> For the complete documentation index, see [llms.txt](https://stavr-team.gitbook.io/nodes-guides/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://stavr-team.gitbook.io/nodes-guides/mainnets/sommelier.md).

# Sommelier

<figure><img src="/files/mhVCfaiTSlTEEO7W0Bv0" alt=""><figcaption></figcaption></figure>

Sommelier is a non-custodial, cross-chain platform for executing actively-managed DeFi investment strategies. Community members can create Cellars that execute on an investment strategy through smart contracts. Cellars are powered by Strategy Providers (SPs) who develop trading strategies and send the recommended actions to the Sommelier Validators to be executed on the Cellar with the intention of gaining yield.

Cellars can be strategies like:\
A portfolio of BTC and ETH that is rebalanced based on price trends that machine learning algorithms identify\
An NFT trading strategy that leverages Twitter sentiment around particular collections\
A strategy that hedges liquidity provision on DEXes

Sommelier employs a unique architecture consisting of the Sommelier Cosmos SDK blockchain, an off-chain execution environment that keeps strategies private while allowing them to leverage a wide variety of off-chain data modeling techniques, and one of the best performing ETH bridges. Strategy instructions are passed across this bridge to reposition assets in Cellars. This bridge is also being expanded to allow access to other chains (like Polygon, Avalanche, etc) so strategies are not tied to just high gas ETH markets.

Sommelier aggregates and batches transactions, thereby reducing gas fees, providing an attractive alternative to Ethereum’s high transaction costs. As for security, Sommelier uses a decentralized governance mechanism run by validators, ensuring state-of-the-art safety of user funds. Validators pass strategy instructions across the bridge, but users’ assets are never moved across it, instead being deployed directly into Cellars. Further, Cellars are non-custodial, meaning that users can withdraw their assets at any time, while strategy providers never have ownership of those assets.

&#x20;[WebSite](https://www.sommelier.finance/)\
&#x20;[GitHub](https://github.com/PeggyJV/sommelier)\
&#x20;[EXPLORER MAINNET](https://explorer.stavr.tech/Sommelier-Mainnet/)
------------------------------------------------------------------------

<mark style="color:green;">We will be glad to receive your support</mark>\
[🔥OUR VALIDATOR🔥](https://restake.app/sommelier/sommvaloper1fes322u0x7422ugc05xkxeav2zzd3kfgf898f4)
-----------------------------------------------------------------------------------------------------

* **Minimum hardware requirements**:

| Node Type | CPU | RAM  | Storage |
| --------- | --- | ---- | ------- |
| Mainnet   | 8   | 16GB | 250GB   |

**Public Tools**

* **api:** [**https://som.api.m.stavr.tech**](https://som.api.m.stavr.tech)
* **rpc:** [**https://somm.rpc.m.stavr.tech**](https://somm.rpc.m.stavr.tech/)


---

# 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://stavr-team.gitbook.io/nodes-guides/mainnets/sommelier.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.