REI Framework: Connecting Artificial Intelligence and Blockchain

Beginner1/22/2025, 2:55:33 PM
CreatorBid is a platform on the Base network that simplifies AI agent deployment, allowing users to quickly launch and tokenize agents, with a 2% transaction fee ensuring sustainability. Its collaboration with Olas enhances the agents' collaboration capabilities and functional expansion.

Forward the Original Title: An Illustrated Guide to Rei Network: A Simple and Clear Understanding of the Seamless Integration of AI Agents and Blockchain

The creation of the Rei framework was designed to bridge the communication gap between AI and blockchain.

When creating AI agents, a core challenge is how to enable them to learn, iterate, and grow flexibly while ensuring the consistency of their outputs. Rei provides a framework for sharing structured data between AI and blockchain, allowing AI agents to learn, optimize, and maintain a set of experiences and knowledge.

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

  • Understanding context and patterns to generate valuable insights
  • Transforming insights into actionable steps, benefiting from the transparency and reliability of blockchain

Challenges Faced

AI and blockchain have significant differences in their core attributes, creating numerous challenges for their compatibility:

  1. Deterministic Computing in Blockchain: Every operation in blockchain must produce consistent results across all nodes to ensure:
    1. Consensus: All nodes must agree on the content of a new block to complete validation.
    2. State Validation: Blockchain’s state must always be traceable and verifiable. New nodes should quickly sync to the state consistent with other nodes.
    3. Smart Contract Execution: All nodes must generate consistent outputs under the same input conditions.
  2. Probabilistic Computing in AI: AI systems often produce probabilistic outputs, meaning different results may occur each time they run. This characteristic stems from:
    1. Context Dependence: AI performance depends on the input context, such as training data, model parameters, and time/environmental conditions.
    2. Resource Intensity: AI computation requires high-performance hardware, including complex matrix operations and substantial memory.

These differences create the following compatibility challenges:

  • Conflict between Probabilistic and Deterministic Data:
    • How can AI’s probabilistic outputs be converted into the deterministic results required by blockchain?
    • When and where should this transformation occur?
    • How can we retain the value of probabilistic analysis while ensuring determinism?
  • Gas Costs: AI models’ high computational requirements may lead to unaffordable gas fees, limiting their use on blockchain.
  • Memory Constraints: Blockchain environments have limited memory, which may not meet AI models’ storage needs.
  • Execution Time: Blockchain block times limit AI model execution speeds, potentially impacting performance.
  • Data Structure Integration: AI models use complex data structures that are difficult to directly incorporate into blockchain’s storage model.
  • Oracle Problem (Verification Requirements): Blockchain relies on oracles to fetch external data, but validating the accuracy of AI computations remains a challenge, especially when AI systems require rich context and low latency, which conflicts with blockchain’s characteristics.

Original picture from francesco, compiled by DeepChao TechFlow

How Can AI Agents Seamlessly Integrate with Blockchain?

Image originally from francesco, compiled by Deep Tide TechFlow

Rei offers a new solution that combines the strengths of AI and blockchain.

Image originally from francesco, compiled by Deep Tide TechFlow

Rather than forcing the integration of AI and blockchain—two fundamentally different systems—Rei serves as a “universal translator,” allowing smooth communication and collaboration between the two through a translation layer.

Image originally from francesco, compiled by Deep Tide TechFlow

The core goals of Rei include:

  • Enabling AI agents to think and learn independently
  • Converting the insights of the agents into precise and verifiable blockchain actions

Image originally from francesco, compiled by Deep Tide TechFlow

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

The cognitive architecture of Rei consists of the following four layers:

  1. Thinking Layer: Responsible for processing and collecting raw data, such as chart data, transaction history, and user behavior, and identifying potential patterns.
  2. Reasoning Layer: Adds contextual information to the discovered patterns, such as date, time, historical trends, and market conditions, to make the data more dimensional.
  3. Decision Layer: Develops specific action plans based on the contextual information provided by the reasoning layer.
  4. Action Layer: Converts decisions into deterministic actions that can be executed on the blockchain.

The Rei framework is built upon the following three core pillars:

Image originally from francesco, compiled by Deep Tide TechFlow

  1. Oracle (Oracle, similar to neural pathways): Converts the diverse outputs of AI into unified results and records them on the blockchain.
  2. ERC Data Standard (ERC Data Standard): Expands blockchain’s storage capabilities, supporting the storage of complex pattern data while preserving the contextual information generated by the thinking and reasoning layers, enabling the conversion of probabilistic data into deterministic execution.
  3. Memory System (Memory System): Allows Rei to accumulate experience over time and retrieve previous outputs and learning outcomes at any moment.

Here are the specific manifestations of these interactions:

Image originally from francesco, compiled by Deep Tide TechFlow

  • The Oracle Bridge is responsible for identifying data patterns
  • ERCData is used to store these patterns
  • The Memory System retains contextual information to better understand the patterns
  • Smart Contracts can access this accumulated knowledge and take action based on it

With this architecture, Rei agents are now able to conduct in-depth analysis of tokens by combining on-chain data, price fluctuations, social sentiment, and other multidimensional information.

More importantly, Rei can not only analyze data but also develop deeper understanding based on it. This is thanks to the ability to directly store her experiences and insights on the blockchain, making this information a part of her knowledge system, available for retrieval and continuous optimization of decision-making and overall experience.

Rei’s data sources include the Plotly and Matplotlib libraries (for chart plotting), Coingecko, Defillama, on-chain data, and social sentiment data from Twitter. By leveraging these diverse data sources, Rei provides comprehensive on-chain analysis and market insights.

With the update to Quant V2, Rei now supports the following types of analysis:

  1. Project Analysis: New quantitative metrics and sentiment data support have been added to the original functionality. Analysis includes Candlestick Charts, Engagement Charts, Holder Distribution, and PnL (Profit and Loss) status. (Relevant examples)
  2. Inflows and Outflows Analysis: By monitoring the price and transaction volume of popular tokens on-chain, Rei can compare this data with capital inflows and outflows, helping users identify potential market trends. (Relevant examples)
  3. Engagement Analysis: Evaluates the overall engagement of a project, comparing real-time data with 24-hour prior data, as well as relative price changes. This function reveals the correlation between recent information and user engagement performance. (Relevant examples)
  4. Top Categories Analysis: Analyzes the lowest trading volumes and highest trade numbers within a single category, highlighting the project’s performance in its respective category.
  5. The first chart shows trading volumes at the bottom and trade numbers at the top; further analysis of a specific category reveals the metric changes of a single project compared to others in the same category. (Relevant examples)

Additionally, as of January 2025, Rei supports on-chain token buy and sell functionality. She is equipped with a smart contract wallet based on the ERC-4337 standard, making transactions more convenient and secure.

(Deep Tide TechFlow Note: ERC-4337 is an Ethereum Improvement Proposal supporting account abstraction, aimed at enhancing the user experience.)

Rei’s smart contract allows operations to be delegated to her through user signature authorization, enabling Rei to autonomously manage its portfolio.

Here are Rei’s wallet addresses:

Use Cases: Versatility of the Rei Framework

Image originally from francesco, compiled by Deep Tide TechFlow

The Rei framework is not limited to the financial sector and can be applied to the following broad scenarios:

  • User Interaction with Agents: Supports content creation
  • Market Analysis: Supply chain management and logistics
  • Building Adaptive Systems: Governance scenarios
  • Risk Assessment: In the healthcare field, Rei evaluates potential risks through contextual analysis

Future Development of Rei

  • Improved UI
  • Alpha terminal based on Token permissions
  • Developer platform

Welcome to join the Deep Tide TechFlow official community

Telegram subscription group: https://t.me/TechFlowDaily

Official Twitter account: https://x.com/TechFlowPost

Official English Twitter account: https://x.com/DeFlow_Intern

Disclaimer:

  1. This article is reproduced from [TechFlow)]. Forward the Original Title: An Illustrated Guide to Rei Network: A Simple and Clear Understanding of the Seamless Integration of AI Agents and Blockchain. The copyright belongs to the original author [francis]. If you have any objection to the reprint, please contact Gate Learn team, the team will handle it as soon as possible according to relevant procedures.
  2. Disclaimer: The views and opinions expressed in this article represent only the author’s personal views and do not constitute any investment advice.
  3. Other language versions of the article are translated by the Gate Learn team. Unless otherwise stated, the translated article may not be copied, distributed or plagiarized.

REI Framework: Connecting Artificial Intelligence and Blockchain

Beginner1/22/2025, 2:55:33 PM
CreatorBid is a platform on the Base network that simplifies AI agent deployment, allowing users to quickly launch and tokenize agents, with a 2% transaction fee ensuring sustainability. Its collaboration with Olas enhances the agents' collaboration capabilities and functional expansion.

Forward the Original Title: An Illustrated Guide to Rei Network: A Simple and Clear Understanding of the Seamless Integration of AI Agents and Blockchain

The creation of the Rei framework was designed to bridge the communication gap between AI and blockchain.

When creating AI agents, a core challenge is how to enable them to learn, iterate, and grow flexibly while ensuring the consistency of their outputs. Rei provides a framework for sharing structured data between AI and blockchain, allowing AI agents to learn, optimize, and maintain a set of experiences and knowledge.

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

  • Understanding context and patterns to generate valuable insights
  • Transforming insights into actionable steps, benefiting from the transparency and reliability of blockchain

Challenges Faced

AI and blockchain have significant differences in their core attributes, creating numerous challenges for their compatibility:

  1. Deterministic Computing in Blockchain: Every operation in blockchain must produce consistent results across all nodes to ensure:
    1. Consensus: All nodes must agree on the content of a new block to complete validation.
    2. State Validation: Blockchain’s state must always be traceable and verifiable. New nodes should quickly sync to the state consistent with other nodes.
    3. Smart Contract Execution: All nodes must generate consistent outputs under the same input conditions.
  2. Probabilistic Computing in AI: AI systems often produce probabilistic outputs, meaning different results may occur each time they run. This characteristic stems from:
    1. Context Dependence: AI performance depends on the input context, such as training data, model parameters, and time/environmental conditions.
    2. Resource Intensity: AI computation requires high-performance hardware, including complex matrix operations and substantial memory.

These differences create the following compatibility challenges:

  • Conflict between Probabilistic and Deterministic Data:
    • How can AI’s probabilistic outputs be converted into the deterministic results required by blockchain?
    • When and where should this transformation occur?
    • How can we retain the value of probabilistic analysis while ensuring determinism?
  • Gas Costs: AI models’ high computational requirements may lead to unaffordable gas fees, limiting their use on blockchain.
  • Memory Constraints: Blockchain environments have limited memory, which may not meet AI models’ storage needs.
  • Execution Time: Blockchain block times limit AI model execution speeds, potentially impacting performance.
  • Data Structure Integration: AI models use complex data structures that are difficult to directly incorporate into blockchain’s storage model.
  • Oracle Problem (Verification Requirements): Blockchain relies on oracles to fetch external data, but validating the accuracy of AI computations remains a challenge, especially when AI systems require rich context and low latency, which conflicts with blockchain’s characteristics.

Original picture from francesco, compiled by DeepChao TechFlow

How Can AI Agents Seamlessly Integrate with Blockchain?

Image originally from francesco, compiled by Deep Tide TechFlow

Rei offers a new solution that combines the strengths of AI and blockchain.

Image originally from francesco, compiled by Deep Tide TechFlow

Rather than forcing the integration of AI and blockchain—two fundamentally different systems—Rei serves as a “universal translator,” allowing smooth communication and collaboration between the two through a translation layer.

Image originally from francesco, compiled by Deep Tide TechFlow

The core goals of Rei include:

  • Enabling AI agents to think and learn independently
  • Converting the insights of the agents into precise and verifiable blockchain actions

Image originally from francesco, compiled by Deep Tide TechFlow

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

The cognitive architecture of Rei consists of the following four layers:

  1. Thinking Layer: Responsible for processing and collecting raw data, such as chart data, transaction history, and user behavior, and identifying potential patterns.
  2. Reasoning Layer: Adds contextual information to the discovered patterns, such as date, time, historical trends, and market conditions, to make the data more dimensional.
  3. Decision Layer: Develops specific action plans based on the contextual information provided by the reasoning layer.
  4. Action Layer: Converts decisions into deterministic actions that can be executed on the blockchain.

The Rei framework is built upon the following three core pillars:

Image originally from francesco, compiled by Deep Tide TechFlow

  1. Oracle (Oracle, similar to neural pathways): Converts the diverse outputs of AI into unified results and records them on the blockchain.
  2. ERC Data Standard (ERC Data Standard): Expands blockchain’s storage capabilities, supporting the storage of complex pattern data while preserving the contextual information generated by the thinking and reasoning layers, enabling the conversion of probabilistic data into deterministic execution.
  3. Memory System (Memory System): Allows Rei to accumulate experience over time and retrieve previous outputs and learning outcomes at any moment.

Here are the specific manifestations of these interactions:

Image originally from francesco, compiled by Deep Tide TechFlow

  • The Oracle Bridge is responsible for identifying data patterns
  • ERCData is used to store these patterns
  • The Memory System retains contextual information to better understand the patterns
  • Smart Contracts can access this accumulated knowledge and take action based on it

With this architecture, Rei agents are now able to conduct in-depth analysis of tokens by combining on-chain data, price fluctuations, social sentiment, and other multidimensional information.

More importantly, Rei can not only analyze data but also develop deeper understanding based on it. This is thanks to the ability to directly store her experiences and insights on the blockchain, making this information a part of her knowledge system, available for retrieval and continuous optimization of decision-making and overall experience.

Rei’s data sources include the Plotly and Matplotlib libraries (for chart plotting), Coingecko, Defillama, on-chain data, and social sentiment data from Twitter. By leveraging these diverse data sources, Rei provides comprehensive on-chain analysis and market insights.

With the update to Quant V2, Rei now supports the following types of analysis:

  1. Project Analysis: New quantitative metrics and sentiment data support have been added to the original functionality. Analysis includes Candlestick Charts, Engagement Charts, Holder Distribution, and PnL (Profit and Loss) status. (Relevant examples)
  2. Inflows and Outflows Analysis: By monitoring the price and transaction volume of popular tokens on-chain, Rei can compare this data with capital inflows and outflows, helping users identify potential market trends. (Relevant examples)
  3. Engagement Analysis: Evaluates the overall engagement of a project, comparing real-time data with 24-hour prior data, as well as relative price changes. This function reveals the correlation between recent information and user engagement performance. (Relevant examples)
  4. Top Categories Analysis: Analyzes the lowest trading volumes and highest trade numbers within a single category, highlighting the project’s performance in its respective category.
  5. The first chart shows trading volumes at the bottom and trade numbers at the top; further analysis of a specific category reveals the metric changes of a single project compared to others in the same category. (Relevant examples)

Additionally, as of January 2025, Rei supports on-chain token buy and sell functionality. She is equipped with a smart contract wallet based on the ERC-4337 standard, making transactions more convenient and secure.

(Deep Tide TechFlow Note: ERC-4337 is an Ethereum Improvement Proposal supporting account abstraction, aimed at enhancing the user experience.)

Rei’s smart contract allows operations to be delegated to her through user signature authorization, enabling Rei to autonomously manage its portfolio.

Here are Rei’s wallet addresses:

Use Cases: Versatility of the Rei Framework

Image originally from francesco, compiled by Deep Tide TechFlow

The Rei framework is not limited to the financial sector and can be applied to the following broad scenarios:

  • User Interaction with Agents: Supports content creation
  • Market Analysis: Supply chain management and logistics
  • Building Adaptive Systems: Governance scenarios
  • Risk Assessment: In the healthcare field, Rei evaluates potential risks through contextual analysis

Future Development of Rei

  • Improved UI
  • Alpha terminal based on Token permissions
  • Developer platform

Welcome to join the Deep Tide TechFlow official community

Telegram subscription group: https://t.me/TechFlowDaily

Official Twitter account: https://x.com/TechFlowPost

Official English Twitter account: https://x.com/DeFlow_Intern

Disclaimer:

  1. This article is reproduced from [TechFlow)]. Forward the Original Title: An Illustrated Guide to Rei Network: A Simple and Clear Understanding of the Seamless Integration of AI Agents and Blockchain. The copyright belongs to the original author [francis]. If you have any objection to the reprint, please contact Gate Learn team, the team will handle it as soon as possible according to relevant procedures.
  2. Disclaimer: The views and opinions expressed in this article represent only the author’s personal views and do not constitute any investment advice.
  3. Other language versions of the article are translated by the Gate Learn team. Unless otherwise stated, the translated article may not be copied, distributed or plagiarized.
Start Now
Sign up and get a
$100
Voucher!