> For the complete documentation index, see [llms.txt](https://docs.pipekit.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.pipekit.io/concepts/pipekit-agent.md).

# Pipekit Agent

About the Pipekit Agent

The Pipekit Agent is a small application that runs within your Kubernetes cluster. It acts as the conduit to Pipekit's API, allowing you to run Argo Workflows from your local machine or through a Git repository.

The Pipekit Agent triggers Argo Workflows based on the configuration you set in Pipekit. It also sends the status of the Argo Workflow back to Pipekit, allowing you to see the status of your workflows in the Pipekit UI. Optionally, the Pipekit Agent can also send the logs of your Argo Workflows to Pipekit.

## How it is deployed

You install the agent with its [Helm chart](/reference/helm-values/agent.md). From chart `7.0.0`, the chart installs an operator and an `Installation` custom resource, and the operator creates and maintains the agent itself, the metrics collector, and Vector when you enable it.

One operator runs per cluster. The model is one agent for each Argo Workflows controller, each with its own `Installation` resource and its own Pipekit cluster, so a Pipekit cluster maps to an Argo Workflows controller rather than to a Kubernetes cluster. An agent watches every namespace by default, or a single namespace when you scope it. Refer to [Namespace-Scoped Agents](/using-pipekit/clusters/namespaced-agent.md).

## Pipekit Agent Software Bill of Materials (SBOM)

An SBOM for the Pipekit Agent is embedded within the container image in SPDX format. Further information is available on the [SBOM](/why-pipekit/security.md#software-bill-of-materials-sbom) page.