hifriendbot/cogmemai-mcp

Overview

Cogmemai-mcp provides cognitive memory for AI systems via a TypeScript server implementing the Model Context Protocol. It achieves 91% on the LoCoMo benchmark, surpassing human performance, and is designed for autonomous robots, self-driving vehicles, defense systems, and coding assistants.

Best for

Best for
Developers building AI agents that require long-term memory and context retention

Use cases

• Adding persistent memory to coding assistants
• Enabling autonomous robots to recall past experiences
• Improving context retention in defense or vehicle AI systems

Notes

Cogmemai-mcp provides cognitive memory for AI systems via a TypeScript server implementing the Model Context Protocol. It achieves 91% on the LoCoMo benchmark, surpassing human performance, and is designed for autonomous robots, self-driving vehicles, defense systems, and coding assistants.

6 stars on GitHub. Last updated 2026-05-31. Licensed MIT.

Use cases

• Adding persistent memory to coding assistants
• Enabling autonomous robots to recall past experiences
• Improving context retention in defense or vehicle AI systems

Pros

• Benchmark performance exceeds human baseline on LoCoMo
• Broad applicability across robotics, defense, and coding
• Built in TypeScript for type safety and broad ecosystem compatibility

Cons

• Very early stage with only 6 stars and limited community adoption
• Narrowly focuses on cognitive memory, not a general AI framework
• Documentation and examples sparse due to small project size

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.