Skip to main content
The catalog holds Komodor-built agents that you deploy as-is, supply credentials for, and run. This section is the reference for each one: what it reads, what to connect before deploying it, how to ask it for something useful, and the boundary it will not cross. For browsing the catalog and walking the deploy wizard, see Use specialized agents. Every page here answers the same nine questions in the same order, so you can compare two agents by reading the same section twice.
The catalog is curated per workspace, so the entries you see in your own console are the authoritative list. An agent documented here may not be offered to your account, and the console is the place to check.

Choosing one

Start from the system that already holds your evidence. An investigator is only as useful as the data it can reach, so the shortest path from deploy to a useful run is the one pointed at a system you have already connected.

Investigators

An investigator gathers evidence from one system and returns structured findings that cite it. None of them changes anything: they read, they correlate, and they report. Deploy the one whose system you trust most, and add a second when an incident spans two.

AWS Infrastructure Investigator

CloudTrail, CloudWatch, IAM and resource dependencies.

Azure Investigator

Resource Graph, Monitor, Log Analytics, AKS and Cost Management.

Datadog Investigator

Traces, logs, metrics, monitors and events.

Google Cloud Investigator

Cloud Logging, narrowed structurally and correlated against the audit log.

Grafana Investigator

Prometheus, Loki, Tempo, Pyroscope, alerts and annotations.

Cluster Investigator

Kubernetes, Grafana telemetry and GPU health in one in-cluster agent.

Kubernetes RCA

One cluster, read-only kubectl, no external data sources.

Klaudia Investigator

Komodor’s own Kubernetes investigator, reachable as an agent.

Code and repositories

These two read source rather than telemetry. One finds the code behind a problem you have already characterised; the other reviews a change before it merges. Neither writes to a repository.

GitHub Agent

Locates the files behind an incident and recommends the durable fix.

Code Reviewer

Reviews each pull request and reports findings by severity.

Remediators

A remediator starts where an investigation ends. One of them only ever plans; the other carries the plan out through a system that has its own approval gates.

Remediation

Reads a finished investigation and proposes a fix, questions, or no action.

Remediation Executor

Delegates the fix to Klaudia, or opens a pull request against the source.

Cost optimization

AWS Cost Analyzer

Scans a connected AWS account for waste, ranked by monthly impact.

What every catalog agent has in common

A few facts hold for all of them, so the individual pages do not repeat them.
A time budget bounds how long one run may take. It does not cap what a run costs — the Komodor Agentic Operation Platform (KAOP) reports spend per run rather than refusing an expensive one. See Agent spend attribution.

Next steps

Use specialized agents

Browse the catalog and walk the deploy wizard.

Built-in integrations

Connect what an agent needs before you deploy it.

Modules & workflows

Bind these agents to workflow steps instead of running them one at a time.

Build from scratch

When no catalog entry fits.