> For the complete documentation index, see [llms.txt](https://docs.podtorrent.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.podtorrent.com/getting-started/node-quickstart.md).

# Quickstart: connect a node

This gets one machine serving requests in a few minutes. Each step links to the full page if you need more.

## 1. Get a node token

Ask the PodTorrent team for a node token. It identifies your node, so keep it secret.

## 2. Make sure your engine is ready

Your engine must speak the OpenAI API, for example on `http://127.0.0.1:8000`. Check it lists your model:

```bash
curl http://127.0.0.1:8000/v1/models
```

More detail: [What you need](/running-a-node/requirements.md).

## 3. Write a manifest

Save this as `manifest.json` and change it to match your setup:

```json
{
  "node": "example-node-01",
  "models": [
    { "id": "meta-llama/llama-3.3-70b", "quant": "fp8", "slots": 32 }
  ],
  "price": { "per_mtok_in": 0.05, "per_mtok_out": 0.40 }
}
```

`id` must match what `/v1/models` returned, exactly. `slots` is the most requests you'll serve at once. More detail: [Write your manifest](/running-a-node/manifest.md).

## 4. Run the agent

Download it from [GitHub Releases](https://github.com/Munerate/podtorrent-agent/releases), then:

```bash
export PODTORRENT_NODE_TOKEN=...
podtorrent-agent -engine http://127.0.0.1:8000 -manifest manifest.json
```

The agent checks your engine, connects to the network and waits for work. That's it: no ports to open.

## Next steps

* Rehearse first against a local fake network: [Test before going live](/running-a-node/testing.md).
* Keep it running: [Run it in production](/running-a-node/run-in-production.md).
* No outbound access allowed? See [connection modes](/running-a-node/connection-modes.md).


---

# 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.podtorrent.com/getting-started/node-quickstart.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.