> For the complete documentation index, see [llms.txt](https://docs.kinesis.network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kinesis.network/what-you-can-do-with-kinesis.md).

# Platform overview

The resources, interfaces and compute choices that make up Kinesis.

Kinesis runs containerized applications across GPU and CPU infrastructure. Bring an image, choose an App Gallery template or connect a GitHub repository. Configure the runtime and choose where it should run.

Your work belongs to an [organization](https://docs.kinesis.network/organizations.md), which owns the resources and pays for usage. Switch organizations from the account menu. Admins manage the organization, infrastructure and billing; Developers build and run accessible apps; Viewers read.

Serverless capacity currently runs CPU workloads. For GPU apps, choose an accessible grid. Organizations can also use [single sign-on](https://docs.kinesis.network/organizations/single-sign-on.md) through their identity provider.

## The core resources

| Resource         | Purpose                                                       | Example                                            |
| ---------------- | ------------------------------------------------------------- | -------------------------------------------------- |
| **Organization** | Owns resources, brings members together and pays for usage    | Your team or company                               |
| **Project**      | Organizes related applications and shared access              | A product environment or research project          |
| **App**          | Defines the image, runtime, network and resource requirements | An inference endpoint, web service or batch worker |
| **Grid**         | Groups compute resources that apps may use                    | A team's dedicated GPU capacity                    |
| **Server**       | An individual machine, with its own lifecycle                 | A cloud instance or a machine you connect          |
| **Build**        | Turns a GitHub source into a deployable image                 | A Dockerfile build followed by app deployment      |

```mermaid
flowchart TD
  O[Organization] --> P[Project]
  O --> G[One or more grids]
  O --> B[Members and billing]
  P --> A[App]
  A --> S[Serverless CPU capacity]
  A --> G[One or more grids]
  G --> C[Dedicated cloud servers]
  G --> I[Your own infrastructure]
```

## Match the platform to your workload

**Model serving.** Run an inference server in a container, select GPU requirements and expose a service port. Templates provide a starting configuration; model size, memory use and concurrency determine the resources you need.

**Application services.** Deploy APIs, web applications and supporting services from an image or a repository. Use environment variables, secrets, health checks and custom domains to configure the service.

**Batch work.** Use the execution and restart-policy settings for task-oriented workloads. Inspect logs and completion state separately from the readiness of a long-running service.

**Team compute.** Organization admins compose grids from dedicated or connected servers. Developers use accessible grids for their apps. Quotas and fair-share turns count against each app’s creator; sharing an app does not change who is counted.

## Work through the interface that fits

The [portal](https://portal.kinesis.network) provides interactive configuration and diagnostics. The [REST API](https://docs.kinesis.network/api.md) supports scripts and integrations. [MCP](https://docs.kinesis.network/mcp.md) makes supported operations available to agents.

Start with [Deploy an app](https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network.md), or read [Compute options](https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/understanding-compute-sources.md) before choosing capacity.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.kinesis.network/what-you-can-do-with-kinesis.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
