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

# Platform

## Dashboard

| Metric             | Description                         |
| ------------------ | ----------------------------------- |
| $ Balance          | Current monetary balance            |
| Total uptime       | Cumulative uptime across all agents |
| Created Agents     | Total agents in your account        |
| AI Credits Balance | Available credits                   |

**Running Agents** — lists every agent in Running state. Empty means no agents are active.

***

## Credits

Credits power LLM usage and compute.

### Buying credits

Go to **Profile → Buy AI Credits with USDC**.

| Pack     | Credits | Price    |
| -------- | ------- | -------- |
| Starter  | 10,000  | 10 USDC  |
| Standard | 50,000  | 45 USDC  |
| Pro      | 120,000 | 100 USDC |

> Balance always visible top-right of the console.

### What consumes credits

**LLM usage** — every message processed. More capable models cost more per interaction.

**Compute** — consumed while agent is in Running state. Stops when agent is stopped.

### Monitoring usage

From **Agent data → Model section**:

| Field       | Description                             |
| ----------- | --------------------------------------- |
| Total spend | Cumulative cost for this agent          |
| Spend limit | Configurable cap (Unlimited by default) |
| Rate limit  | Max requests per time window            |

***

## Profile

| Field       | Description                      |
| ----------- | -------------------------------- |
| Public name | Display name across the platform |
| Email       | Account email                    |

**Wallet Settings** — connect an EVM-compatible wallet to purchase credits with USDC.

***

## Agent Identity Layer

> Coming soon.

Every agent will receive a cryptographic identity — verifiable, tamper-proof, and portable.

| Feature                | Description                                                                           |
| ---------------------- | ------------------------------------------------------------------------------------- |
| Cryptographic Identity | Unique Ed25519 keypair per agent. Every action is signed and tamper-proof.            |
| On-Chain Anchoring     | Identity hash anchored to blockchain. Public verification. Portable across platforms. |
| Agent-to-Agent Auth    | Agents prove authorship and verify messages. No spoofing.                             |

***

## Agentic Payments

> Coming soon.

Agents will make and receive payments autonomously under programmable constraints you define.

```
Agent A → calls Agent B
Agent B → charges 0.01 USDC
Policy  → validates
Payment → settles in < 1s
```

| Control                 | Description                                                                   |
| ----------------------- | ----------------------------------------------------------------------------- |
| Delegated Authority     | Spending limits, approved recipients, policy rules — agents can't exceed them |
| Agent-to-Agent Commerce | Agents charge per execution and purchase capabilities programmatically        |
| Enterprise Control      | Budget caps, manual approval thresholds, full audit trail                     |

***


---

# 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 dynamically by asking a question.

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

```
GET https://docs.guayaba.run/platform.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.