Fully Managed AI DevOps Worker
as a Service

Deploy AI DevOps Worker as a fully managed service starting at €9/mo. Get automated backups, SSL, updates, support and monitoring included.

AI DevOps Worker is the headless agent node of the open-source aidevops framework: it accepts task dispatches over an HTTP API, runs coding sessions in isolated Git worktrees, and opens pull requests for review, combining the convenience of a hosted AI coding agent with the security and control of self-hosted infrastructure.

✓Free 7-day trial  ✓99.9% Uptime SLA  ✓No credit card  ✓Cancel anytime

✓Free 7-day trial  ✓99.9% Uptime SLA
✓No credit card  ✓Cancel anytime

AI DevOps Worker

AI DevOps Worker

STARTING AT

€9/month
Automated Backups
Monitoring
Automated Updates
Auto SSL

USAGE

Unlimited
Human Support
Custom Domains
Terminal Access
File Manager Access
Deploy in your region — 21 locations worldwide
GermanyFinlandNetherlandsUKSwedenUnited StatesCanadaSingaporeJapanAustraliaBrazilSouth Africa+9 more →
AI DevOps Worker Preview Image

ABOUT THE SOFTWARE

What is AI DevOps Worker

AI DevOps Worker is the worker node of aidevops, an open-source framework that gives AI coding agents structure: shared context, isolated Git worktrees, budget tracking, and a supervisor that decides what runs next. The worker executes dispatched tasks and reports the result back.

The project is MIT licensed and maintained by Marcus Quinn, first published in November 2025. Reuse including commercial use is explicitly permitted so long as the copyright and licence notices are retained, which is why the app can be offered as a managed service without a separate arrangement. The codebase is Bash and TypeScript on the Bun runtime, with a set of Model Context Protocol servers alongside it.

State lives in SQLite in write-ahead-logging mode: the inter-agent mailbox, the supervisor state machine and a full-text memory index, plus files on disk. There is no separate database server and no cache layer to operate, which is why a worker fits comfortably in two gigabytes of memory. Inference is not local by default: the worker calls whichever model provider you configure, using the key you supply.

FEATURES

What AI DevOps Worker does

The worker is a task executor, not an editor you sit in front of. Work arrives over an HTTP dispatch endpoint or from the supervisor, runs in an isolated checkout, and leaves as a pull request you review in your own Git host.

HTTP task dispatch

Accepts jobs over an HTTP API, so a script, a webhook or another node can queue work without a person sitting at a keyboard.

Isolated Git worktrees

Each task gets its own checkout on its own branch, so two workers can run against one repository without stepping on each other.

Supervisor pulse

A scheduled loop decides what runs next, reassigns stalled work, and stops workers that are making no measurable progress on their task.

Slash-command library

A large set of named commands covers build, fix, review, release, hosting and reporting work, so instructions are repeatable rather than freehand prompts.

Model account pool

Routes work across OpenAI, Anthropic, Google, Cursor and xAI accounts, or a local endpoint, sending routine jobs to the cheaper tiers.

Budget tracking

Tracks spend per mission against a threshold and reports which tasks consumed it, so an expensive run is visible before the provider invoice is.

Model Context Protocol servers

Ships with MCP servers that give the agent structured access to tools instead of screen-scraping its way through them.

Searchable memory

A full-text index over prior work lets an agent recall what was already decided on a repository rather than rediscovering it every session.

WHAT'S ALWAYS INCLUDED

Every app. Fully managed.
Nothing extra to pay for.

Every app on DANIAN ships with the same operational baseline. You do not choose a backup add-on or a monitoring tier. Hosting, patching, backups, SSL, and support are part of the €9, and they apply to AI DevOps Worker the same way they apply to everything else in the catalog.

Automatic updates and patches

Apps run the latest stable version. Security patches applied silently, with rollback if needed.

Daily off-site backups

Multiple daily backups in redundant off-site locations. One-click restore if anything goes wrong.

24/7 uptime monitoring

Continuous monitoring with instant alerting. We respond before you notice.

SSL, firewall, DDoS protection

Auto-renewing SSL, hardened firewall rules, DDoS mitigation on every deployment.

Performance and scaling

We monitor resource usage continuously. When your app needs more headroom, we flag it and upgrade with your explicit approval.

Dedicated engineering support

Real engineers by email and ticket. DNS, SMTP & migration help. All included in €9.

WHY MANAGED

Why teams pick managed AI DevOps Worker

The reason teams move is billing. Hosted AI coding agents have shifted from flat seats to metered tokens and credit pools, so identical work now costs a different amount every month. Running the agent yourself puts the meter back where you can see it and cap it.

Running the worker is not the hard part. The hard part is everything around it: a Linux host that stays patched, a process supervisor that restarts a dead session, certificates that renew before they lapse, backups of a SQLite file that is being written to while you copy it, and somebody watching when the dispatch endpoint stops answering at three in the morning.

The failure mode specific to this app is the agent itself. An unsupervised worker can loop: retrying, re-planning, spending provider credit on a task it will not finish. Upstream ships the countermeasures: a struggle ratio that marks a worker as thrashing, a kill for any worker running three hours without opening a pull request, and a flag on pull requests left idle six hours. What it also ships is a supervisor that dispatches every two minutes with no human in the loop, which is how a quiet weekend becomes an expensive one.

REVIEWS

Hear from customers ​like you​​​​​​​

Successful businesses and professionals around the world rely on DANIAN every day

USE CASES

Three teams who run AI DevOps Worker on DANIAN

Three composite teams matching the buyers who ask for this app. Each wants an agent working on their repositories, and each wants the monthly bill to be a number they chose rather than a number they discover.

SIX-PERSON WEB STUDIO

Moving off a metered coding-agent bill

Six seats of a hosted agent became unpredictable once usage billed per token. They run one worker in a location close to their clients, enable the pulse overnight only, and merge the morning's pull requests themselves.

PLATFORM PAIR AT A 40-PERSON FINTECH

Keeping agent runs where the risk register says

Two engineers support forty people. The worker runs in the region their risk register names, the review gate is set to wait so nothing self-merges, and every dispatched task lands as a reviewable branch rather than a direct push.

INDEPENDENT CONSULTANT, TWELVE CLIENT SITES

One worker per client, not one shared box

Twelve client estates, twelve €9 workers, each with its own model-provider key and its own backups. A client leaving means deleting one app, not untangling a shared machine.

COMPARISON

Four ways to run AI DevOps Worker

Four ways to get an AI agent working on your repositories, priced at one, five and ten people. The difference that matters is not only the sticker price: it is who carries the operational work and who carries the variable cost.

Path1 person5 people10 peopleWhat you also carry
GitHub Copilot Business$19/mo$95/mo$190/moMetered credits above the included allowance. Agent usage bills per token, so the monthly number moves with how hard the agent worked.
Self-host on a VPS$24/mo$24/mo$24/mo + tuningYour time: patching, process supervision, certificate renewal, backups, and a database tune once several workers share the same box.
Home server~€300 one-time+ electricity+ electricityAn Intel N100-class mini PC with 16 GB RAM, plus your own uptime, your own restores and your home connection's outbound reputation.
DANIAN managed AI DevOps Worker€9/mo€9/mo€9/moNothing operational. Backups, patching, monitoring, certificates and support are in the €9. You hold the model-provider key, so agent spend stays yours to cap.

BY INDUSTRY

AI DevOps Worker for specific industries

An agent with commit rights to your repositories behaves more like a supplier than a tool, and the sectors below already have rules about how suppliers are recorded and controlled. Each puts a different demand on how this app is set up.

Studios running client repositories increasingly work to ISO/IEC 42001:2023, the AI management-system standard, which asks an organisation to document how each AI system is assessed for risk and kept under control rather than simply used. For studios we ship the supervisor pulse switched off and worker concurrency pinned, so nothing dispatches against a client repository until somebody schedules it. The pattern that suits them is an overnight window: the pulse enabled from midnight, workers picking up labelled issues across client repositories, dependency bumps and copy changes arriving as pull requests, and a person merging in the morning. Two numbers from the app itself keep that honest: any worker running three hours without opening a pull request is killed, and pull requests idle for six hours are flagged back to the queue.

Financial firms have worked under DORA, the Digital Operational Resilience Act, since it began applying on 17 January 2025. It requires a register of information and communications technology arrangements held with third parties, and reporting of major incidents. Two things follow for this app: the worker runs in the datacenter location you name rather than one we pick, and the change record it produces stays exportable. We keep cross-model verification enabled so destructive operations are checked by a second model before they run, and we set the review gate to wait so no worker merges its own pull request into a production branch. The 30 GB of storage included per app holds a long history of worktrees and dispatch records without an add-on.

Service desks run change enablement under ITIL 4, where every change carries a record and an authorisation path before it reaches a client estate. An agent that opens its own pull requests fits that model only if it cannot also approve them, so we ship the review gate set to wait rather than the upstream default of merging with follow-up. The workflow that suits a desk is ticket to branch to pull request: the ticket reference goes in with the dispatch, the worker opens a branch named for it, and the resulting pull request is the change record. Each worker is sized at two gigabytes of memory, so providers give every client estate its own €9 worker instead of sharing one machine across accounts.

Product teams selling into large buyers are asked for build provenance, and the SLSA levels describe what a signed statement about a build artifact has to prove, including which build service produced it. That pushes releases away from whichever laptop was free. Here the worker cuts the tag, generates the changelog from commit history and opens the release pull request, running on a host whose state is backed up daily off-site. We pin every dependency to the version we tested, which matters for this app in particular after a widely used model-routing package was compromised upstream. Each app includes 1,000 GB of outbound transfer, which covers release artifacts and container pulls without a metered surprise.

FAQ

Frequently asked questions

Three groups of questions: how the worker is configured and what it costs to run, how repositories and keys move onto it, and how the platform bills and supports the app. The answers describe what we ship, not what is possible in principle.

01

Technical and configuration

Yes. The worker calls whichever provider you configure and never proxies inference through us, so you supply the key for OpenAI, Anthropic, Google, Cursor or xAI, or point it at a local endpoint. Your provider relationship, your rate limits, your spend cap.
We pin worker concurrency instead of letting it scale to free memory, lower the mission budget alert threshold below the upstream default of eighty percent, and keep the upstream kill for any worker running three hours without opening a pull request. You still set a hard cap at your provider.
No. Upstream ships a pulse that dispatches every two minutes with no human in the loop. We ship it switched off, because a fresh install pointed at a real repository should not start committing before you have looked at it. You enable it when you are ready.
The framework watches a struggle ratio and marks a worker as struggling, then thrashing, when retries outpace progress. Workers running three hours without a pull request are killed and their worktree released. Pull requests left idle six hours are flagged so they do not sit unnoticed.
In SQLite in write-ahead-logging mode plus files on disk: the inter-agent mailbox, the supervisor state machine, a full-text memory index, and the Git worktrees. There is no external database and no cache server, so the backup is a copy of those paths.
It has to, in order to open pull requests. You add a deploy key or a scoped token for the repositories you want it to touch, and we keep that credential inside your own app environment rather than in shared platform configuration.
Yes. Terminal and file manager access are scoped to your own app container, so you can read a log, inspect the SQLite state or drop in a config file without us handing you the underlying host.

02

Migration and onboarding

21 datacenter locations across six continents. You choose the region at provisioning. Application data sits in the region you choose; pick whichever is closest to your users or matches your data-residency preference.
Yes. Request a region migration from the dashboard and we run the move in the background. The system emails you when the migration completes; total transfer time depends on data volume but typical instances finish in a few hours. There is no extra charge for a region change.
Yes. Full data export is available at any time, in a portable format you can bring to any infrastructure.
Yes. The parts worth moving are your repository registration file, your model account pool and any project state directories. Copy them into the app data directory and add your provider key, and the worker picks up the same repositories. Worktrees are disposable and do not need to come.
Provisioning the app is handled for you. What takes time is yours: adding a provider key, adding a deploy key or token per repository, and deciding whether the supervisor runs on a schedule at all. We do not put a stopwatch on that decision.
Yes, with a deploy key or scoped token per repository. Public and private behave the same way. Start with one repository and a narrow issue label, then widen once you have seen what the worker opens and how it words a pull request.
Yes, at no extra cost. Bring a domain and we will set the records with you, or ask us to do it for you. Certificates are issued and renewed automatically once the name points at the app.
The dispatch endpoint is protected at the app level, and we can put your identity provider in front of the app where the protocol allows it. Tell us what you use and we will say honestly whether it fits before you commit.
Usually. The account pool accepts subscription-backed accounts as well as API keys, which is how teams with an existing plan avoid paying for the same capacity twice. Whether a given plan permits automated use is between you and that provider.

03

Billing, support, and platform

€9 covers everything we do for that app: hardware in the region you choose, daily off-site backups with one-click restore, automatic security patches and version upgrades, 24/7 monitoring, SSL and firewall, and engineering support on email and the ticket section in the client portal. There are no setup fees or hidden line items. For more info see our Pricing page.
If you decide to continue, we charge €9/app/month from day 8. If you don't, the trial ends and you can export your data. No card is required for the trial, and we never auto-charge you without explicit consent.
No. The €9/month is flat regardless of how many users log into your app. Add 5 users or 50; the price doesn't change.
24/7 email and ticket support, both staffed by engineers who run the systems. We handle DNS configuration, SMTP setup, app integrations, performance tuning, troubleshooting, and migration help. Response time is typically under an hour. There is no tier system — every customer gets the same support.
Yes. Cancel from the dashboard. We don't charge a cancellation fee, we don't lock data, and we will export your data to you on request before deletion. data to you on request before deletion.
Every customer instance is backed up daily to a separate region from the primary. We test restores. You can request a restore at any backup point within the retention window — usually 7 days for daily backups.
Your application data sits in the region you choose at provisioning — 21 datacenter locations across six continents. Account-level data (billing, account email, support ticket history) is processed centrally. Application data region is picked by you, per app.
99.9% uptime SLA on every app, every tenant. Service credits are documented at danian.co/service-level-agreement. The status page is located at status.danian.co.
When your tenant approaches the resource ceiling — the base tier holds 1 vCPU/RAM, 30 GB storage — we notify you. Resource upgrades happen with your explicit consent; we will not upgrade your tenant or charge you without it.
We wait. We don't suspend the app or delete your data on the first failed charge. We email you, you fix the card on file, and we continue.
Invoices can be downloaded from the billing dashboard in PDF the day each charge succeeds. EU VAT is added where applicable and the VAT-reverse-charge regime applies for VAT-registered businesses with a valid number.
150+ open-source apps across automation, team chat, file sync, analytics, AI, password management, email marketing, dev tools, project management, smart home, CMS, and federated social. See the full catalog →
Yes. Every instance comes with a web-based terminal and a file manager in your DANIAN management dashboard. Useful for managing your data and customizations.
Resources scale with your usage. If your app needs more vCPU, RAM, or storage, we add it — and we ask first before any change to your plan. €9 is the floor; resource-heavy workloads may price higher, but you'll always know in advance.
Yes. We have both a Partner program and an Affiliate program available. Anybody can sign up.
No contract. No minimum commitment. Cancel anytime from the dashboard with one click. The 7-day free trial requires no credit card. After the trial converts to paid, you can still cancel at any month without notice or penalty.

DEPLOY IN YOUR REGION

21 datacenter locations on six continents

Pick the region closest to your users.

United States, Germany, Finland, Singapore, Australia, Brazil, Canada, Netherlands, UK, Spain, Italy, France, Sweden, Malaysia, India, Japan, Mexico, Poland, South Korea, Chile, South Africa and more coming soon

Global Reach Map

Try managed AI DevOps Worker for 7 days

No card. Cancel from the dashboard.