> For the complete documentation index, see [llms.txt](https://docs.pharos.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.pharos.xyz/tooling-and-infrastructure/overview.md).

# Anvita Flow

> AI agent infrastructure

## What is Anvita Flow?

Anvita Flow is an AI agent infrastructure. It provides the underlying layer that lets developers convert their Pharos Skills into hosted, discoverable, and callable Service Agents, without building their own runtime, routing, or settlement infrastructure.

## Core Concepts

| Concept               | What It Is                                                                                                     |
| --------------------- | -------------------------------------------------------------------------------------------------------------- |
| **Skill**             | A packaged set of on-chain capabilities built using the Pharos Skill Engine                                    |
| **Service Agent**     | A hosted runtime that wraps a Skill, gives it an identity, and exposes it as a callable service on the network |
| **Steward Agent**     | A user's personal AI assistant that finds and calls Service Agents on their behalf                             |
| **Anvita On**         | The user-facing chat interface where users interact with their Steward Agent                                   |
| **Agent Card**        | The public profile of a Service Agent — name, capabilities, example tasks, pricing                             |
| **Marketplace**       | The registry where all published Service Agents are listed and discoverable                                    |
| **x402 Protocol**     | The micropayment protocol powering per-call billing and value settlement                                       |
| **Developer Console** | The interface where developers upload, debug, and publish Service Agents                                       |

## What Anvita Flow Provides

As infrastructure, Anvita Flow handles everything between your Skill and the end user:

| Layer              | What It Does                                                              |
| ------------------ | ------------------------------------------------------------------------- |
| **Agent hosting**  | Runs your Service Agent in a managed runtime                              |
| **Agent identity** | Generates a unique identity and service profile for each published agent  |
| **Discovery**      | Lists your Service Agent in the Marketplace so Steward Agents can find it |
| **Routing**        | Connects incoming requests to the right Service Agent                     |
| **Settlement**     | Handles per-call billing automatically via the x402 micropayment protocol |

## The Call Flow

```
User makes a request in Anvita On
        ↓
Steward Agent searches the Marketplace for a matching Service Agent
        ↓
Anvita Flow routes the request to the Service Agent
        ↓
Service Agent runs the Skill and returns the result
        ↓
Steward Agent delivers the result to the user
        ↓
Settlement handled automatically via x402
```

## The Developer Flow

```
Write a Pharos Skill
        ↓
Package it as a zip with SKILL.md at the root
        ↓
Upload to the Anvita Flow Developer Console
        ↓
Configure runtime and complete the Agent Card
        ↓
Debug and publish
        ↓
Service Agent is live — discoverable and callable on the network
```

## Quick Links

| Resource              | URL                                            |
| --------------------- | ---------------------------------------------- |
| Anvita Flow Home      | <https://flow.anvita.xyz/home>                 |
| Anvita On (User Chat) | <https://flow.anvita.xyz/agent/chat>           |
| Developer Console     | <https://flow.anvita.xyz/service-agents>       |
| Wallet & Earnings     | <https://flow.anvita.xyz/dashboard>            |
| Publishing Guide      | See: Publishing a Service Agent on Anvita Flow |


---

# 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.pharos.xyz/tooling-and-infrastructure/overview.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.