Collaboration between GitHub users @jasonkneen and @ExpressionsBot
Uses TensorFlow.js for efficient tensor operations in the neural memory model with operations wrapped in tf.tidy() for proper memory management
Implements a type-safe implementation with TypeScript including type-safe MCP tool definitions
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables neural memory sequence learning with a memory-augmented model for improved code understanding and generation, featuring state management, novelty detection, and model persistence.
- Overview
- Features
- Usage
- Installation
- Running the Server
- Development
- Testing
- Advanced Features
- Citation
- License
Related Resources
Related MCP Servers
- -securityAlicense-qualityProvides deep source code analysis for Unreal Engine codebases, allowing AI assistants to understand C++ class structures, search code, and analyze subsystems.Last updated -102MIT License
- AsecurityAlicenseAqualityEnhances Claude AI with persistent memory storage for Infrastructure-as-Code components, supporting version tracking and relationship mapping for Terraform and Ansible resources.Last updated -236MIT License
- -securityAlicense-qualityThis advanced memory server facilitates neural memory-based sequence learning and prediction, enhancing code generation and understanding through state maintenance and manifold optimization as inspired by Google Research's framework.Last updated -3469MIT License
- -securityFlicense-qualityProvides a project memory bank and RAG context provider for enhanced code understanding and management through vector embeddings, integrated with RooCode and Cline.Last updated -18