# Quickstart

### Prerequisites

* A Frixion account
* An LLM provider API key (Anthropic, OpenAI, OpenRouter, or any OpenAI-compatible endpoint)
* (Optional) A messaging channel credential if you want to reach your agent via Telegram, Discord, Slack, etc.

### Step 1 — Create a project

From the Frixion dashboard, click **New Project** and give it a name. A project is the top-level container for your agents, wallets, and billing.

```bash
# Or via CLI
frixion project create my-agent
```

### Step 2 — Choose a framework

Frixion currently supports two auto-deployment targets:

| Framework | Best for                                                                                 |
| --------- | ---------------------------------------------------------------------------------------- |
| OpenClaw  | Personal assistants, messaging-first agents, heartbeat-driven automation                 |
| Hermes    | Self-improving agents with persistent skills, research workflows, serverless deployments |

If you're not sure, OpenClaw is the safer default for personal assistant use cases; Hermes is stronger when you care about the agent learning over time.

### Step 3 — Deploy

```bash
frixion deploy --framework openclaw --tier standard
```

Frixion will:

1. Provision a compute instance sized to your tier.
2. Install and configure the chosen framework.
3. Generate a wallet for the agent (see Wallets).
4. Hand you connection details and a dashboard URL.

### Step 4 — Connect your keys

Paste your LLM provider API key into the project's **Secrets** panel. Frixion injects it into the agent's runtime environment — it never leaves your project.

### Step 5 — Talk to your agent

Open the built-in web chat, or plug in a messaging channel:

```bash
frixion channel add telegram --token {BOT_TOKEN}
```

Your agent is now reachable from Telegram.

### Next steps

* Fund your agent's wallet to let it make x402 payments
* Learn how scaling works as your agent's workload grows
* Browse the Configuration Reference to tune behavior


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.frixionai.com/quickstart/quickstart.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.