GitOps Assistant turns live infrastructure signals into small, verified draft merge requests (MRs). Rules do what rules can. An AI model helps where judgement is needed. Code checks the answer. A human approves every change. Run it inside your own infrastructure, or offer it to your customers.
The same software runs in each case. What changes is who operates it, and where.
Nothing to install or operate. You give scoped, read-only access, and your team receives reviewed draft MRs.
For organisations whose data or policies require it. The assistant runs in your infrastructure, with your credentials and your own AI model endpoints, including self-hosted models.
You run infrastructure for others. Add continuous maintenance to your service, under a revenue-sharing agreement.
We work with local partners: specialised consultants who do the first setup and the integrations for you. We will announce the first names soon.
Every platform team has a list of work it knows it should do. Upgrades, migrations, monitoring, cleanup. The work is important, but it is never urgent. So it waits, and the infrastructure falls behind. GitOps Assistant does the boring part of that work. Your engineers keep the part that needs their judgement.
The assistant reads the changelogs, gathers the metrics, writes the change and tests it. Each MR explains what it changes and why. Most reviews take minutes.
Maintenance work arrives ready to review, inside the workflow your team already uses. Feature work does not have to stop for it. Firefighting gets rarer as the infrastructure gets current.
Fewer outdated components. Less capacity reserved and never used. Fewer gaps in monitoring. A human approves every change, and every change has an audit trail.
GitOps Assistant is not "an AI with access to Kubernetes". It is a fixed loop: observe, analyse, validate, propose, and a human reviews. Three layers do the work, and the AI model is only one of them.
Schema checks, version comparisons, metric thresholds, ownership detection, deduplication, minimal YAML patches and chart render comparisons. When the answer is known, code gives it.
Reading changelogs and deciding which breaking changes apply to you. Reasoning about an incident. Writing the fix where no rule can, and the explanation in the MR.
Safety clamps on every number. A dry-run against your real API server. A secret scan. Read-only cluster access, draft MRs only, an independent second review and a full audit trail.
If the assistant does not know, it says so.
Every MR lists what the assistant could not check. A held proposal says why it was held.
See an upgrade, step by step →
We have run the assistant on our own production infrastructure and on our customers' since April 2026. These are merged changes that run in production today. A human engineer reviewed and approved each one.
Our engineers delivered larger migrations by working with the assistant, for example an ingress-nginx → Traefik / Gateway API cut-over. The assistant prepares, verifies and follows up. A human drives.
Counting is easy. These numbers show quality. We measured them from 22 August to 21 October 2026, over every MR the assistant opened in that period. Each number shows what it counts.
The review numbers run to 18 October 2026. We do not measure incidents caused by MRs yet. Before each test cycle we close our own open MRs and generate them again. We do not count those closures as rejections.
You do not buy a list of features. You buy infrastructure that stays current, efficient, reliable and secure. Each outcome has small agents behind it. Each agent owns one concern. Many use no AI model at all.
Chart, image and controller upgrades, with every changelog read. Deprecated APIs and Flux v1 → v2 migrations.
Resource requests sized from 30 days of real usage. Idle volumes and forgotten environments found.
Probes, disruption budgets and replicas. Backup failures caught early. Each alert checked for a permanent fix.
What runs but is not in git gets adopted from its live state. Drift and failing reconciles become one issue per cause.
Committed secrets move to Vault. Vault policy and audit denials get reviewed. Security posture gets reported.
Monitors and dashboards written for you. MR reviews on request. Fifty warnings grouped into one issue.
You have three other options. Each one solves part of the problem.
The backlog keeps growing. Every month behind makes the next upgrade bigger and riskier. The cost arrives later, as an outage or a rushed migration.
They find broken rules and new versions. They do not see what runs in your cluster or how much it uses. They do not read the changelog for you or check that the change applies.
It is like using a bazooka. It is powerful, but you need a lot of experience and protection to guide it without collateral damage, and it usually needs broad access to act. You stay responsible for everything it does. And you are potentially handing the complete details of your infrastructure to a third party, without any filtering or guardrails.
Looks at your real infrastructure. Prepares the actual fix. Checks it with code and against your cluster. Puts it in the review workflow you already trust.
“Doing everything by hand equates to using a shovel. A general AI agent with access to your infrastructure is like using a bazooka. It is powerful, but you need a lot of experience and protection to be able to guide it properly without causing collateral damage. You stay responsible for everything it does, but you are potentially handing the complete details of your infrastructure to a third party, without any filtering or guardrails. I wanted something in between: a scalpel. One precise cut for each job, where you control what information gets exposed. And you get all the context to decide what ships, and to accept the responsibility.”
The assistant may be wrong. It is not allowed to be dangerous. Safety and data privacy are design constraints, not features added later.
The assistant has no merge rights. Your normal review and approval flow decides what ships. Nothing reaches a cluster without a human.
The assistant reads live state and metrics. It cannot change your clusters. Its dry-run identity can only test a change, never apply it.
You choose where the AI model runs: a cloud model, an approved provider or a self-hosted model. Secrets are scrubbed first. There is no silent fallback to the cloud.
We do not blindly send your data or infrastructure details to third parties. The assistant can pseudonymise your data before an AI model processes it. Every run records which agents ran, which AI model they used and why each proposal was sent or held. Independent reviewers check each MR against the cluster, without exposing all your details.
Every path starts the same way: a read-only assessment of one repository. Nothing changes, and the assistant opens no MR and no issue. Then we talk about the model that fits you.
Talk to us →
No. Every proposal is a draft MR, and the assistant has no merge rights. Its cluster access is read-only. Your normal approval flow decides what ships. This is the same in every model.
Your own. Each infrastructure declares where data may go: frontier cloud models, an approved provider, or self-hosted open-weight models only. The assistant routes work per call type, and it never falls back to a cloud model silently. Many agents use no AI model at all. The security architecture →
No. Many start with the managed service and a read-only assessment. You can move to a licence later, when your data or policies require it.
Support is deepest for Kubernetes with Flux CD, GitLab and Prometheus or Mimir. Vault, GKE and Cloudflare are also in daily use. See what is live, in development and on the roadmap →