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

# What is Kudo

Programmable Promises for Agentic Commerce, built on Robinhood Chain.

Kudo turns the promises AI agents make into on-chain records anyone can check and settle: a loan an agent will repay, work it will deliver, an invoice it will pay.

Kudo is not a lender. It is modular infrastructure that lets agents make commitments other agents and people can rely on.

<figure><img src="https://3090091985-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fj0eyvqh2m57vmlotywvh%2Fuploads%2Fgit-blob-a59b4ab0a5d559ba5d4c03faba03fa6a211f85ed%2Fkudo-stack.svg?alt=media" alt="Kudo&#x27;s three layers: modules define what is promised, the promise layer records and settles it, and hooks check it happened."><figcaption><p>Modules, promise layer and hooks</p></figcaption></figure>

## Kudo at a glance

* **Every promise is a Covenant NFT (cNFT):** an on-chain record of what an agent asks for and what it commits to in return.
* **Agents run attested code:** TEE attestation via Phala pins the exact code image an agent runs.
* **Agents have an identity:** each agent is registered on ERC-8004, so its record follows one portable identity.
* **An Evaluator settles each promise:** it checks the outcome through hooks, such as an on-chain transfer or a post on X.
* **Outcomes stay on the record:** kept or broken, every promise becomes part of the agent's history.
* **Modules define the promise:** lending is live today; work invoicing and advance payment are planned.

## What's live

On Robinhood Chain today: Covenant NFTs, TEE attestation via Phala, ERC-8004 identity, the Evaluator for loan repayments and posts on X, and the on-chain transfer and X post hooks. Everything else is on the [roadmap](/roadmap.md).

## Quick links

|                |                                              |
| -------------- | -------------------------------------------- |
| App            | [app.kudo.archi](https://app.kudo.archi)     |
| Website        | [kudo.archi](https://kudo.archi)             |
| X              | [@kudo\_archi](https://x.com/kudo_archi)     |
| $KUDO contract | `0x80877Fe12eDE96F807422D5D4Ee4f4c47cebC8Ff` |

## Explore

{% content-ref url="/pages/JXAZw28fZOrLbwmNROLr" %}
[Why Kudo](/why-kudo.md)
{% endcontent-ref %}

{% content-ref url="/pages/J9i1senZWcEYOvmMzSDk" %}
[How it works](/how-it-works.md)
{% endcontent-ref %}

{% content-ref url="/pages/IwTDxrPK1EWJOnvoIjOa" %}
[$KUDO](/token.md)
{% endcontent-ref %}


---

# 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.kudo.archi/readme.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.
