit trail, and no agents. Nothing can act until an administrator installs something.

Every agent declares itself

Before it is installed, an agent declares each thing it can do, how far each one reaches, the records it keeps, the secrets it needs and the hosts it connects to.

Installed like an app

An administrator reads the declaration and installs one exact version, checked byte for byte. Nothing updates itself: a new version is a new review.

Held to it on every call

Every call is checked against the agent's declaration, your organization's rules and the chat's trust. Above that trust, a person approves first.

Isolated while it works

Each agent runs in a sandbox of its own, with its own files and its own network, and reaches only the hosts it declared.

Written in any language

An agent is a program and a manifest, written to one published standard. Your ERP or internal portal can have its own agent, under the same controls.

DecentAI, piece by piece

One platform, and every way to reach it.

Run the platform once; people use it from a browser, and soon from their desktop and phone.

Available

The platform

The server side of DecentAI: people, agents, records and chats, the sandbox agents run in, and the audit trail. Runs with Docker, on one computer or on your servers.

Available

The web client

The app people use in a browser: chats, approvals, agents, records and the organization's settings. Connects to any DecentAI server.

Available

Agents

Thirty-eight agents for mail, calendars, files, documents and records you keep, and a real web browser. Open source, in two public catalogs.

Coming soon

Desktop app

For Windows and macOS: connect to a DecentAI server, or run DecentAI on the computer itself.

Coming soon

Mobile apps

For iPhone and Android: chats, approvals and notifications from your DecentAI server, wherever you are.

Where it runs, and what stays yours

DecentAI runs inside your environment.

Nothing about your people, your conversations or your data passes through us.

Your environment

On your own computer, or on your own servers or cloud account. There is no hosted version: the platform runs where you run it. One installation can serve several organizations, each kept apart.

Your AI model

Choose from over two hundred providers, or a model you host yourself. You hold the keys. The model sees the conversation; it never sees a credential.

Your data

Conversations, documents, records, credentials and the audit trail stay in your deployment. Secrets are encrypted, and reach only an agent you listed, during a call.

Licensed to you

DecentAI is proprietary, and we grant access case by case. You run it; we never see it. Updates are installed when you choose, and agents' updates through your own review.

What leaves your environment is listed and yours to limit: the conversation to the model you chose, an agent's calls to the hosts it declared, and notifications where you send them.

DecentAI compared with a general AI tool

The difference is not the model. It is what surrounds it.

AspectA general AI toolDecentAI
Where it runsThe vendor's cloudYour environment
What it can do on day oneWhatever it was connected toNothing, until you install an agent
How capability is addedA vendor connector, for everyoneAn agent you review, install, allow and can uninstall
Your credentialsHeld by the toolEncrypted, released only to an agent you listed, during a call
Actions that change thingsWhen the model decidesChecked against your rules; above the chat's trust, a person approves
What you can see afterwardsA chat historyAn audit trail of every call, approval and refusal
Your own systemsA vendor roadmap itemAn agent your developers write, in any language, to one standard

A general tool asks you to trust the model. DecentAI asks you to approve a declaration and read a trail.

How to start

Write to us, then run it yourself.

  1. 1

    Ask for access

    Write to ahmed@decentai.io with your organization and what you'd like to do. We answer within a few working days, with access or a demo.

  2. 2

    Run it

    On your own computer or your servers. One command sets DecentAI up with Docker and generates every password and key; then name your organization: you are its administrator.

  3. 3

    Add a model and agents

    Connect the AI model you choose, add an agent catalog, install each agent after reading what it declares, and ask for the work in plain words.

Build your own

An agent for your own work.

An agent is a program and a manifest, in any language. The standard is one public document, and the project's own agents, open source, show every part of it.