Giter Club home page Giter Club logo

agentstark's Introduction

Agent STARK

SN_Ver_0.12.2

Exploration_Team

AgentSTARK is an AI agent framework designed for Starknet. It uses the Account Abstraction and will be used with Giza's AI Agents to operate verifiable machine learning models and enable autonomous actions on Starknet.

How does it work?

skynet_diagram

agentstark's People

Contributors

lana-shanghai avatar raphaeldkhn avatar

Stargazers

 avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

agentstark's Issues

Train an ML algorithm for yield prediction

Description

Train a Machine Learning model for yield prediction on the next time epoch (e.g. day/week).

Requirements

  • Needs to be compatible with Giza CLI
  • Performance should be better than a rolling mean benchmark
  • No lookahead bias introduced in the training or testing process

Add SNIP-9 to An Account Abstraction contract

Description

Add SNIP-9 to the code of an Agent's Account Abstraction contract.

Refer to the standard account functions in the docs.
Use scarb package manager.

Acceptance Criteria

Contract compiles and deploys on Starknet Sepolia successfully.
Contract is able to pass a dummy call to a trivial one value storage update contract.
Test suite passes successfully.

Test SHARP with a Giza model

Depends on SHARP.

SHARP will have a new API feature that will allow to call it and get back a proof.
Test the flow of generating a proof for a simple Giza model.

Prepare a training dataset for the yield prediction on Starknet lending markets

Description

Yield Aggregation can be done with a predictive component. A strategy manager can use a forecasting model to predict the yield from a given pool in the next time epoch. This prediction in turn impacts the asset allocation of the agent.

The first step in introducing this capability is creating a training dataset for the yield prediction algorithm. This dataset should be composed of publicly available data sources, ideally onchain. This is required for the agent to be able to fetch the newest onchain data and make a prediction based on it.

The target variable should be the APY in the next time epoch (e.g. on the next day/week).

Submission

Please create a PR in this repo with a functioning data fetching and processing pipeline, ideally using python for a streamlined integration with the Giza Agent.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.