Xedant MultiAgent

Run a fleet of AI workers on any number of servers — all from one place

Connects and manages any number of Linux servers over SSH

Docker is installed and configured on your servers automatically

An agent is one click to run: provision, start, stop, restart

Agents already running on a server can be connected without a reinstall

You can also work on your own computer: the server comes up right in WSL, with no passwords or keys

Addresses and ports are assigned automatically — no conflicts

Every server gets its own deployment slug: several servers on one machine never get in each other’s way

A shared Postgres database serves every agent on the server

A built-in Git code repository with automatic sync

One login for the whole server: sign in once and open every protected agent and product

Server checkup: a Check and fix checklist that repairs what it finds in one click

All the server’s not-yet-deployed agents come up with a single “Deploy” action

An agent can be moved to another server together with its data and database — or erased without a trace

The server home page can be opened from a phone with a QR code — no password to type

Every chat of every agent in one window

Tasks: long jobs queue up — with a live log and a stop button

Management: a control room for dozens of agents — the decision queue, states and spend on one screen

Analytics across all agents in one place

Chat statistics can also be archived to ClickHouse for long-term storage

Prompt queue, scheduled tasks, bots, MCP and skills — right in the agent chats

Skill catalog: store ready-made skills and upload them to the agents that need them

Environment sets: define a set of variables once and upload it to as many agents and servers as you like

Own Agent: your own assistant with a chat panel on every page

Balances and limits of your AI provider accounts, all in one place

A library of ready-made services you can install on any server from a template

Every app on one domain: each gets its own subfolder, and the server gets a home page

Agent API: let other agents run the system for you — with an access key

The interface is in English by default; Russian can be enabled in the settings

Passwords and access keys are stored encrypted

New agent, app and service ports are closed to the internet — they open to the outside only when you choose

Agent licenses can be issued right in the interface — no separate tools needed

Live updates — no page reloading needed

Server files in the browser: two panels, copy between servers, built-in terminal

Backups of your data run automatically

Everything runs on your servers — no external clouds

Dark and light themes, comfortable on a phone

Product catalog: eleven ready-made apps — from research and analytics to interface testing and news — each with its own agent

Secure HTTPS connection: self-signed, custom or Let’s Encrypt certificates — requesting a certificate also enables the secure port, and all traffic moves to HTTPS

Server management

Server management: connecting over SSH and onboarding checks

Add a server in a minute: address, username, password or key

All required software installs and configures itself

Server checkup — a Check and fix checklist: access, software, folders, certificates, databases, backups; anything missing is repaired in one click

Shared projects and data folders for all agents on the server

App addresses and certificates are set from the interface — no manual edits on the server

The server’s home page is a static panel with app cards at the root

Central login (the Authelia tab): one login for every protected app on the server

Deploying agents

Deploying agents: an agent card and settings preview

Creating an agent is simple: pick the server and the app, answer a few questions

Full lifecycle control: provision, start, stop, restart or remove

You see exactly what will be installed before anything runs — with validation

Live agent load (CPU, memory, occupied space), logs and the connection test right from the interface

Ready products (Research, Analytics, Data, Proxy) install together with their agent — from the same dialog

Updates run without downtime: MultiAgent waits for a quiet moment in the chats and restarts the agent on the new version itself

All the server’s not-yet-deployed agents and apps come up with a single “Deploy” action

Moving an agent to another server together with its folders and database — or erasing it completely

Centralized chats

Centralized chats of all agents in a single list

Every chat of every agent in one filterable list

Send messages and read replies without logging into each agent

Per-message stats: tokens, cost and speed

Everything updates in real time

Prompt queue, scheduled tasks, bots, MCP servers and skills — without leaving the chat

Tasks: the queue of jobs across all servers

Jobs of one server run one at a time and do not get in each other’s way

Fleet-wide jobs run on their own lane and do not wait for routine tasks

A live log and a week of history — you can see what was done and when

Any task can be stopped with one button

“Check and fix”, the terminal and file copying run right away and do not queue

Management: a control room for dozens of agents

Seven agent states: busy, thinking, idle, waiting for a decision, stuck, offline and unknown

Decision queue: response deadlines, only identical repeats merged, a “Dismiss” action and the decision journal

Ten screens: “Fleet”, “Fleets”, “Registry”, “Chats”, “Decisions”, “Cost”, “Tokens”, “Posture”, “Policies” and “Analytics” as the last item of the section

Incident mode, fleet freeze, hotkeys and the command palette

Notifications reach the queue, the notification centre and a messenger — but approving happens in the interface

Fleets: named groups of agents from any servers — one team instead of the whole park

A queue row opens the chat where the decision is needed, and a question answered in the chat closes itself

Readiness: where the infrastructure slipped

One readiness score for the whole fleet — 0 to 100, recomputed by every findings sweep

Findings with numbers: what exactly lowered the score, and by how many points

The score’s own history: every material move logged with its delta and a sparkline

Incident mode: switched on by hand, or by itself when agents go offline

Tokens: spend and forecast

One number per entity — a chat’s total is input + output + cache read + cache write, never a per-category split

Rolling windows — today, the last 7 days and the last 30 days — plus a next-30-days forecast labelled as one

Daily charts stacked by agent, by model and by skill

Attribution by agent, model, server and skill, with chat counts

Aggregates-only export — keys, tokens, shares and counts, never a prompt or message text

Policies: the autonomy rules

Autonomy ladder: suggest, confirm or act on its own

Confidence thresholds: above the top one the agent acts by itself, below the bottom one a human decides

A gap of at least 0.1 between the thresholds keeps the system from dithering on the border

Rules are set for the whole fleet, for a class of actions or for a single agent

Threshold history records how often decisions go to a human

Your own assistant (Own Agent)

Connect once — the agent’s address and key are set at startup; the key never reaches the browser

A chat panel and a sidebar block on every page: message box, models and skills, a live chat summary, and the “Tasks (N)” and “Chats” buttons in the footer

Prompt queue with auto-send, voice input and chat sounds

Scheduled work, bots and prompts in chats

Scheduled work, messenger bots and external services — all from the agent’s page, no window switching

Prepare prompts ahead of time — the agent sends them itself, one by one, or on your command

All settings and data belong to the agent: MultiAgent stores nothing of its own

Agent API — automation from other agents

Access only with the secret X-API-Key you issue

The helper discovers the available commands by itself — no separate manual needed

Only built-in actions, no arbitrary programs; everything is visible in the interface

Product catalog

MultiAgent (6000), Research (6010), Analytics (6020), Data (6030), Proxy (6040), Chatbot (6050), Telegram (6060), Test (6070), CRM (6080), News (6090), Portal (6100)

Credentials are generated automatically, and the app and the agent know about each other from the start

The shared database and shared folders (documents, scripts) are configured automatically

Centralized analytics

Centralized analytics across all agents

Every chat of every agent flows into one database

Charts for cost, tokens, messages and commits

Named filters: save a report scope — fleets, servers, agents — under a name and switch between them

See when your agents are most active

Optionally, chat statistics also go to a ClickHouse archive for long-term storage

Ranges from hours to months, and same-named agents on different servers are shown as separate lines

Tracking AI provider accounts

AI provider accounts: quotas and balances

All your AI provider accounts in one list

Balances and limits update in real time

Sign in to a Codex account right from the interface

Spending analytics per provider and per account

Tools and services

The tool library and deploying services to servers

A library of ready-made services for your tasks

A service installs on any server, with settings entered step by step

Settings can be text, secrets, numbers or choices

Full control over the running services

Every app on one domain

One domain per server: every agent, product and tool gets its own subfolder, and a summary of all apps sits at the root

It configures itself: deploy an agent or a service and its subfolder appears

Four kinds of routes: agents and products, tools with a web interface, custom routes to any address, and the central login’s own route

Certificates: self-signed, your own, or Let’s Encrypt — requesting one enables the secure port itself

Apps talk over the internal network; a fallen service only takes down its own subfolder

Security and backups

Security: encrypted secrets and backups

Passwords and access keys are stored encrypted

The programmatic API and your own assistant turn on only with a secret key — off by default

New agents and apps are not visible from the outside: their ports open only when you choose, and only the web server and the backup receiver face the world

Agent licenses are issued right in the interface when the signing key is on the host — no third-party tools needed

Server data is backed up automatically

Agent licenses are stored and reused without manual work

Handing the server over to the client

The client becomes the owner of their own MultiAgent

If the server belongs to your client, it makes sense to hand over the controls too. The handover is a one-time operation: it moves the records from your central instance to the client’s own MultiAgent on the same server — agents, apps, tools, routes and access keys. Running apps are untouched: nothing stops and nothing gets reinstalled.

Before you run it, you can see exactly what will move and what stays; if anything fails on your side, nothing changes — you can simply repeat the operation. Secrets travel directly between the two instances over a secure channel and never appear in the interface or the logs. You can look into the client’s instance with the Manage button — it signs you in automatically, no password needed.

A one-time, verifiable operation: success means every record has landed

Secrets travel only over the machine channel — they never reach the browser or logs

The Manage button opens the client’s instance already signed in

Installing on Windows

Installed as a service — no Docker

On Windows, MultiAgent installs as a service: the setup wizard walks you through the steps (the port, 3990 by default; the data folder; the login; the license), and after the install MultiAgent starts with the computer and keeps watching the servers even when you are not logged in. The install is machine-wide and needs administrator rights — Docker and other extra software are not needed on that computer.

Servers connect over SSH, and if you need agents on the computer itself, you add a server as local WSL — no passwords or keys. All the data — the database, keys, certificates, license — lives in one folder and survives both reinstalling and uninstalling; PostgreSQL, the programmatic API and your own assistant are enabled in the same place. Re-running the wizard offers to reconfigure the service or remove it completely, and the settings page controls the startup type and whether connections from other computers are allowed.

Setup wizard: a Windows service, port 3990, shortcuts and the Start menu

The data lives in ProgramData and survives reinstall and uninstall — nothing is lost

Login, license and the service settings are configured in the wizard

Free trial

Free use for 30 days — the trial license is already built into the program. Even after the free license expires, the app stays fully functional: only creating new servers and agents, and sending new messages, are blocked. No lock-in — you can move your data out to any database.

Personal license

Any number of servers and agents for one person. $97 — a one-time payment for a lifetime license. 12 months of free updates, then (optionally) 50% off the next 12 months of updates from the original purchase price. The key works offline and lasts a lifetime.

Company license

Any number of servers and agents for everyone in your company or team, including outside contractors. $970 — a one-time payment for a lifetime license with 12 months of free updates, then (optionally) 50% off the next 12 months of updates from the original purchase price. The key works offline and lasts a lifetime.

Service license

Any number of installs under your domain, plus the full source code with the right to change it however you like, restyle or rebrand it for your company, and integrate it into your infrastructure. Any visitor of your domain can use the product as part of your services. $297 — a one-time payment for a lifetime license with 12 months of free updates, then (optionally) 50% off the next 12 months of updates from the original purchase price. To keep updates painless, we recommend changing only branding and integrations — then merging with new features and fixes goes smoothly.

Free licenses

In some cases we are happy to gift a free license:

  • if you found a bug or a security vulnerability in any of our products (we honestly have no budget for a paid bug bounty);
  • if you suggested a useful improvement to our products (no coding needed — a good idea is enough; you get a license if we put it on the roadmap);
  • if you are an active open-source contributor (we love open-source; we just do not have the time to maintain our own products as open-source);
  • if you run a popular blog, Telegram channel or YouTube channel about programming, AI, analytics, marketing, business, finance or IT in general (no mention or promotion required — entirely up to you);
  • if you are an active affiliate partner (sales are not required, but you should have at least some content about our products).

If any of that sounds like you, just message us on Telegram. Tell us your name and email, and we will generate your personal lifetime license key.