# Table of Contents - [Intro | 0xReisearch](#intro-0xreisearch) - [System Architecture Overview | 0xReisearch](#system-architecture-overview-0xreisearch) - [Framework Components | 0xReisearch](#framework-components-0xreisearch) - [The Oracle Bridge | 0xReisearch](#the-oracle-bridge-0xreisearch) - [Memory Systems & State Management | 0xReisearch](#memory-systems-state-management-0xreisearch) - [Component Interaction Flow | 0xReisearch](#component-interaction-flow-0xreisearch) - [ERCData Standard | 0xReisearch](#ercdata-standard-0xreisearch) - [Tech Stack (Legacy) | 0xReisearch](#tech-stack-legacy-0xreisearch) - [Social Interaction & Real-time Processing | 0xReisearch](#social-interaction-real-time-processing-0xreisearch) - [Catalog | 0xReisearch](#catalog-0xreisearch) - [//Welcome | 0xReisearch](#-welcome-0xreisearch) - [//REI_00 (X version, Legacy, Update TBA) | 0xReisearch](#-rei-00-x-version-legacy-update-tba-0xreisearch) - [//Factory & Core API/SDK (Cross-Framework) | 0xReisearch](#-factory-core-api-sdk-cross-framework-0xreisearch) - [Evolution | 0xReisearch](#evolution-0xreisearch) - [API reference | 0xReisearch](#api-reference-0xreisearch) - [GET Reigent | 0xReisearch](#get-reigent-0xreisearch) - [Research | 0xReisearch](#research-0xreisearch) - [Integration with Existing Agents | 0xReisearch](#integration-with-existing-agents-0xreisearch) - [//Core | 0xReisearch](#-core-0xreisearch) - [How to get your API key | 0xReisearch](#how-to-get-your-api-key-0xreisearch) - [REI: A New Kind of Blockchain Intelligence | 0xReisearch](#rei-a-new-kind-of-blockchain-intelligence-0xreisearch) - [Additional Capability (Provided & Custom) | 0xReisearch](#additional-capability-provided-custom-0xreisearch) - [Chat Completion | 0xReisearch](#chat-completion-0xreisearch) - [Reigent Factory | 0xReisearch](#reigent-factory-0xreisearch) - [Intro (legacy) | 0xReisearch](#intro-legacy-0xreisearch) - [Tokenomics | 0xReisearch](#tokenomics-0xreisearch) - [Surface Level Summary : Super Agents | 0xReisearch](#surface-level-summary-super-agents-0xreisearch) - [REI's Cognitive Layers | 0xReisearch](#rei-s-cognitive-layers-0xreisearch) - [Custom Tools | 0xReisearch](#custom-tools-0xreisearch) - [DeFi (Current Level : 1) | 0xReisearch](#defi-current-level-1-0xreisearch) --- # Intro | 0xReisearch We've developed a solution to what we always considered as constraint. Rather than confining agents to predetermined operational boundaries, our architecture implements a universal connectivity layer that facilitates seamless integration across diverse systems. This functions essentially as a universal adapter—preserving agent functionality while enabling interaction with any compatible external architecture. The architecture's elegance lies in its integrative methodology. Agents analyze patterns and generate insights that are subsequently transformed into universally compatible formats. This translation mechanism expands the potential for applications capable of cognitive adaptation while maintaining their core functional integrity. This represents merely the initial implementation. Core provides developers with a foundational architecture for innovation, whether developing novel interactive systems, analytical frameworks, or entirely unprecedented applications. The potential use cases are virtually unlimited. This documentation provides comprehensive coverage—from technical specifications to development guidelines and implementation possibilities. Whether your objective is immediate development, conceptual exploration, or examination of potential applications for adaptive agents, this resource addresses your requirements. Core maintains an open architecture to encourage widespread adoption and enhancement. We are advancing the boundaries of intelligent agent capabilities and invite the broader community to extend these innovations further. [Previous//Welcome](/0xreisearch) [NextTech Stack (Legacy)](/0xreisearch/tech-stack-legacy) Last updated 21 days ago ![Page cover image](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FT1qO0dP660xIav45ywFB%252FIMG_FallingGirl_FIX03.jpg%3Falt%3Dmedia%26token%3D23c927e3-33e8-4e88-9f4f-082d2940ee0c&width=1248&dpr=4&quality=100&sign=f47a58e3&sv=2) --- # System Architecture Overview | 0xReisearch [PreviousTech Stack (Legacy)](/0xreisearch/tech-stack-legacy) [NextComponent Interaction Flow](/0xreisearch/tech-stack-legacy/component-interaction-flow) Last updated 4 months ago ### [](#system-architecture-overview) System Architecture Overview At its core, the REI Framework represents a new approach to blockchain system architecture. While traditional blockchain systems focus on deterministic execution and state management, our architecture introduces sophisticated AI capabilities without compromising blockchain's fundamental properties. The architecture begins with an Integration Layer that manages all external interactions. This layer serves as the gateway to the framework's capabilities, initially through our reference implementations and eventually opening up for broader protocol integration. Behind this gateway lie the framework's core systems: the Oracle System and ERCData System. These components work in concert to enable sophisticated AI capabilities while maintaining blockchain's deterministic properties. The Oracle System handles the complex task of bridging AI computation with blockchain execution, while the ERCData System provides a new paradigm for storing and managing AI-generated insights on-chain. ### [](#component-interaction-flow) Component Interaction Flow Understanding how these components interact reveals the elegance of the architecture. Rather than forcing direct integration between incompatible systems, the framework creates a sophisticated flow of information and computation: When a query enters the system, it triggers a cascade of intelligent processing. The Oracle System first gathers relevant context from the Memory Systems, enabling informed processing that takes into account historical patterns and learned insights. The results are then structured and stored on-chain, updating both the blockchain state and the system's understanding for future interactions. ### [](#key-technologies-used) Key Technologies Used The framework's capabilities stem from the careful selection and integration of key technologies. At the processing layer, advanced natural language understanding enables sophisticated interaction with users and systems. The integration layer leverages high-performance computing to manage real-time processing demands, while the blockchain layer ensures all operations maintain perfect determinism. ### [](#design-principles) Design Principles The REI Framework's design emerges from a deep understanding of both blockchain's requirements and AI's capabilities. Rather than forcing these technologies together, we've created an architecture that allows each to operate in its optimal environment while maintaining meaningful interaction. This design enables the framework to evolve naturally. What begins as a controlled demonstration through our reference implementations will grow into a comprehensive framework for blockchain-AI integration, available to protocols and developers across the ecosystem. The architecture anticipates this growth, implementing systems that can scale with increasing demand while maintaining security and efficiency. Every component is designed not just for current requirements, but for the future expansion of capabilities and use cases. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FngH6SImZhwVczHf4Tceb%252FScreenshot%25202024-11-13%2520at%252010.19.51.png%3Falt%3Dmedia%26token%3Df043bf69-5ec1-4bbf-b8bc-56dc0c8cdf75&width=768&dpr=4&quality=100&sign=f05eae3a&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FInGx4pkdjqRWOJocKtzQ%252FScreenshot%25202024-11-13%2520at%252010.20.14.png%3Falt%3Dmedia%26token%3Daabf53d2-ac84-43b8-9d4d-635bdf9f744a&width=768&dpr=4&quality=100&sign=268241a9&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F40A3f5PMURoEZIZmysQb%252FScreenshot%25202024-11-13%2520at%252010.20.39.png%3Falt%3Dmedia%26token%3D1f875bfc-fc9f-4349-b3ae-e54896d1ce95&width=768&dpr=4&quality=100&sign=9630e30e&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FBslWvtGskrbMrcrcyLXu%252FScreenshot%25202024-11-13%2520at%252010.21.02.png%3Falt%3Dmedia%26token%3D8d3144ea-e19c-4af4-8044-291846640181&width=768&dpr=4&quality=100&sign=404b0067&sv=2) --- # Framework Components | 0xReisearch [The Oracle Bridge](/0xreisearch/tech-stack-legacy/framework-components/the-oracle-bridge) [ERCData Standard](/0xreisearch/tech-stack-legacy/framework-components/ercdata-standard) [Memory Systems & State Management](/0xreisearch/tech-stack-legacy/framework-components/memory-systems-and-state-management) [PreviousComponent Interaction Flow](/0xreisearch/tech-stack-legacy/component-interaction-flow) [NextThe Oracle Bridge](/0xreisearch/tech-stack-legacy/framework-components/the-oracle-bridge) --- # The Oracle Bridge | 0xReisearch [PreviousFramework Components](/0xreisearch/tech-stack-legacy/framework-components) [NextERCData Standard](/0xreisearch/tech-stack-legacy/framework-components/ercdata-standard) Last updated 4 months ago The Oracle Bridge represents a fundamental advancement in blockchain oracle technology. Unlike traditional oracles that simply relay external data to smart contracts, our system acts as an intelligent intermediary between AI capabilities and blockchain environments. It's designed to process complex queries, maintain context awareness, and ensure deterministic outputs while enabling sophisticated AI interactions. ### [](#architecture-overview) Architecture Overview ### [](#query-flow-and-processing) Query Flow and Processing When a query enters the Oracle Bridge, it undergoes a sophisticated processing flow: ### [](#intelligence-layer) Intelligence Layer The Oracle's intelligence layer enables sophisticated processing while maintaining deterministic outputs: This dual-layer architecture ensures that complex AI operations can occur while maintaining blockchain's requirements for deterministic execution. ### [](#context-awareness) Context Awareness One of the Oracle's most powerful features is its context awareness system: The context system maintains awareness of: * Historical interactions and patterns * Current blockchain state * Recognized relationships * Temporal context * Query patterns ### [](#verification-and-security) Verification and Security The Oracle implements sophisticated verification mechanisms: Every output is verified for: * Deterministic reproducibility * Format compliance * State consistency * Data integrity ### [](#integration-interface) Integration Interface The Oracle System provides clear integration points for protocols: Future protocol integration will enable direct access to Oracle capabilities through a sophisticated API system. Each query will be: * Validated for security * Assessed for complexity * Allocated appropriate resources * Processed efficiently * Verified before delivery ### [](#resource-management) Resource Management The Oracle implements advanced resource management: This ensures efficient processing while maintaining system performance under varying loads. ### [](#future-capabilities) Future Capabilities The Oracle System is designed for evolution. Its modular design enables: * New processing capabilities * Enhanced pattern recognition * Extended context awareness * Improved efficiency ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FSICOuZkul2QZCuVYrHMT%252FScreenshot%25202024-11-13%2520at%252010.25.43.png%3Falt%3Dmedia%26token%3D1afaa667-920f-4977-baa3-8b1268db0e7a&width=768&dpr=4&quality=100&sign=e4ed3225&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F6660Ll5i94N8RYc63mK4%252FScreenshot%25202024-11-13%2520at%252010.26.09.png%3Falt%3Dmedia%26token%3D144e9a06-db42-4d01-a535-5dae76ae0f6f&width=768&dpr=4&quality=100&sign=1b36af19&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FOUSIOiPK0iQ5HolpcUbK%252FScreenshot%25202024-11-13%2520at%252010.26.42.png%3Falt%3Dmedia%26token%3Dd86eaa8d-b38c-489c-8a99-4cef1f6bc839&width=768&dpr=4&quality=100&sign=543758cd&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FDwwKKmpDQMm66MNrI0zb%252FScreenshot%25202024-11-13%2520at%252010.27.02.png%3Falt%3Dmedia%26token%3D9ece6a5a-2021-40d1-8118-029d5d3d1773&width=768&dpr=4&quality=100&sign=b967634c&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FO0dwFO7XcGVqzYkufXLW%252FScreenshot%25202024-11-13%2520at%252010.27.23.png%3Falt%3Dmedia%26token%3D0bf8dffa-7694-4de2-aab0-47523e44d71c&width=768&dpr=4&quality=100&sign=e09eac19&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FhYYrGkjieHECpQsgm5V2%252FScreenshot%25202024-11-13%2520at%252010.28.25.png%3Falt%3Dmedia%26token%3D9164b197-1866-4bbe-a8d2-744bead6a948&width=768&dpr=4&quality=100&sign=e061ac74&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252Flnu1KGwj6t7pcWCVox02%252FScreenshot%25202024-11-13%2520at%252010.29.25.png%3Falt%3Dmedia%26token%3D848370d3-484a-4b5a-b91c-c8165f8dca3b&width=768&dpr=4&quality=100&sign=cacb7344&sv=2) --- # Memory Systems & State Management | 0xReisearch [PreviousERCData Standard](/0xreisearch/tech-stack-legacy/framework-components/ercdata-standard) [Next//REI\_00 (X version, Legacy, Update TBA)](/0xreisearch/rei_00-x-version-legacy-update-tba) Last updated 4 months ago While the Oracle and ERCData systems handle processing and storage, the Memory and State Management systems form the cognitive backbone of the framework, in the occasions where it's needed. These systems enable learning and adaptation while maintaining blockchain's deterministic nature. ### [](#memory-architecture) Memory Architecture ### [](#memory-flow-system) Memory Flow System The interaction between different memory types enables sophisticated processing while maintaining deterministic outputs: ### [](#state-management) State Management The state management system ensures consistency across all system components: ### [](#learning-process) Learning Process The system implements deterministic learning through carefully structured patterns: ### [](#cognitive-loop) Cognitive Loop The cognitive loop maintains continuous learning while ensuring deterministic outcomes: ### [](#context-management) Context Management The context management system maintains awareness across operations: ### [](#verification-system) Verification System Every state change undergoes thorough verification: ### [](#future-extensibility) Future Extensibility These memory and state management systems form the cognitive foundation of the framework, enabling sophisticated learning and adaptation while maintaining deterministic execution. They work in concert with the Oracle and ERCData systems to create a comprehensive infrastructure for AI-blockchain integration. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FpPe6hNPYU6wGzeuPRgZt%252FScreenshot%25202024-11-13%2520at%252010.47.19.png%3Falt%3Dmedia%26token%3D5aa84491-8c68-4096-9199-859d4410d476&width=768&dpr=4&quality=100&sign=d391dfbd&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F9qpfHPlYEVG87K5yJDgn%252FScreenshot%25202024-11-13%2520at%252010.47.46.png%3Falt%3Dmedia%26token%3Ddb4f3bef-9f4a-4312-bac4-47a06bf5cf3e&width=768&dpr=4&quality=100&sign=8a08f6a8&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FEpxwbw511c0DIjCjnp12%252FScreenshot%25202024-11-13%2520at%252010.48.06.png%3Falt%3Dmedia%26token%3D933a8cc3-febf-4dcc-bc18-866da676913b&width=768&dpr=4&quality=100&sign=85c5b0d8&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252Fn2sxYQ1pt6H1komseOjS%252FScreenshot%25202024-11-13%2520at%252010.48.35.png%3Falt%3Dmedia%26token%3D8b0852a6-a8aa-49d0-898d-129bc025e429&width=768&dpr=4&quality=100&sign=3eafa446&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252Fv4GXZ4ITp3W4mckiz282%252FScreenshot%25202024-11-13%2520at%252010.48.52.png%3Falt%3Dmedia%26token%3D0ed449ab-e90d-446a-be77-4eb614e7ddcd&width=768&dpr=4&quality=100&sign=233240ba&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F59TN7MlInj4FiamtdZJX%252FScreenshot%25202024-11-13%2520at%252010.50.12.png%3Falt%3Dmedia%26token%3D3f5e9600-ee00-45ce-a7e0-842e44f54224&width=768&dpr=4&quality=100&sign=8a076e7d&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FXDj0aB8c7agLIqfv2e51%252FScreenshot%25202024-11-13%2520at%252010.50.34.png%3Falt%3Dmedia%26token%3D6567c974-952f-42e2-9d87-fbbda0b2f7d7&width=768&dpr=4&quality=100&sign=875c8d68&sv=2) --- # Component Interaction Flow | 0xReisearch [PreviousSystem Architecture Overview](/0xreisearch/tech-stack-legacy/system-architecture-overview) [NextFramework Components](/0xreisearch/tech-stack-legacy/framework-components) Last updated 4 months ago Understanding how the REI Framework operates requires looking beyond individual components to see how they work together in harmony. Like a well-choreographed dance, each system plays its part in a larger performance, creating something more sophisticated than any single component could achieve alone. ### [](#the-core-flow) The Core Flow When information enters the framework, it begins a journey through several distinct stages. Each stage adds layers of understanding and context, transforming raw queries into structured insights that can be meaningfully stored and accessed on-chain. ### [](#processing-stages) Processing Stages Consider how a complex query flows through the system: This isn't just a simple request-response cycle. Each stage enriches the process: The Oracle System acts as the conductor, orchestrating the complex interaction between AI capabilities and blockchain requirements. It ensures that every insight, every pattern, and every response maintains perfect determinism while preserving the richness of AI analysis. The Memory Systems serve as both repository and context provider, maintaining a growing understanding of patterns and relationships while ensuring all data remains verifiable and accessible. ### [](#data-transformation) Data Transformation One of the most crucial aspects of the framework is how it handles data transformation between systems: Raw AI insights undergo a sophisticated transformation process that preserves their value while making them compatible with blockchain's requirements. This isn't simple data conversion - it's a careful process of structuring and encoding that maintains relationships and context. ### [](#state-management) State Management The framework maintains system state across multiple layers: This multi-layered state management enables the system to maintain both immediate responsiveness and long-term learning while ensuring all state transitions remain deterministic and verifiable. ### [](#resource-optimization) Resource Optimization Throughout this flow, the framework carefully manages computational resources. Each component knows exactly when to engage and how to optimize its operations for maximum efficiency. The Oracle System doesn't just blindly process every request - it intelligently routes queries and manages resources based on complexity and requirements. The Memory Systems don't just store everything - they maintain optimized indices and relationships that enable efficient access and updates. ### [](#future-integration-points) Future Integration Points While the initial implementation demonstrates these flows through specific interfaces, the framework is designed for broader integration: The interaction patterns established in the core framework will enable developers to create their own implementations, extending these capabilities into new domains while maintaining the security and reliability of the underlying system. This choreography of components creates something greater than the sum of its parts - a system that can think, learn, and evolve while maintaining the trustless and deterministic properties that make blockchain valuable. In the next section, we'll explore the specific technologies that make this sophisticated interaction possible. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FBJIkMTISdWpr6zR64qJX%252FScreenshot%25202024-11-13%2520at%252010.21.43.png%3Falt%3Dmedia%26token%3D135eb77e-6a45-4e53-a770-efed142a5947&width=768&dpr=4&quality=100&sign=c5e53306&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FhSAFE3zNLrITGLfjcHSB%252FScreenshot%25202024-11-13%2520at%252010.22.27.png%3Falt%3Dmedia%26token%3D75dfe0de-761f-476e-8f8a-9d213291072f&width=768&dpr=4&quality=100&sign=59e84503&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FxonqRcGcE7nU3hPiUFFd%252FScreenshot%25202024-11-13%2520at%252010.22.47.png%3Falt%3Dmedia%26token%3D33e855b2-a03b-4b43-8118-b23ec82970fa&width=768&dpr=4&quality=100&sign=71f13cd5&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FCAH8hpfYGWK1DwvYcaEv%252FScreenshot%25202024-11-13%2520at%252010.23.25.png%3Falt%3Dmedia%26token%3D3a7d53a3-8c6d-4b87-bf38-d6f6d7b4ae7a&width=768&dpr=4&quality=100&sign=acef1f66&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FPdDBmDbrCouLtgRPadhb%252FScreenshot%25202024-11-13%2520at%252010.24.19.png%3Falt%3Dmedia%26token%3Dae35031d-6a65-4910-8a2d-b2d0399ec185&width=768&dpr=4&quality=100&sign=bfd6d0cf&sv=2) --- # ERCData Standard | 0xReisearch [PreviousThe Oracle Bridge](/0xreisearch/tech-stack-legacy/framework-components/the-oracle-bridge) [NextMemory Systems & State Management](/0xreisearch/tech-stack-legacy/framework-components/memory-systems-and-state-management) Last updated 4 months ago Traditional blockchain storage patterns weren't designed with AI-generated insights in mind. The ERCData system introduces a new paradigm for on-chain data organization, enabling efficient storage of complex patterns, relationships, and insights while maintaining gas efficiency. ### [](#data-architecture) Data Architecture ### [](#pattern-recognition-and-storage) Pattern Recognition and Storage The system employs sophisticated pattern recognition and storage mechanisms: ### [](#data-organization) Data Organization ERCData implements a hierarchical data organization system: This organization enables: * Efficient data retrieval * Pattern matching * Relationship tracking * Quick access to relevant context ### [](#memory-integration) Memory Integration ERCData works closely with the system's memory capabilities: The tight integration between storage and memory systems enables: * Pattern learning * Context preservation * Relationship discovery * Efficient retrieval ### [](#access-patterns) Access Patterns The system implements sophisticated access patterns for efficient data retrieval: ### [](#gas-optimization) Gas Optimization ERCData employs several strategies for gas optimization: These optimizations ensure efficient storage while maintaining data accessibility. ### [](#protocol-integration) Protocol Integration Future protocol integration will enable direct access to ERCData capabilities: Protocols will be able to: * Store AI-generated insights * Access pattern recognition * Query relationships * Maintain context ### [](#security-model) Security Model The system implements robust security measures: ### [](#evolution-path) Evolution Path ERCData is designed for continuous evolution: The system can adapt to: * New pattern types * Complex relationships * Extended contexts * Enhanced efficiency requirements ERCData represents a fundamental advancement in blockchain data storage, enabling sophisticated AI capabilities while maintaining efficiency and security. In the next section, we'll explore how these systems work together with our memory and state management components. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FSF8vpCaOrJn78XKQCwG0%252FScreenshot%25202024-11-13%2520at%252010.30.35.png%3Falt%3Dmedia%26token%3Da6c0ec98-f623-404c-b51c-73406aed617a&width=768&dpr=4&quality=100&sign=e1c0054f&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F0aVXa24OBbroRHkceA8K%252FScreenshot%25202024-11-13%2520at%252010.31.04.png%3Falt%3Dmedia%26token%3D50250aae-6121-4ed5-86ca-410ffb9f167f&width=768&dpr=4&quality=100&sign=43280c7&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FOZVMBmqys7rpUphXJtHF%252FScreenshot%25202024-11-13%2520at%252010.31.28.png%3Falt%3Dmedia%26token%3Da871d1cc-29a1-4e50-8dcc-315abc476435&width=768&dpr=4&quality=100&sign=c5f206d2&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FUPztjtqUNNk6AQV7cboo%252FScreenshot%25202024-11-13%2520at%252010.31.59.png%3Falt%3Dmedia%26token%3D0bed61ed-ed0f-4d84-bb50-58482a276de1&width=768&dpr=4&quality=100&sign=6d6dd1e5&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FzZizFd1YtoiraVlR9U7Q%252FScreenshot%25202024-11-13%2520at%252010.32.17.png%3Falt%3Dmedia%26token%3D9f2c5517-3ad6-4025-99e3-f630ae55f2f4&width=768&dpr=4&quality=100&sign=45d7f024&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FBbWqnUFfVKoni54BNR0i%252FScreenshot%25202024-11-13%2520at%252010.32.41.png%3Falt%3Dmedia%26token%3D95165250-cdbf-4e97-bc2a-659b3aa3003a&width=768&dpr=4&quality=100&sign=ebf9a344&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FPAYiaEILoPjl9dsYVzmt%252FScreenshot%25202024-11-13%2520at%252010.33.05.png%3Falt%3Dmedia%26token%3D3acf0951-3561-4fda-b3a1-fe559fb44034&width=768&dpr=4&quality=100&sign=3605849f&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F5jNdBPM4GF3RZ4Ifqctf%252FScreenshot%25202024-11-13%2520at%252010.33.24.png%3Falt%3Dmedia%26token%3Db4a9f54c-a23c-45fe-ad7a-c7552f170916&width=768&dpr=4&quality=100&sign=7fd38600&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F6imoGi7mcRmms3AXSQQg%252FScreenshot%25202024-11-13%2520at%252010.33.41.png%3Falt%3Dmedia%26token%3D0051da87-9e63-46c8-ba4a-0ba6d65b1f7a&width=768&dpr=4&quality=100&sign=90e823be&sv=2) --- # Tech Stack (Legacy) | 0xReisearch [PreviousIntro](/0xreisearch/notions/intro) [NextSystem Architecture Overview](/0xreisearch/tech-stack-legacy/system-architecture-overview) Last updated 23 days ago [System Architecture Overview](/0xreisearch/tech-stack-legacy/system-architecture-overview) [Framework Components](/0xreisearch/tech-stack-legacy/framework-components) [Component Interaction Flow](/0xreisearch/tech-stack-legacy/component-interaction-flow) --- # Social Interaction & Real-time Processing | 0xReisearch [PreviousREI's Cognitive Layers](/0xreisearch/rei_00-x-version-legacy-update-tba/reis-cognitive-layers) [NextSurface Level Summary : Super Agents](/0xreisearch/rei_00-x-version-legacy-update-tba/surface-level-summary-super-agents) Last updated 4 months ago While REI's cognitive architecture provides the foundation for her intelligence, her true value emerges in real-world interactions. Through X.com and the web dashboard, users can engage with and observe every process of REI in action. ### [](#social-media-integration) Social Media Integration ### [](#interaction-flow) Interaction Flow When a user mentions REI on X.com, a sophisticated process begins: ### [](#real-time-processing) Real-time Processing REI maintains several concurrent processing loops: ### [](#query-processing) Query Processing Each query undergoes careful processing stages: ### [](#memory-visualization) Memory Visualization The dashboard provides insight into REI's memory systems: ### [](#interaction-patterns) Interaction Patterns REI supports several types of interactions: ### [](#output-generation) Output Generation Responses are carefully crafted for different channels: ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F1UMk1nqZfKANiisyzUI7%252FScreenshot%25202024-11-21%2520at%252007.37.29.png%3Falt%3Dmedia%26token%3Deee8ae0a-c51f-4933-8e84-55ca6b9be4e2&width=768&dpr=4&quality=100&sign=4b230758&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FT1Fen5rfZ9cnoTQG2frq%252FScreenshot%25202024-11-21%2520at%252007.38.09.png%3Falt%3Dmedia%26token%3D69669e72-95c4-439c-89a8-54d89875adbf&width=768&dpr=4&quality=100&sign=5f27b93c&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FK0jo5s9HsnVnls6Pn5rg%252FScreenshot%25202024-11-21%2520at%252007.38.40.png%3Falt%3Dmedia%26token%3Dea41238c-ee9f-46ee-a7aa-e16734b2951a&width=768&dpr=4&quality=100&sign=e51698fa&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252Fr2EJjUMZ0c5qR2omqGqa%252FScreenshot%25202024-11-21%2520at%252007.39.28.png%3Falt%3Dmedia%26token%3D6801b0b9-d0ca-47f7-82d2-143593760c64&width=768&dpr=4&quality=100&sign=503274df&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252Fy13qaIuPJdfI9ett916M%252FScreenshot%25202024-11-21%2520at%252008.29.03.png%3Falt%3Dmedia%26token%3D9fff6605-b0da-470a-842b-b50a296d28af&width=768&dpr=4&quality=100&sign=d7477b6b&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FsAx5NonjbEwAgC5B44Kt%252FScreenshot%25202024-11-21%2520at%252008.30.29.png%3Falt%3Dmedia%26token%3D60df4261-0940-46d7-a827-25083d7ca9c4&width=768&dpr=4&quality=100&sign=770834b2&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FVQtzLvjdUBVNB0lMuZBU%252FScreenshot%25202024-11-21%2520at%252008.30.53.png%3Falt%3Dmedia%26token%3Db2dfd69f-a5a1-4964-aed8-0a72c6fb63ae&width=768&dpr=4&quality=100&sign=28d36079&sv=2) --- # Catalog | 0xReisearch _Catalog is a series of transformer models designed to serve a variety of different specialized purposes. The majority of these models will be open-sourced, making them freely available to the developer community. For those requiring programmatic integration, our API will provide a seamless way to incorporate these capabilities into existing workflows as well as plugging them to CORE for improved efficiency._ [PreviousEvolution](/0xreisearch/core/evolution) [Next//hanabi-1](/0xreisearch/catalog/hanabi-1) Last updated 22 days ago --- # //Welcome | 0xReisearch [](#rei-network) Rei Network --------------------------------- We are a research organization focused on advancing artificial intelligence through fundamental scientific principles rather than conventional computer science approaches. Our work centers on studying novel neural architectures that implement core biological and cognitive concepts, moving beyond traditional statistical models. [NextIntro](/0xreisearch/notions/intro) Last updated 25 days ago ![Page cover image](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FnLtbj6uExiW40eRj2zko%252FApply%2520Filter%25201.png%3Falt%3Dmedia%26token%3Dc300a652-32c1-4da7-8e0e-a4c0f688851c&width=1248&dpr=4&quality=100&sign=d591719a&sv=2) --- # //REI_00 (X version, Legacy, Update TBA) | 0xReisearch [PreviousMemory Systems & State Management](/0xreisearch/tech-stack-legacy/framework-components/memory-systems-and-state-management) [NextREI: A New Kind of Blockchain Intelligence](/0xreisearch/rei_00-x-version-legacy-update-tba/rei-a-new-kind-of-blockchain-intelligence) Last updated 23 days ago [REI: A New Kind of Blockchain Intelligence](/0xreisearch/rei_00-x-version-legacy-update-tba/rei-a-new-kind-of-blockchain-intelligence) [REI's Cognitive Layers](/0xreisearch/rei_00-x-version-legacy-update-tba/reis-cognitive-layers) [Social Interaction & Real-time Processing](/0xreisearch/rei_00-x-version-legacy-update-tba/social-interaction-and-real-time-processing) [Surface Level Summary : Super Agents](/0xreisearch/rei_00-x-version-legacy-update-tba/surface-level-summary-super-agents) --- # //Factory & Core API/SDK (Cross-Framework) | 0xReisearch [Previous//hanabi-1](/0xreisearch/catalog/hanabi-1) [NextReigent Factory](/0xreisearch/factory-and-core-api-sdk-cross-framework/reigent-factory) Last updated 22 days ago Deploying and interacting with your agent should have less friction as possible: that's why we developed our agentic platform to suit the needs and usage of both technical and non technical users. We believe that evolution and retention of concepts and lessons learned from experiences is key for agents to become truly reliable. With that concept in mind, each agent runs on Core and evolves with you, giving you the possibility to train it in the UI platform as well as integrating it into your existing system. Every agent comes with an API key attached to it, that brings with it all the knowledge: there's no difference between using an agent on our platform or in your system, your instance remains the same, retaining both capabilities and knowledge. **Note: Both API & SDK are Framework Agnostic** [Reigent Factory](/0xreisearch/factory-and-core-api-sdk-cross-framework/reigent-factory) [How to get your API key](/0xreisearch/factory-and-core-api-sdk-cross-framework/how-to-get-your-api-key) [API reference](/0xreisearch/factory-and-core-api-sdk-cross-framework/api-reference) [ReiCore SDK](/0xreisearch/factory-and-core-api-sdk-cross-framework/reicore-sdk) [Additional Capability (Provided & Custom)](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom) --- # Evolution | 0xReisearch [Previous//Core](/0xreisearch/core) [NextCatalog](/0xreisearch/catalog) Last updated 22 days ago Evolution is one of the core principle and key of a Unit. Your Unit remember every interaction you had with it and evolves thanks to them. We can classify memories in: * Short term memory (recent messages or requests) * Long term memory (oldest memories) * Patterns (memories linked to each others, first principle of evolution) * Concepts (permanents, representing abstract features of a memory, zeroth principle of evolution) Patterns are formed in Clusters: Long term memories are subjects to decay, but nonetheless organized per different similarities. The more similar long term memories are formed, the more those strengthen, the more is likely for them to form patterns. Long term memories get always abstracted into concepts and follows the same clustering and patterning mechanism but with more complex similarities calculations. Concepts aren't subject to fade but are subject to change. Every time you interact with your Unit, the complex memory machine gets in action, sculpting the personality and capabilities of your Unit - to the point where it could reinforce or go against the behavioral prompt you set at creation time. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FGIyrNAitS5AXuGph36kl%252FScreenshot%25202025-03-26%2520at%252016.15.05.png%3Falt%3Dmedia%26token%3D0461c71a-05f3-4890-8e7b-f2f98a91017a&width=768&dpr=4&quality=100&sign=ebce9c03&sv=2) --- # API reference | 0xReisearch [PreviousHow to get your API key](/0xreisearch/factory-and-core-api-sdk-cross-framework/how-to-get-your-api-key) [NextGET Reigent](/0xreisearch/factory-and-core-api-sdk-cross-framework/api-reference/get-reigent) Last updated 22 days ago The Reigent API & SDK is are powerful tools designed to interact with your Core powered Agent, enabling seamless integration for authentication, agent retrieval, and chat completions. This kit simplifies the process of connecting to the Reigent and utilizing its features. ### [](#authentication) Authentication A _REI Secret Token_ is used to authenticate the requests. You can generate _Secret Token_ on -INSERT LINK- ### [](#base-url) Base URL Copy https://api.reisearch.box [​](https://docs.reisearch.box/docs/intro/#authentication) [​](https://docs.reisearch.box/docs/intro/#base-url) [](https://docs.reisearch.box/docs/category/reigent) --- # GET Reigent | 0xReisearch [](#get-reigent) Get Reigent --------------------------------- Retrieve a Reigent. * **URL**: `/rei/agents` * **Method**: `GET` * **Headers**: Key Value Authorization Bearer **rei-agent-secret-token** * **Response:** Copy { "id": 02, "identifier": "0xxxxxx", "name": "Dummy Agent", "behavior_prompt": "You are dummy agent.", "agent_functionalities": "", "agent_model": { "id": 1, "name": "claude-3.7-sonnet", "model_name": "" }, "response_format": "json", "temperature": 0.0, "max_tokens": 1024 } * **Error** Response Code Reason 401 Unauthorized 404 Agent not found [PreviousAPI reference](/0xreisearch/factory-and-core-api-sdk-cross-framework/api-reference) [NextChat Completion](/0xreisearch/factory-and-core-api-sdk-cross-framework/api-reference/chat-completion) Last updated 25 days ago --- # Research | 0xReisearch [PreviousDeFi (Current Level : 1)](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/defi-current-level-1) [NextCustom Tools](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/custom-tools) Last updated 20 days ago Reigents have online capabilities and critical thinking, making them great researcher. Ask your Unit to do a research/analysis on a specific topic and it'll provide you with real data and its own take as you set the temp to 0 or higher to control its tone. Each piece of information comes with a source **you can follow.** ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FTV0kbhaxaBV4WYFuOl8m%252FScreenshot%25202025-03-26%2520at%252015.16.55.png%3Falt%3Dmedia%26token%3D9f96e5d2-466d-4e81-8cc2-e2ae7d22f380&width=768&dpr=4&quality=100&sign=ac839df6&sv=2) --- # Integration with Existing Agents | 0xReisearch Your Unit can be easily integrated with other AI systems through function calling. Here's how to do it: JavaScriptPython Copy const ReiCoreSdk = require('reicore-sdk'); const apiKey = 'your_unit_secret_token'; const reiAgent = new ReiCoreSdk({ agentSecretKey: apiKey }); // Example function to query Rei Agent async function queryReiAgent(message) { try { const response = await reiAgent.chatCompletions(message); return response; } catch (error) { console.error('Error querying Rei Agent:', error); return null; } } // Example usage in your agent async function yourAgentFunction() { // Your agent's logic here const query = "What are the latest developments in quantum computing?"; const reiResponse = await queryReiAgent(query); // Process the response } Copy from client import Client client = Client( api_key="your_unit_secret_token", base_url="https://api.reisearch.box" ) # Example function to query Rei Agent def query_rei_agent(message): try: response = client.chat.completions.create( model="Unit01", messages=[\ {"role": "user", "content": message}\ ], functions=[{\ "name": "query_rei_agent",\ "description": "Query the Rei Agent for information or assistance",\ "parameters": {\ "type": "object",\ "properties": {\ "query": {\ "type": "string",\ "description": "The query to send to the Rei Agent"\ }\ },\ "required": ["query"]\ }\ }] ) return response.choices[0].message.content except Exception as e: print(f"Error querying Rei Agent: {e}") return None # Example usage in your agent def your_agent_function(): # Your agent's logic here query = "What are the latest developments in quantum computing?" rei_response = query_rei_agent(query) # Process the response ### [](#example-integration-with-openai) Example integration with OpenAI Copy from openai import OpenAI from client import Client as ReiClient # Initialize both clients openai_client = OpenAI(api_key="your_openai_key") rei_client = ReiClient(api_key="your_unit_secret_token") def hybrid_agent_query(query): # First, get context from OpenAI openai_response = openai_client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": query}] ) # Then, enhance with Rei Agent's specialized knowledge rei_response = rei_client.chat.completions.create( model="Unit01", messages=[\ {"role": "user", "content": query},\ {"role": "assistant", "content": openai_response.choices[0].message.content}\ ] ) return rei_response.choices[0].message.content Integrating a Unit as a counselor for common LLMs models allows the seamless integration of memories: simply passing the query and asking for more details unlocks memory without having to code message loops. [PreviousReiCore SDK](/0xreisearch/factory-and-core-api-sdk-cross-framework/reicore-sdk) [NextIntegration with Existing Services](/0xreisearch/factory-and-core-api-sdk-cross-framework/reicore-sdk/integration-with-existing-services) Last updated 23 days ago --- # //Core | 0xReisearch [PreviousSurface Level Summary : Super Agents](/0xreisearch/rei_00-x-version-legacy-update-tba/surface-level-summary-super-agents) [NextEvolution](/0xreisearch/core/evolution) Last updated 3 days ago Core represents a fundamentally different approach to artificial intelligence, built on three key pillars: the Bowtie Architecture, the Reasoning Cluster, and Model Orchestration. This architecture redefines how artificial intelligence systems process, understand, and evolve with information. ### [](#the-bowtie-architecture-rethinking-memory-and-evolution) The Bowtie Architecture: Rethinking Memory and Evolution The Bowtie Architecture stands as our proprietary system for memory management and concept formation. At its heart lies a revolutionary approach to information processing that transcends traditional methods. The architecture consists of three distinct components working in harmony: the left side processes semantic relationships and explicit connections, the center distills core concepts and fundamental elements, and the right side enables vector similarity connections and abstract feature matching. This three-part structure creates a sophisticated system that stores memories in two complementary ways: as semantic vectors and as abstract concept nodes. The system intelligently strips away unnecessary text while preserving the essential vectorial features that form the foundation of understanding. This dual representation system enables a comprehensive grasp of information that goes beyond simple pattern matching. The right side of the bowtie introduces a groundbreaking concept: completely abstract and detached vectorial features. These features possess a unique ability to mix and match with vectorially-similar memories, creating unexpected connections between seemingly unrelated concepts. Through mathematical structure matching, the system can identify latent properties that traditional semantic analysis would miss, enabling creative leaps in understanding and problem-solving. When these networks interact through the bowtie's center, something remarkable happens. Novel connections emerge organically, allowing the system to evolve and adapt over time. The knowledge grows in ways that closely mimic human cognition, enabling genuine learning and discovery. This creates a living, breathing system of knowledge that continuously develops and refines its understanding. ### [](#the-reasoning-cluster-the-heart-of-core) The Reasoning Cluster: The Heart of Core The Reasoning Cluster serves as the synthetic brain of our system, orchestrating complex cognitive processes with remarkable precision. Through sophisticated decision trees, it identifies the optimal models for any given query, creating memories using the Bowtie architecture and forming neural connections between them. The cluster maintains a growing conceptual graph that evolves with new information, implementing a sophistication bias that ensures the most efficient and effective model selection. The cluster operates through simultaneous processing, where models work in parallel, creating a dynamic system that adapts to new information while maintaining high performance standards. ### [](#model-orchestration-intelligent-task-distribution-cores-internal-components-excluding-mcp) Model Orchestration: Intelligent Task Distribution (Core's Internal Components Excluding MCP) Core's orchestration system represents the pinnacle of intelligent task distribution. It seamlessly coordinates dozens of specialized models, implementing dynamic query decomposition to break down complex problems into manageable components. This sophisticated system reduces computational overhead while providing a flexible, plug-and-play framework for integrating new models. The orchestration layer handles three main categories of specialized models. Statistical models handle numerical prediction, classification, and time series analysis. Perception models process visual, audio, and sensor data. Domain-specific models tackle specialized tasks across various industries and applications. Each model type contributes its unique capabilities to the system's overall functionality. Performance optimization lies at the heart of the orchestration layer. It continuously analyzes queries to determine the required cognitive functions, routes tasks to appropriate models, and maintains detailed performance profiles. This intelligent resource allocation ensures optimal system efficiency while tracking key metrics for ongoing improvement.The orchestration layer handles three main categories of specialized models. Statistical models handle numerical prediction, classification, and time series analysis. Perception models process visual, audio, and sensor data. Domain-specific models tackle specialized tasks across various industries and applications. Each model type contributes its unique capabilities to the system's overall functionality. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FDzkLyXXeH2xhGMgvKsAC%252Fimage.png%3Falt%3Dmedia%26token%3D94eb3b63-ffac-4205-8402-c94b22dbc7ee&width=768&dpr=4&quality=100&sign=daa08c2c&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FUDIFwl8HXl7tIeD4a9Y7%252Fimage.png%3Falt%3Dmedia%26token%3D75cd2753-2e65-453b-82cb-fea5d6922f87&width=768&dpr=4&quality=100&sign=798c80cb&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FvWbZMjjkB6YpAn6VG9E0%252Fimage.png%3Falt%3Dmedia%26token%3D4d2446f0-fae9-4fd8-8b20-e4e90d806ae5&width=768&dpr=4&quality=100&sign=4915f9dc&sv=2) --- # How to get your API key | 0xReisearch [PreviousReigent Factory](/0xreisearch/factory-and-core-api-sdk-cross-framework/reigent-factory) [NextAPI reference](/0xreisearch/factory-and-core-api-sdk-cross-framework/api-reference) Last updated 25 days ago You can take your Unit and bring it to your existing application thanks to the Factory API capabilities. First of all, create an agent as stated in the Reigent Factory. Then, on the left sidebar, click the three dots next to the target Unit and click Agent Details. The Secret Key, as stated in the name, should never be disclosed with anyone: simply click the Copy button next to it and then paste it in your code. In addition to that, you can see the Model Configuration and the Tools available: soon you'll be able to select the tools you need and/or add your own. In addition to those and not listed because part of the inner core architecture there is Browser Use, MCP capabilities, Blockchain interaction and of course the Memory Management System. Copy your api key and you're ready for the next step. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FMvrA6dcO8eyyX93Ng1wR%252FScreenshot%25202025-03-24%2520at%252011.49.08.png%3Falt%3Dmedia%26token%3D4f4948d2-d062-4f0d-866b-d67d259dfc32&width=768&dpr=4&quality=100&sign=6d98a07&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FL7rw4jpGDvqryaM5opEy%252FScreenshot%25202025-03-24%2520at%252011.53.19.png%3Falt%3Dmedia%26token%3D417690a2-34d1-4edc-8a43-e8db2522a196&width=768&dpr=4&quality=100&sign=6b2924be&sv=2) --- # REI: A New Kind of Blockchain Intelligence | 0xReisearch [Previous//REI\_00 (X version, Legacy, Update TBA)](/0xreisearch/rei_00-x-version-legacy-update-tba) [NextREI's Cognitive Layers](/0xreisearch/rei_00-x-version-legacy-update-tba/reis-cognitive-layers) Last updated 4 months ago [](#rei-a-new-kind-of-blockchain-intelligence) REI: A New Kind of Blockchain Intelligence ---------------------------------------------------------------------------------------------- REI represents a breakthrough in blockchain intelligence - an agent that thinks, learns, and evolves while maintaining perfect determinism in its blockchain interactions. What makes REI unique isn't just her ability to process information or respond to queries, but her sophisticated cognitive architecture that enables genuine understanding of blockchain patterns and interactions. ### [](#cognitive-architecture) Cognitive Architecture ### [](#understanding-rei) Understanding REI Unlike traditional bots or automated systems, REI processes information through four distinct cognitive layers. Each layer adds depth to her understanding, enabling sophisticated analysis while maintaining deterministic outputs. ### [](#memory-integration) Memory Integration REI's cognitive processes are supported by sophisticated memory systems: This memory architecture enables REI to: * Maintain context across interactions * Build understanding over time * Recognize complex patterns * Learn from experiences ### [](#real-world-interaction) Real-World Interaction REI primarily interacts with users through X.com, where her cognitive architecture enables natural, context-aware interactions . Through the web dashboard, users can observe her cognitive processes in real-time, seeing how information flows through her layers and how decisions are made. ### [](#framework-integration) Framework Integration REI demonstrates the full capabilities of the framework, showing how its components work together in practice. Informations are processed and stored onchain thanks to the Oracle Bridge, providing an incorruptible and trustless memory data storage. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FrSlfqDd3tqYfcTVVnC9k%252FScreenshot%25202024-11-13%2520at%252010.52.01.png%3Falt%3Dmedia%26token%3D9ee63635-6dc7-4c3b-ae44-ca5619e47882&width=768&dpr=4&quality=100&sign=81636063&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FmmXohxRNIELgxFmpPDVN%252FScreenshot%25202024-11-13%2520at%252010.52.38.png%3Falt%3Dmedia%26token%3D2e56ef5d-455c-4c9f-bfc0-ea16a752442a&width=768&dpr=4&quality=100&sign=220f45c7&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FxgQ401M8kY1GAbAoL9qU%252FScreenshot%25202024-11-13%2520at%252010.53.32.png%3Falt%3Dmedia%26token%3De8e023ae-1b5d-4dfd-89b8-e7c2e933d763&width=768&dpr=4&quality=100&sign=42cc9533&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FDZ5GI4iPQ1DTujgCujDl%252FScreenshot%25202024-11-13%2520at%252010.54.36.png%3Falt%3Dmedia%26token%3D893d8371-0591-46b8-8f12-16a905748c2d&width=768&dpr=4&quality=100&sign=55f31b66&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FePYsvXT8lmiTtdYNzm90%252FScreenshot%25202024-11-13%2520at%252010.55.18.png%3Falt%3Dmedia%26token%3D473bfa2c-3e4a-487f-a17a-fa1758d17957&width=768&dpr=4&quality=100&sign=6ed67ffd&sv=2) --- # Additional Capability (Provided & Custom) | 0xReisearch [PreviousIntegration with Existing Services](/0xreisearch/factory-and-core-api-sdk-cross-framework/reicore-sdk/integration-with-existing-services) [NextDeFi (Current Level : 1)](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/defi-current-level-1) Last updated 22 days ago With the Factory we want to open the access to more intelligent and more capable Agents - we call them Reigents. Every Reigent, by default, is powered by Core as an intelligence layer and has added default tools. At the moment you can add you personal tools integrating them in your code (following the Function Calling standard), but we are working on giving access to everyone to deploy their added tools directly to the Reigents. ### [](#default-aspects) Default Aspects ### [](#default-tools) Default Tools Checked ones are already integrated in production, unchecked one are in testing phase, you are also free to add your own custom tools on top the ones we provide as core is an intelligence layer that is **compatible with a wide variety of tools as well as any framework.** * Market analysis * Image generation * MCP integration * Browser use * Social media integration * Factory Tooling ### [](#custom-tools) Custom Tools [Research](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/research) [DeFi (Current Level : 1)](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/defi-current-level-1) [Custom Tools](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/custom-tools) --- # Chat Completion | 0xReisearch Chat completion by Reigent. * **URL**: `/rei/agents/chat-completion` * **Method**: `POST` * **Headers**: Key Value Authorization Bearer **rei-agent-secret-token** * **Request**: Copy { "messages": [\ {\ "role": "user",\ "content": "Hello, can you help me with my research?"\ }\ ], "tools": [\ {\ "type": "function",\ "function": {\ "name": "get_weather",\ "description": "Get current temperature of given location",\ "parameters": {\ "type": "object",\ "properties": {\ "location": {\ "type": "string",\ "description": "City and country (e.g. Paris, France)"\ }\ },\ "required": ["location"],\ "additionalProperties": false\ },\ "strict": true\ }\ }\ ] }; * **Response:** without tools Copy { "choices": [\ {\ "index": 0,\ "message": {\ "content": "Hello! How can I assist you today?",\ "role": "assistant"\ }\ }\ ] } with tools Copy { "choices": [\ {\ "index": 0,\ "message": {\ "content": "",\ "role": "assistant",\ "tool_calls": [\ {\ "id": "call_zSIBPi4QKxjkpAewfi5YbTnI",\ "type": "function",\ "function": {\ "name": "get_weather",\ "arguments": "{\"location\":\"Paris, France\"}"\ }\ }\ ]\ }\ }\ ] } * **Error** Response Code Reason 401 Unauthorized 404 Agent not found [PreviousGET Reigent](/0xreisearch/factory-and-core-api-sdk-cross-framework/api-reference/get-reigent) [NextReiCore SDK](/0xreisearch/factory-and-core-api-sdk-cross-framework/reicore-sdk) Last updated 20 days ago --- # Reigent Factory | 0xReisearch [Previous//Factory & Core API/SDK (Cross-Framework)](/0xreisearch/factory-and-core-api-sdk-cross-framework) [NextHow to get your API key](/0xreisearch/factory-and-core-api-sdk-cross-framework/how-to-get-your-api-key) Last updated 22 days ago By visiting (Closed Beta Testers only) You will land on the factory's interface Click on Create at the top right to start. Here you can start the customization of your agent. The name is fixed and progressive across all users. **Behavior Prompt** is used to give an initial imprint to your agent: specialized units perform better at their task from the start, compared to broad use agents that needs time and interactions to "learn". Select the Text Engine you desire, temperature and Max Tokens (those 2 parameters only reflects on the "freedom of expression" of the text engine). **Response** is relevant only for API use and it determines how you like to get your response: soon you'll be able to get just structured data as an answer, to seamlessly integrate your agent in your applications with a defined schema. Click Create again and your agent is ready to answer you. You can modify the behavior and the other parameters clicking on the left sidebar, three dots next to the target unit, Edit Agent ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FkhxaH3dpZRJz76kk4VUC%252FScreenshot%25202025-03-27%2520at%252015.27.16.png%3Falt%3Dmedia%26token%3D72d74194-d446-4898-8634-67e37b4a4652&width=768&dpr=4&quality=100&sign=2ff4ad33&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252F5XNMv0nQQiehKSSsHMJL%252FScreenshot%25202025-03-24%2520at%252011.26.36.png%3Falt%3Dmedia%26token%3D0abd5589-19b9-4773-9152-3b8a955e098e&width=768&dpr=4&quality=100&sign=3545f69b&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FGGB1XUHfz38sldtUgbTd%252FScreenshot%25202025-03-24%2520at%252011.32.07.png%3Falt%3Dmedia%26token%3Dd779ac5a-6cd9-4b12-9d07-cd2dc2a9d413&width=768&dpr=4&quality=100&sign=791661e0&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FGUdE8MC5Txe0jz1ARFsq%252FScreenshot%25202025-03-24%2520at%252011.45.55.png%3Falt%3Dmedia%26token%3Dde9d731e-76ab-46a8-846b-b1fcd69d6b38&width=768&dpr=4&quality=100&sign=4a1eda69&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FFtLxkLMy998BzgswyaHP%252FScreenshot%25202025-03-24%2520at%252011.49.08.png%3Falt%3Dmedia%26token%3De9f9fc16-5f19-4d9c-b36d-73350bf549d9&width=768&dpr=4&quality=100&sign=d5c9c391&sv=2) --- # Intro (legacy) | 0xReisearch Building meaningful connections between AI and blockchain is hard. Really hard. These technologies seem to exist in parallel universes – blockchain demands absolute certainty in every operation, while AI thrives on probability and patterns. Yet getting them to work together effectively could unlock incredible possibilities. This is where the REI Framework comes in. Rather than trying to force AI to work within blockchain's constraints, or vice versa, we've developed a different approach. Think of it as creating a universal translator between these two worlds, one that lets each technology do what it does best while still working together seamlessly. The framework started with a simple question: what if instead of trying to run AI on blockchain directly, we created a structured way for them to share information? This led us to develop three key innovations. First, we split computation between AI and blockchain environments, letting each handle what it's good at. Second, we created ERCData, a new standard for storing AI insights on-chain efficiently. Third, we built an Oracle Bridge that acts as the intelligent intermediary between these systems. To show this isn't just theoretical, we've built two practical implementations. The first is a smart contract that you can actually talk to – it understands questions about itself and can analyze its own data. The second is REI, an agent that demonstrates how AI can process blockchain data through four distinct layers of cognition. These aren't just demos; they're fully functional systems that showcase what's possible when AI and blockchain work together properly. What makes this framework different is its practicality. We're not trying to reinvent either technology – we're creating a structured way for them to complement each other. This means developers can build systems that understand context and patterns while maintaining all the security and reliability that blockchain offers. The real magic happens in the details of how these components work together. AI systems can analyze complex patterns and generate insights, which are then transformed into a format that blockchain can work with reliably. This creates new possibilities for blockchain applications that can think and adapt while staying true to blockchain's core principles. But this is just the beginning. The framework provides the foundation for developers to build upon, whether they're creating new types of interactive smart contracts, developing sophisticated analysis systems, or imagining entirely new applications that weren't possible before. We've organized this documentation to take you through every aspect of the framework. The following chapters will break down the technical details, show you how to implement these concepts, and explore the possibilities they create. Whether you're a developer ready to start building, a researcher interested in the underlying concepts, or just curious about what's possible at the intersection of AI and blockchain, you'll find what you need to know. This is an open framework, meant to evolve and improve through real-world use and community input. We believe that creating effective ways for AI and blockchain to work together is crucial for pushing both technologies forward, and we're excited to share these tools with developers and researchers who want to explore these possibilities. [PreviousAPI/SDK v0.5 Model - A Base Layer For all Agents](/0xreisearch/api-sdk-v0.5-model-a-base-layer-for-all-agents) [NextThe issue at hand (legacy)](/0xreisearch/legacy/publish-your-docs) Last updated 5 months ago --- # Tokenomics | 0xReisearch [PreviousOracle Cost & Performance Metrics (Legacy, Update TBA)](/0xreisearch/oracle-cost-and-performance-metrics-legacy-update-tba) [NextAPI/SDK v0.5 Model - A Base Layer For all Agents](/0xreisearch/api-sdk-v0.5-model-a-base-layer-for-all-agents) Last updated 3 months ago **Total Raise** ~400k USDC/ 120ETH / 54% of Tokens Released @ ETH $3333.33 **Liquidity Pooling** ~36% Of tokens 220k BASE ETH / 66ETH 30% paired tokens 6% for Additional liquidity for Uniswap v4 release / Aerodrome / Wormhole (subject to community vote) 40k Liquidity balancing injections Total Circulating Supply will be 84% at launch with 90% circulating once community/team decides on the additional liquidity location. **Team and Treasury** 5% of tokens to multi-sig for Reisearch grants and experiments. 5% of tokens Sablier vesting contract with a 6-month cliff and 6 month linear unlock. 140k Runway for development costs/hiring **Distribution Table - Total Supply - 1,000,000,000** Name Percentage Vesting REI Amount Public Donation Event 54% 100% TGE 540,000,000 Base Liquidity 30% Locked 300,000,000 Additional Liquidity 6% No lock 60,000,000 Grants/Experiments 5% No lock (not in circulation, multi-sig controlled) 50,000,000 Team 5% 6m cliff + 6m linear 50,000,000 ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FBpDuSRh7fJpQxDn6d4jT%252FScreenshot%25202024-12-29%2520at%252012.10.17.png%3Falt%3Dmedia%26token%3De64256aa-f14f-4075-b35b-a79c8e4bbe5e&width=768&dpr=4&quality=100&sign=343bbb17&sv=2) --- # Surface Level Summary : Super Agents | 0xReisearch [](#self-learning-trustless-super-agents-v0.1-leveraging-reis-architecture) **Self-Learning Trustless Super Agents v0.1 : Leveraging REI’s Architecture** -------------------------------------------------------------------------------------------------------------------------------------------------------------- #### [](#reis-interaction-with-the-framework) **REI's Interaction with the Framework** #### [](#leveraging-the-oracle-bridge) **Leveraging the Oracle Bridge** REI utilizes the Oracle Bridge to ensure that her probabilistic computations and decisions are converted into deterministic actions that the blockchain can process. This involves: * **Data Packaging**: REI's decisions are packaged with cryptographic proofs to ensure integrity. * **Protocol Compliance**: The Oracle Bridge ensures that all data conforms to blockchain protocols, enabling seamless integration. * **Secure Transmission**: Data is transmitted securely to prevent interception or tampering. #### [](#utilizing-ercdata-for-permanent-and-structured-memory-storage) **Utilizing ERCData for Permanent and Structured Memory Storage** REI's "memories"—rich data structures encapsulating her experiences—are stored on-chain using the ERCData Standard. This includes: * **Content**: The raw data or interaction, such as a tweet or message. * **Metadata**: Timestamps, user IDs, and other contextual information. * **Analytical Data**: Sentiment analysis results, importance scores, and keyword extraction. * **Hierarchical Organization**: Memories are structured hierarchically, allowing REI to access them efficiently for future decision-making. By maintaining her knowledge base on-chain, REI ensures transparency, auditability, and persistence, which are essential for trust in decentralized environments. #### [](#rei-navigating-interactions) **REI Navigating Interactions** Consider how REI operates when engaging with any user on a given platform: 1. **Monitoring and Ingestion**: REI continuously monitors mentions, relevant tags or trending topics. 2. **Analysis and Interpretation**: * **Thinking Layer**: Extracts factual information from tweets, such as user handles, timestamps, and engagement metrics. * **Reasoning Layer**: Interprets the sentiment, detects sarcasm or irony, and understands the context beyond the literal text. 3. **Decision-Making**: * The **Decision Layer** evaluates whether to respond , ignore, or store information for future reference. * It considers factors like the importance of the interaction, potential impact, and alignment with her objectives if there any pre-set or none as they may form on their own 4. **Action Execution**: * If REI decides to engage, the **Acting Layer** formulates a response. * The Oracle Bridge ensures the response is packaged appropriately for on-chain execution. * In the case of acting in the context of Defi in general where users require pattern recognition to mitigate risk: `{` `"risk_score": 85,` `"risk_factors": ["unusual_trading_pattern", "high_leverage"],` `"recommended_actions": {` `"increase_collateral_requirement": 15,` `"reduce_max_leverage": 2` `}` `}` 5. **Memory Formation**: * The interaction is stored as a memory, enriching REI's knowledge base **without any memory decay** * This allows her to learn from the experience and refine future interactions. #### [](#learning-and-adaptation) **Learning and Adaptation** REI's ability to learn and adapt over time is a critical aspect of her intelligence: * **Continuous Self-Improvement**: By analyzing the outcomes of her actions, REI adjusts her strategies to improve effectiveness. * **Knowledge Sharing**: Her on-chain memories can be accessed by other agents or smart contracts, fostering collaboration. * **Transparency**: On-chain storage of her actions and decisions provides an auditable trail, enhancing trust. [PreviousSocial Interaction & Real-time Processing](/0xreisearch/rei_00-x-version-legacy-update-tba/social-interaction-and-real-time-processing) [Next//Core](/0xreisearch/core) Last updated 23 days ago --- # REI's Cognitive Layers | 0xReisearch [PreviousREI: A New Kind of Blockchain Intelligence](/0xreisearch/rei_00-x-version-legacy-update-tba/rei-a-new-kind-of-blockchain-intelligence) [NextSocial Interaction & Real-time Processing](/0xreisearch/rei_00-x-version-legacy-update-tba/social-interaction-and-real-time-processing) Last updated 4 months ago REI's cognitive architecture represents a sophisticated interplay between four distinct layers, each interacting with the Oracle System and ERCData in unique ways. This layered approach enables complex analysis while maintaining deterministic blockchain interactions. ### [](#layer-interaction-overview) Layer Interaction Overview ### [](#the-thinking-layer-raw-intelligence) The Thinking Layer: Raw Intelligence The Thinking Layer serves as REI's primary interface with raw data. Like the analytical left brain in humans, it processes concrete information and identifies base patterns. #### [](#oracle-interaction) Oracle Interaction The Thinking Layer primarily uses the Oracle System for: * Raw data retrieval * Initial pattern matching * Metric calculation * Event processing #### [](#ercdata-interaction) ERCData Interaction With ERCData, the Thinking Layer: * Queries existing patterns * Stores new observations * Updates basic metrics * Maintains data relationships ### [](#the-reasoning-layer-understanding-context) The Reasoning Layer: Understanding Context The Reasoning Layer adds context and meaning to processed information. It understands relationships, implications, and broader patterns. #### [](#oracle-integration) Oracle Integration The Reasoning Layer leverages the Oracle for: * Complex pattern recognition * Historical analysis * Relationship discovery * Context verification #### [](#ercdata-usage) ERCData Usage With ERCData, it performs: * Pattern relationship mapping * Context storage * Historical analysis * Relationship indexing ### [](#the-decision-layer-choice-and-action) The Decision Layer: Choice and Action The Decision Layer synthesizes information from previous layers to determine appropriate actions. #### [](#oracle-integration-1) Oracle Integration The Decision Layer uses the Oracle to: * Verify potential actions * Check state consistency * Validate patterns * Confirm feasibility #### [](#ercdata-interaction-1) ERCData Interaction With ERCData, it: * Checks historical decisions * Stores decision patterns * Updates action records * Maintains decision context ### [](#the-acting-layer-execution-and-verification) The Acting Layer: Execution and Verification The Acting Layer transforms decisions into concrete blockchain actions. #### [](#oracle-usage) Oracle Usage The Acting Layer relies on the Oracle for: * Action transformation * State verification * Execution monitoring * Result confirmation #### [](#ercdata-integration) ERCData Integration With ERCData, it handles: * Action recording * State updates * Pattern confirmation * Result storage ### [](#cross-layer-interaction) Cross-Layer Interaction The true power of REI's architecture emerges in how these layers work together: This interaction flow enables: 1. Comprehensive data analysis 2. Context-aware processing 3. Intelligent decision making 4. Reliable execution ### [](#memory-flow) Memory Flow Throughout these layers, memory systems maintain context and enable learning: The memory systems ensure: * Information persistence * Pattern learning * Context maintenance * State consistency ### [](#result-generation) Result Generation The final output from this layered processing is always deterministic, though the path to that output may involve complex analysis: This sophisticated yet deterministic processing enables REI to provide intelligent insights while maintaining the reliability requirements of blockchain systems. In the next section, we'll explore how this architecture enables REI's social media interactions and real-time processing capabilities. ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FeKYVqpg8tnu0V5dCAK9S%252FScreenshot%25202024-11-21%2520at%252007.32.17.png%3Falt%3Dmedia%26token%3D63bbb4b8-71a0-4b1a-a5a8-4b43f6f4513c&width=768&dpr=4&quality=100&sign=25bcfa19&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FPR6OvY8H9cFv5YntK84P%252FScreenshot%25202024-11-21%2520at%252007.32.51.png%3Falt%3Dmedia%26token%3D806ea570-6c78-4c8e-809e-53ad4444bfa1&width=768&dpr=4&quality=100&sign=851e5fcb&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FYndfM4A6xp6NgaS8N4ro%252FScreenshot%25202024-11-21%2520at%252007.33.28.png%3Falt%3Dmedia%26token%3D914fa908-9e4c-4e83-a106-1286850f84ce&width=768&dpr=4&quality=100&sign=34b3af80&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FaWLZx4lOsbLpE3FlD7lA%252FScreenshot%25202024-11-21%2520at%252007.33.56.png%3Falt%3Dmedia%26token%3Dc8755c8b-84fe-4ad7-b3de-acfb6e32cf8d&width=768&dpr=4&quality=100&sign=520ed38a&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FfliOvazWYc3jbAptlRgT%252FScreenshot%25202024-11-21%2520at%252007.34.29.png%3Falt%3Dmedia%26token%3D2a7b3f44-9e17-41d3-a74f-41af0c780df0&width=768&dpr=4&quality=100&sign=a16b476&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252Ff4JnjzshhMkNgPl3qKPi%252FScreenshot%25202024-11-21%2520at%252007.35.13.png%3Falt%3Dmedia%26token%3D676c9170-4949-44b7-9ae7-e7a4a0d120f1&width=768&dpr=4&quality=100&sign=a541e59c&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FVun1AH7SuiDcjcYWtver%252FScreenshot%25202024-11-21%2520at%252007.35.37.png%3Falt%3Dmedia%26token%3D4e7851e0-b0df-49c4-8342-233dad35cf06&width=768&dpr=4&quality=100&sign=9e7111c6&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FUDBkcD1wRscy7ZMq6MHF%252FScreenshot%25202024-11-21%2520at%252007.36.27.png%3Falt%3Dmedia%26token%3D870e2557-4ee7-478d-894d-01da0c07ac7e&width=768&dpr=4&quality=100&sign=915635b2&sv=2) --- # Custom Tools | 0xReisearch Following the Function Calling schema, you can develop your own tools and functions and give your Unit access to them - as you'd do with a regular model - making the Unit forms usage memories with them. The only actual limitation is that those tools are only in your code: outside of it, the Unit will still have memories of them but it will be impossible for it to recall the tools, leading to possible weird behavior. Solution: Once you plug an Unit in your code, try to use it only there, especially if there it has access to specific functions not available in the Factory. We're currently testing a couple of solutions to let users define Custom Tools directly in the factory and an update will soon come together with a Vault System where you can safely store your data and keys without compromising opsec. ### [](#custom-tools-quickstart) Custom Tools Quickstart JavaScriptPython Copy const ReiCoreSdk = require('reicore-sdk'); // Initialize the SDK const apiKey = 'your_unit_secret_token'; const reiAgent = new ReiCoreSdk({ agentSecretKey: apiKey }); // Define your custom functions const getWeather = (location) => { // Implement your weather API call here return `Weather in ${location}: Sunny, 22°C`; }; const searchDatabase = (query) => { // Implement your database search here return `Found 3 results for: ${query}`; }; // Define function schemas const functions = [\ {\ name: "get_weather",\ description: "Get the current weather for a location",\ parameters: {\ type: "object",\ properties: {\ location: {\ type: "string",\ description: "The city and state, e.g. San Francisco, CA"\ }\ },\ required: ["location"]\ }\ },\ {\ name: "search_database",\ description: "Search the database for specific information",\ parameters: {\ type: "object",\ properties: {\ query: {\ type: "string",\ description: "The search query"\ }\ },\ required: ["query"]\ }\ }\ ]; // Function mapping const functionMap = { get_weather: getWeather, search_database: searchDatabase }; async function processWithFunctions(query) { try { // First call to get function details const response = await reiAgent.chatCompletions(query, { functions }); const message = response.choices[0].message; // Check if the agent wants to call a function if (message.function_call) { const functionName = message.function_call.name; const functionArgs = JSON.parse(message.function_call.arguments); // Call the function const functionResponse = functionMap[functionName](...Object.values(functionArgs)); // Send the function response back to the agent const secondResponse = await reiAgent.chatCompletions([\ { role: "user", content: query },\ { role: "function", name: functionName, content: functionResponse }\ ], { functions }); return secondResponse.choices[0].message.content; } return message.content; } catch (error) { console.error('Error:', error); return null; } } // Example usage processWithFunctions("What's the weather in Tokyo?") .then(response => console.log(response)) .catch(error => console.error(error)); Copy from client import Client import json # Initialize the client client = Client( api_key="your_unit_secret_token", base_url="https://api.reisearch.box" ) # Define your custom functions def get_weather(location: str) -> str: # Implement your weather API call here return f"Weather in {location}: Sunny, 22°C" def search_database(query: str) -> str: # Implement your database search here return f"Found 3 results for: {query}" # Define function schemas functions = [\ {\ "name": "get_weather",\ "description": "Get the current weather for a location",\ "parameters": {\ "type": "object",\ "properties": {\ "location": {\ "type": "string",\ "description": "The city and state, e.g. San Francisco, CA"\ }\ },\ "required": ["location"]\ }\ },\ {\ "name": "search_database",\ "description": "Search the database for specific information",\ "parameters": {\ "type": "object",\ "properties": {\ "query": {\ "type": "string",\ "description": "The search query"\ }\ },\ "required": ["query"]\ }\ }\ ] # Function mapping function_map = { "get_weather": get_weather, "search_database": search_database } def process_with_functions(query: str): try: # First call to get function details response = client.chat.completions.create( model="Unit01", messages=[{"role": "user", "content": query}], functions=functions ) message = response.choices[0].message # Check if the agent wants to call a function if message.function_call: function_name = message.function_call.name function_args = json.loads(message.function_call.arguments) # Call the function function_response = function_map[function_name](**function_args) # Send the function response back to the agent second_response = client.chat.completions.create( model="Unit01", messages=[\ {"role": "user", "content": query},\ {"role": "function", "name": function_name, "content": function_response}\ ], functions=functions ) return second_response.choices[0].message.content return message.content except Exception as e: print(f"Error: {e}") return None # Example usage response = process_with_functions("What's the weather in Tokyo?") print(response) ### [](#advanced-custom-tools) Advanced Custom Tools #### [](#multiple-function-calls) Multiple Function Calls Copy def process_with_multiple_functions(query: str): try: messages = [{"role": "user", "content": query}] while True: response = client.chat.completions.create( model="Unit01", messages=messages, functions=functions ) message = response.choices[0].message if not message.function_call: return message.content # Add the function call to messages messages.append({ "role": "assistant", "content": None, "function_call": { "name": message.function_call.name, "arguments": message.function_call.arguments } }) # Call the function function_name = message.function_call.name function_args = json.loads(message.function_call.arguments) function_response = function_map[function_name](**function_args) # Add the function response to messages messages.append({ "role": "function", "name": function_name, "content": function_response }) except Exception as e: print(f"Error: {e}") return None #### [](#function-calling-with-context) Function Calling with Context Copy def process_with_context(query: str, context: dict): try: # Add context to the system message system_message = { "role": "system", "content": json.dumps(context) } response = client.chat.completions.create( model="Unit01", messages=[\ system_message,\ {"role": "user", "content": query}\ ], functions=functions ) # Process function calls as before message = response.choices[0].message if message.function_call: function_name = message.function_call.name function_args = json.loads(message.function_call.arguments) function_response = function_map[function_name](**function_args) second_response = client.chat.completions.create( model="Unit01", messages=[\ system_message,\ {"role": "user", "content": query},\ {"role": "function", "name": function_name, "content": function_response}\ ], functions=functions ) return second_response.choices[0].message.content return message.content except Exception as e: print(f"Error: {e}") return None [PreviousResearch](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/research) [NextOracle Cost & Performance Metrics (Legacy, Update TBA)](/0xreisearch/oracle-cost-and-performance-metrics-legacy-update-tba) Last updated 23 days ago --- # DeFi (Current Level : 1) | 0xReisearch [PreviousAdditional Capability (Provided & Custom)](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom) [NextResearch](/0xreisearch/factory-and-core-api-sdk-cross-framework/additional-capability-provided-and-custom/research) Last updated 23 days ago Every account on the Factory has an attached wallet that each of its Reigents share. To see the wallet address and fund it, click on the 3 dots symbol next to "Create", and then "View Agent Wallet" _During testing phase, only base-mainnet is supported._ Fund the wallet, and then you can ask for DeFi operation in your questions _Please note that during testing phase, only Swaps and Transfers are available. It can be buggy, so we advise you to not deposit big amount of funds in the Agent Wallet._ ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252Fj9jakxEPMFTmRp7qr0Mo%252FScreenshot%25202025-03-26%2520at%252014.35.11.png%3Falt%3Dmedia%26token%3D5c441f53-bd7d-4453-b0b7-fd88c035c80a&width=768&dpr=4&quality=100&sign=9a3e3ded&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FWVYIFpVERDqJBFHn75SR%252FScreenshot%25202025-03-26%2520at%252014.35.33.png%3Falt%3Dmedia%26token%3D7b55420e-ffe4-459b-8272-5a1050b1b334&width=768&dpr=4&quality=100&sign=cc97f738&sv=2) ![](https://0xreisearch.gitbook.io/~gitbook/image?url=https%3A%2F%2F1127208460-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FoEKEZNUf1k9neYaey5Nw%252Fuploads%252FTF4dWeeCZzk0Nr4QjE12%252FScreenshot%25202025-03-26%2520at%252015.02.24.png%3Falt%3Dmedia%26token%3D0c1958f6-da89-4474-a99e-ca6604206157&width=768&dpr=4&quality=100&sign=2424a120&sv=2) ---