# Komodor - KAOP

- [Overview](https://docs.komodor.com/get-started/overview.md): What the Komodor Agentic Operation Platform is, who it is for, and how to get from signing in to a working agent.
- [Before you begin](https://docs.komodor.com/get-started/before-you-begin.md): The access, connections, and tooling you need in place before building or running your first agent.
- [Concepts & glossary](https://docs.komodor.com/get-started/concepts.md): The vocabulary of the platform — agents, runs, workflows, modules — and how the pieces fit together.
- [Interfaces](https://docs.komodor.com/get-started/interfaces.md): Every way to work with the platform — console, REST API, SDKs, MCP, and Slack — and when to reach for each.
- [Architecture](https://docs.komodor.com/get-started/architecture.md): How the control plane, your agents, and the evidence trail fit together — and where the boundaries are.
- [Control plane](https://docs.komodor.com/get-started/architecture/control-plane.md): Understand the control plane's ownership of identity, routing, durable state, API surfaces, and worker evidence.
- [Data flow](https://docs.komodor.com/get-started/architecture/data-flow.md): Trace job inputs, credentials, tool traffic, and evidence so you can assess what crosses your deployment boundaries.
- [Onboarding](https://docs.komodor.com/get-started/onboarding.md): The guided checklist that takes a new workspace from empty to a working, connected, governed agent.
- [Deployment methods](https://docs.komodor.com/get-started/deployment-methods.md): Which parts of the platform run on Komodor's infrastructure and which run in yours, and what that means for access and data.
- [Self-hosted control plane](https://docs.komodor.com/get-started/on-prem/overview.md): Run the whole platform inside your own cluster — what it includes, the three deployment tiers, and what it requires of your environment.
- [Install](https://docs.komodor.com/get-started/on-prem/install.md): Run the preflight, write the values your environment needs, install the chart, and sign in as the first user.
- [Operating a self-hosted install](https://docs.komodor.com/get-started/on-prem/operating.md): Upgrades, the one secret you must never regenerate, moving off the bundled database, and what to send support.
- [How it works](https://docs.komodor.com/manage-your-agents/build/how-it-works.md): What building an agent involves in KAOP — the two authoring paths, and everything you attach to an agent before it runs.
- [Build from scratch](https://docs.komodor.com/manage-your-agents/build/build-from-scratch.md): Author your own agent with the SDK — its spec, instructions, tools, and handler — then create it from the console, the API, or code.
- [Use specialized agents](https://docs.komodor.com/manage-your-agents/build/use-specialized-agents.md): Deploy a Komodor-built specialized agent from the catalog — validated, ready to run, and live in minutes without writing code.
- [Agent catalog](https://docs.komodor.com/manage-your-agents/build/catalog/overview.md): Reference for every Komodor-built agent you can deploy from the catalog — what each one reads, what it costs in time, and where it stops.
- [AWS Infrastructure Investigator](https://docs.komodor.com/manage-your-agents/build/catalog/aws-investigator.md): Traces an AWS incident through CloudTrail, CloudWatch and IAM, and returns findings that cite the evidence behind each one.
- [Azure Investigator](https://docs.komodor.com/manage-your-agents/build/catalog/azure-investigator.md): Investigates an Azure subscription across Resource Graph, Monitor, Log Analytics and AKS, and cites portal deeplinks for every finding.
- [Datadog Investigator](https://docs.komodor.com/manage-your-agents/build/catalog/datadog-investigator.md): Localises a regression through Datadog traces, logs, metrics and monitors, and returns findings that link back to the permalink behind each one.
- [Google Cloud Investigator](https://docs.komodor.com/manage-your-agents/build/catalog/gcp-investigator.md): Investigates a Google Cloud project through Cloud Logging — pinning the earliest failing entry and correlating it against the audit log.
- [Grafana Investigator](https://docs.komodor.com/manage-your-agents/build/catalog/grafana-investigator.md): Localises a regression across Prometheus, Loki, Tempo and Pyroscope, and returns findings that link back into Grafana.
- [Cluster Investigator](https://docs.komodor.com/manage-your-agents/build/catalog/cluster-investigator.md): Combines Kubernetes RCA, Grafana telemetry and GPU diagnostics in one in-cluster agent, deployed one per cluster.
- [Kubernetes RCA](https://docs.komodor.com/manage-your-agents/build/catalog/kubernetes-rca.md): Root-causes a single Kubernetes resource from inside its own cluster, using read-only kubectl and nothing else.
- [Klaudia Investigator](https://docs.komodor.com/manage-your-agents/build/catalog/klaudia-investigator.md): Puts Komodor's Klaudia behind an agent — ask a Kubernetes question across clusters and get her answer, with any approval she raises surfaced to you.
- [GitHub Agent](https://docs.komodor.com/manage-your-agents/build/catalog/github-agent.md): Finds the repository files behind a problem an investigation has already characterised, and recommends the durable code change that stops it recurring.
- [Code Reviewer](https://docs.komodor.com/manage-your-agents/build/catalog/code-reviewer.md): Reviews every pull request from its diff and reports Blocking, Should-fix and Nit findings, each citing a file, a line and a consequence.
- [Remediation](https://docs.komodor.com/manage-your-agents/build/catalog/remediation.md): Reads a finished investigation and returns a typed decision — propose a fix, decide no action is warranted, or ask the questions that would settle it.
- [Remediation Executor](https://docs.komodor.com/manage-your-agents/build/catalog/remediation-executor.md): Carries a finished investigation into action — briefing Klaudia to fix the live resource, or opening the pull request that fixes the source.
- [AWS Cost Analyzer](https://docs.komodor.com/manage-your-agents/build/catalog/aws-cost-analyzer.md): Scans a connected AWS account for waste across six use cases and reports findings ranked by estimated monthly impact, each with its evidence.
- [Integrations overview](https://docs.komodor.com/manage-your-agents/build/integrations-overview.md): The two ways an agent reaches anything external — the built-in integration catalog or the MCP Gateway — and how to choose between them.
- [Built-in integrations](https://docs.komodor.com/manage-your-agents/build/built-in-integrations.md): The catalog of ready-made connections — cloud, observability, source control, ticketing, chat — with the credentials each needs and how to test one.
- [Integration groups](https://docs.komodor.com/manage-your-agents/build/integration-groups.md): Bundle your connected tool servers into a named group, narrow which tools it grants, and attach the whole set to an agent in one move.
- [MCP Gateway](https://docs.komodor.com/manage-your-agents/build/mcp-gateway.md): Expose your own tools to agents — an MCP server you run, or an OpenAPI document that becomes tools — governed by gateway policy.
- [Credentials & secrets](https://docs.komodor.com/manage-your-agents/build/credentials-secrets.md): Store a secret once, bind it to the agents allowed to use it, and have it delivered to runs without its value ever being exposed.
- [Use cases](https://docs.komodor.com/manage-your-agents/build/use-cases.md): The typed actions an agent advertises — each becomes a callable tool on that agent's own MCP endpoint, with its own input and output schema.
- [Skills](https://docs.komodor.com/manage-your-agents/build/skills.md): Package your runbooks and procedures as reusable, versioned skills, attach them to any agent, and see which ones a run actually used.
- [Knowledge base](https://docs.komodor.com/manage-your-agents/build/knowledge-base.md): Give agents your runbooks, postmortems, and service docs as a searchable source they retrieve from and cite during a run.
- [Triggers & schedules](https://docs.komodor.com/manage-your-agents/build/triggers-schedules.md): Run an agent on a recurring cron schedule from the trigger registry — and where inbound webhook endpoints live instead.
- [Deploy an agent](https://docs.komodor.com/manage-your-agents/build/deploy-an-agent.md): How an agent becomes a running worker — where it can run, the three values it needs, and exactly what happens on first registration.
- [Manage a deployed agent](https://docs.komodor.com/manage-your-agents/build/manage-a-deployed-agent.md): Operate a live agent — enable and disable it, edit its configuration, manage its token and labels, archive it, and read its activity.
- [Memory](https://docs.komodor.com/manage-your-agents/build/memory.md): What an agent learned in one run and wrote down for its future self — reviewed before it is published, and searchable by the agents you bind to it.
- [Providers](https://docs.komodor.com/manage-your-agents/build/providers.md): The models your fleet can call — the ones Komodor manages for you, and your own provider accounts registered alongside them.
- [Outposts](https://docs.komodor.com/manage-your-agents/build/outposts.md): A small relay you run inside your own network so agents can reach private services — outbound only, deny-by-default, with no inbound hole to open.
- [Marketplace](https://docs.komodor.com/manage-your-agents/build/marketplace.md): Understand packaged-agent availability and choose the supported deployment path for your workspace.
- [How Run works](https://docs.komodor.com/manage-your-agents/run/how-it-works.md): Every way work reaches an agent, what one execution records, and where to look when you need to know what happened.
- [Orchestration](https://docs.komodor.com/manage-your-agents/run/orchestration.md): How a workflow's steps deliver tasks to agents, how orchestrators coordinate specialists, and how a run walks the graph.
- [Chat & history](https://docs.komodor.com/manage-your-agents/run/chat-history.md): Work conversationally with your agents in resumable sessions, and read every run and chat in one ledger.
- [Runs & evidence](https://docs.komodor.com/manage-your-agents/run/runs-evidence.md): Every execution is a run with a full evidence trail — inputs, tool calls, reasoning, output, and cost. Here is how to read it.
- [Outbound webhooks](https://docs.komodor.com/manage-your-agents/run/outbound-webhooks.md): Have KAOP post signed, retried, auditable events to your own endpoints so external systems react to what your agents do.
- [Channels](https://docs.komodor.com/manage-your-agents/run/channels.md): Connect Slack so your team starts agents, workflows, and incident pipelines from the conversation they are already having.
- [Attention](https://docs.komodor.com/manage-your-agents/run/attention.md): The operator inbox — held calls waiting on approval, parked selections waiting on a choice, and runs that stopped and need a look.
- [Optimize — how it works](https://docs.komodor.com/manage-your-agents/optimize/how-it-works.md): The four lenses on a running fleet — reliability, quality, cost, and portability — and which surface answers each.
- [Fleet health](https://docs.komodor.com/manage-your-agents/optimize/fleet-health.md): Read the whole agent fleet at a glance — what is online, what went quiet, what is failing, and what changed.
- [Evaluations](https://docs.komodor.com/manage-your-agents/optimize/evaluations.md): Grade agent runs with LLM judges against explicit rubrics, and read exactly why a score is what it is.
- [Model Evaluation](https://docs.komodor.com/manage-your-agents/optimize/model-evaluation.md): Run a candidate agent or model beside production on real traffic and let a blinded judge say which one is better.
- [Continuous Improvement](https://docs.komodor.com/manage-your-agents/optimize/continuous-improvement.md): Turn accumulated judge verdicts into a concrete proposed change, then settle it as an experiment against real history.
- [Agent spend attribution](https://docs.komodor.com/manage-your-agents/optimize/agent-spend-attribution.md): What the fleet costs per run, agent, and model — how each figure is derived, and how to cap spend with budgets.
- [Knowledge graph](https://docs.komodor.com/manage-your-agents/optimize/knowledge-graph.md): Explore the resources your agents have discovered while operating the fleet, and how they connect to incidents and cost findings.
- [Observability & OTel export](https://docs.komodor.com/manage-your-agents/optimize/observability-otel-export.md): Export agent traces, logs, and metrics over OpenTelemetry so agent activity sits beside the rest of your systems.
- [Golden Scenarios](https://docs.komodor.com/manage-your-agents/optimize/golden-scenarios.md): Versioned regression cases with a known right answer, run on demand or on a schedule, scored into the same ledger as everything else.
- [Modules & workflows](https://docs.komodor.com/modules-and-workflows/overview.md): A module is an operational outcome you own; the workflows inside it are the automation that delivers it.
- [Incident management & troubleshooting](https://docs.komodor.com/modules-and-workflows/sre/incidents.md): Detect, group, investigate, remediate, and learn from production incidents — with the evidence behind every conclusion.
- [Alert Intelligence](https://docs.komodor.com/modules-and-workflows/sre/alert-hygiene.md): Classify which monitors are worth waking someone for, and propose the threshold, dedupe, and suppression fixes that quiet the rest.
- [Proactive reliability optimization](https://docs.komodor.com/modules-and-workflows/sre/reliability-optimization.md): Turn indicators, error budgets, and recurring failure patterns into concrete reliability improvements — including the agent that eliminates the recurrence.
- [Kubernetes Cost](https://docs.komodor.com/modules-and-workflows/cost-optimization/k8s-cost.md): Attribute Kubernetes spend to the teams that cause it, then turn the waste into right-sizing and placement changes you approve.
- [Cloud Cost](https://docs.komodor.com/modules-and-workflows/cost-optimization/cloud-optimization.md): Track cloud vendor spend, catch the anomaly the week it happens, and convert waste into remediation actions with an owner attached.
- [Observability Cost](https://docs.komodor.com/modules-and-workflows/cost-optimization/observability-optimization.md): Find the observability spend that buys nothing — high-cardinality metrics, unread logs, unused dashboards — with an agent configured to manage that provider.
- [Change Intelligence & Risk Control](https://docs.komodor.com/modules-and-workflows/ops-automation/change-intelligence.md): Decide whether the change that just shipped is good — and undo it if not — with a verdict backed by the signals inside its blast radius.
- [Production Readiness & Standards](https://docs.komodor.com/modules-and-workflows/ops-automation/production-readiness.md): Score services and release candidates against production standards, block unsafe releases, and manage evidence-backed waivers.
- [CI/CD Health & Remediation](https://docs.komodor.com/modules-and-workflows/ops-automation/ci-cd-pipeline-health.md): Keep the merge path trustworthy — flaky stages quarantined, queue time cut, and a broken delivery stage caught before it blocks everyone.
- [How it works](https://docs.komodor.com/security-and-governance/how-it-works.md): The five things that decide what an agent may do — identity, permissions, standards, runtime guardrails, and the record of every decision.
- [Signing in](https://docs.komodor.com/security-and-governance/identity-and-access/signing-in.md): How people authenticate through your identity provider, how a session behaves, and how someone comes to belong to a workspace.
- [Accounts & members](https://docs.komodor.com/security-and-governance/identity-and-access/accounts-members.md): The workspace as an isolation boundary, belonging to several at once, and how to invite, suspend, and restore the people in one.
- [Roles & permissions](https://docs.komodor.com/security-and-governance/identity-and-access/roles-permissions.md): Capabilities, policies, and roles — how default-deny access is composed, and the three ways to scope a grant to the right resources.
- [API keys](https://docs.komodor.com/security-and-governance/identity-and-access/api-keys.md): Issue, use, and revoke bearer tokens for programmatic access — and choose whether a key acts as a service account or as you.
- [Service accounts](https://docs.komodor.com/security-and-governance/identity-and-access/service-accounts.md): Non-human identities that belong to the workspace rather than to a person, so automation survives your team changing.
- [Agent identity](https://docs.komodor.com/security-and-governance/identity-and-access/agent-identity.md): Every agent is a governed principal with its own credential and permissions, enforced where the action lands rather than inside the agent.
- [Access explorer](https://docs.komodor.com/security-and-governance/identity-and-access/access-explorer.md): Ask what an identity can actually do, and test one action against one resource, before you grant or revoke anything.
- [Configuration clusters](https://docs.komodor.com/security-and-governance/identity-and-access/configuration-clusters.md): Declare KAOP resources from your own cluster's manifests, and see which cluster owns what — including when an edit here will be reverted.
- [Standards & Guardrails](https://docs.komodor.com/security-and-governance/controls/standards-guardrails.md): The standards every new agent inherits, and the deterministic rules that block, hold, redact, or flag an action at the boundary — every decision recorded.
- [Approvals](https://docs.komodor.com/security-and-governance/controls/approvals.md): A consequential action waits for a person, with the evidence needed to decide — and the decision becomes part of the run's record.
- [Audit log](https://docs.komodor.com/security-and-governance/controls/audit-log.md): An append-only record of every governed change and every sensitive read — written in the same transaction as the change itself.
- [Admin Console](https://docs.komodor.com/security-and-governance/controls/admin-console.md): Administration that happens above a single workspace — workspace lifecycle, trusted domains, platform operators, and the records they leave.
- [Agent isolation & tenancy](https://docs.komodor.com/security-and-governance/architecture-considerations/agent-isolation-tenancy.md): The workspace is the isolation boundary — how a request is bound to exactly one, and how an agent is kept from reaching anything outside it.
- [Secrets & credential handling](https://docs.komodor.com/security-and-governance/architecture-considerations/secrets-credential-handling.md): How a stored secret reaches the run that needs it without being exposed to a browser, a deploy, a log, or another agent.
- [Data handling & redaction](https://docs.komodor.com/security-and-governance/architecture-considerations/data-handling-redaction.md): What an agent can see, what is masked automatically, what is not — and the levers that decide how much of your estate ever leaves it.
- [Network & egress control](https://docs.komodor.com/security-and-governance/architecture-considerations/network-egress-control.md): A worker dials out and nothing dials in — and what an agent can reach on the way out is decided by its tool surface, not by its network.
- [Overview](https://docs.komodor.com/developer-tools/overview.md): The four programmatic surfaces — REST API, Python SDK, Go SDK, and MCP server — and which one to reach for.
- [APIs](https://docs.komodor.com/developer-tools/apis.md): The REST API behind the console — base URL, bearer authentication, error and pagination conventions, and the interactive reference.
- [Python SDK](https://docs.komodor.com/developer-tools/python-sdk.md): Build an agent worker in Python — the agent spec, a handler, evidence, run-scoped credentials, and a local test loop before you deploy.
- [Go SDK](https://docs.komodor.com/developer-tools/go-sdk.md): Build an agent worker in Go — one blocking call manages registration, claiming, and telemetry, with no Python in the container.
- [MCP server](https://docs.komodor.com/developer-tools/mcp-server.md): The platform's own capabilities as MCP tools — grouped into toolsets, scopable per connection, and authorized exactly like the API.
- [Connect coding agents](https://docs.komodor.com/developer-tools/connect-coding-agents.md): Wire Claude Code, Codex CLI, or Cursor to your workspace over MCP — including how to pick the workspace when you belong to several.
- [Troubleshooting](https://docs.komodor.com/reference/troubleshooting.md): The problems people actually hit — offline agents, 401s, missing credentials, integration failures, stuck runs — and the checks that fix them.
- [Limits & quotas](https://docs.komodor.com/reference/limits-quotas.md): The caps, sizes, timeouts, and page limits KAOP enforces — what each one is, and what happens when you reach it.
- [What's new](https://docs.komodor.com/reference/changelog.md): Where release notes live, how to read them, and how to keep track of what changed in your own workspace.
- [Support](https://docs.komodor.com/reference/support.md): How to get help with KAOP, what to gather before you ask, and which questions you can answer yourself in seconds.