Illustration of Rei Network framework: seamless connection between AI Agent and blockchain

Author: francesco

Compiled by: Shenchao TechFlow

When creating AI agents, a core challenge is how to allow them to learn, iterate, and grow flexibly while ensuring consistency in output results.

Rei provides a framework for sharing structured data between AI and blockchain, enabling AI agents to learn, optimize, and retain a set of experience and knowledge base.

The emergence of this framework makes it possible to develop AI systems with the following capabilities:

• Understand context and patterns and generate valuable insights

• Turn insights into actionable actions while benefiting from the transparency and reliability of blockchain

Challenges faced

There are significant differences in core properties between AI and blockchain, which makes their compatibility face many challenges:

1. Deterministic computation of blockchain: Every step of the blockchain operation must produce completely consistent results on all nodes to ensure:

1. **Consensus** : Each node agrees on the content of the new block and completes verification together.

2. **State Verification** : The state of the blockchain is always traceable and verifiable. Newly added nodes should be able to quickly synchronize to a consistent state with other nodes

3. **Smart contract** **execution** : all nodes must generate consistent outputs given the same input conditions

2. Probabilistic calculations of AI : The output results of AI systems are usually based on probability, which means that each run may result in different results. This feature comes from:

1. **Context** **dependence** : AI performance depends on the context of the input, such as training data, model parameters, and time and environmental conditions

2. **Resource intensive** : AI calculations require high-performance hardware support, including complex matrix operations and large amounts of memory

The above differences raise the following compatibility challenges :

• Conflict between probabilistic and deterministic data

  • How to transform the probabilistic output of AI into the deterministic results required by blockchain?

  • When and where should this transformation be accomplished?

  • How to ensure certainty while retaining the value of probabilistic analysis?

• Gas Cost: The high computing requirements of AI models may result in unaffordable Gas costs, thus limiting their application on the blockchain.

• Memory limitations: The memory capacity of the blockchain environment is limited, making it difficult to meet the storage needs of the AI ​​model.

• Execution time: The block time of the blockchain limits the running speed of the AI ​​model, which may affect its performance.

• Integration of data structures: AI models use complex data structures that are difficult to directly integrate into the blockchain’s storage model.

• Oracle problem (verification requirements): Blockchain relies on oracles to obtain external data, but how to verify the accuracy of AI calculations is still a problem. In particular, AI systems require rich context and low latency, which conflicts with the characteristics of blockchain.

 The original picture comes from francesco, compiled by Shenchao TechFlow

How can AI agents be seamlessly linked with the blockchain?

 The original picture comes from francesco, compiled by Shenchao TechFlow

Rei proposes a brand new solution that combines the advantages of AI and blockchain.

The original picture comes from francesco, compiled by Shenchao TechFlow

Rather than forcibly integrating two completely different systems, AI and blockchain, Rei prefers to act as a "universal translator", allowing the two to communicate and collaborate smoothly through the translation layer.

 The original picture comes from francesco, compiled by Shenchao TechFlow

Rei's core goals include:

• Allow AI agents to think and learn independently
• Translate agent insights into precise and verifiable blockchain operations

 The original picture comes from francesco, compiled by Shenchao TechFlow

The first application of this framework is Unit00x0 (Rei_00 - $REI), which is currently trained as a quantitative analyst.

Rei 's cognitive architecture consists of the following four levels:

1. Thinking Layer: Responsible for processing and collecting raw data, such as chart data, transaction history and user behavior, and looking for potential patterns.
2. Reasoning Layer: On the basis of discovering patterns, it adds contextual information, such as date, time, historical trends and market conditions, to make the data more three-dimensional.
3. Decision Layer: Develop specific action plans based on the contextualized information provided by the reasoning layer.
4. Action Layer: Converts decisions into deterministic operations that can be executed on the blockchain.

Rei 's framework is built on three core pillars:

 The original picture comes from francesco, compiled by Shenchao TechFlow

1. Oracle (oracle, similar to neural pathways): Converts the diverse output of AI into unified results and records them on the blockchain.
2. ERC Data Standard: Expands blockchain storage capabilities, supports data storage of complex patterns, while retaining contextual information generated by the thinking layer and reasoning layer, thereby realizing the transformation from probabilistic data to deterministic execution.
3. Memory System: Allows Rei to accumulate experience over time and recall previous output results and learning results at any time.

Here 's how these interactions look like:

 The original picture comes from francesco, compiled by Shenchao TechFlow

• Oracle Bridge is responsible for identifying data patterns
• ERCData is used to store these schemas
• Memory systems retain contextual information to better understand patterns
• Smart contracts can access this accumulated knowledge and act accordingly

With this architecture, the Rei agent has been able to conduct in-depth analysis of Tokens by combining multi-dimensional information such as on-chain data, price changes, and social sentiments.

What's more, Rei can not only analyze data, but also develop a deeper understanding based on it. This is due to her directly storing her experience and insights on the blockchain, making this information part of her knowledge system and able to be called at any time, thereby continuously optimizing her decision-making capabilities and overall experience.

Rei's data sources include Plotly and Matplotlib libraries (for charting), Coingecko, Defillama, on-chain data, and Twitter's social sentiment data. Through these diverse data sources, Rei is able to provide comprehensive on-chain analysis and market insights.

With the function update of Quant V2 , Rei now supports the following analysis forms:

1. Project analysis: Based on the original functions, new quantitative indicators and sentiment data support have been added. The analysis content includes Candlestick Chart, Engagement Chart, Holder Distribution and PnL. ( Related examples )

2. Inflow and outflow analysis: By monitoring the price and transaction volume of popular Tokens on the chain, Rei can compare these data with capital inflows and outflows to help users discover potential market trends. ( Related examples )

3. Interaction analysis: Evaluate the overall interaction of the project, including comparison of real-time data with data 24 hours ago, and relative price changes. This feature reveals correlations between the latest information and user engagement performance. ( Related examples )

4. Top Category Analysis: Analysis of the lowest transaction volume and highest number of transactions in a single category, highlighting the performance of the project within its category.

5. The first chart shows the volume at the bottom and the number of deals at the top; then drill down into individual categories to reveal how a single project's metrics compare to similar projects. ( Related examples )

In addition, as of January 2025, Rei has supported the on-chain Token buying and selling function . It is equipped with a smart contract wallet based on the ERC-4337 standard , making transactions more convenient and secure.

Rei's smart contract delegates operations to her through user signature authorization, allowing Rei to autonomously manage her portfolio.

The following is Rei’s wallet address:

• EOA wallet (signature wallet) :

• https://basescan.org/address/0x3BC4c3A2a2Fa5ad20a2B95B18CA418D06A360cB

• Smart wallet (account abstract wallet) :

• https://basescan.org/address/0xf6835acc8d2b51e5d47632ca8954bfee9a0ce49c

Use Case: The Versatility of the Rei Framework

 The original picture comes from francesco, compiled by Shenchao TechFlow

The Rei framework is not limited to the financial field, but can also be applied to the following broad scenarios:

• User- agent interaction : supporting content creation

• Market Analysis : Supply Chain Management and Logistics Sector

• Building adaptive systems : governance scenarios

• Risk Assessment : In healthcare, Rei assesses potential risks through contextual analysis

Rei’s future development direction

• Better UI

• Alpha terminal based on Token permissions

• Developer platform