Cortex

by cdeust · MCP Server · ★ 37

About Cortex

Persistent memory for Claude Code — 41 neuroscience papers, 26 biological mechanisms with paper-bearing per-mechanism ablation evidence (E1 v3). LongMemEval R@10 98.4% / MRR 0.9124 (n=500). LoCoMo R@10 94.2% / MRR 0.8278 (n=1986). BEAM-10M +33.4% over flat retrieval. PostgreSQL + pgvector. Verified via 31-row two-benchmark ablation campaign.

agent-memory-systemanthropicartificial-intelligencecausal-inferenceclaudeclaude-codeclaude-code-plugincognitive-architecturecognitive-scienceepisodic-memory

Quick Facts

Stars37
Forks8
LanguagePython
CategoryMCP Server
Quality Score28.8/100
Last Updated2026-05-21
Created2026-03-18
Platformsclaude-code, mcp, python
Est. Tokens~4338k

Compatible Skills

These tools work well together with Cortex for enhanced workflows:

  • Zikkaron — semantic(0.61)+rare_topics+same_lang+similar_pop+shared_platform (66%)
  • BRAD-Video — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • roampal-core — semantic(0.36)+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • MemOS — semantic(0.34)+complementary+rare_topics+same_lang+shared_platform (56%)
  • claude-prime — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Cortex?

Cortex is Persistent memory for Claude Code — 41 neuroscience papers, 26 biological mechanisms with paper-bearing per-mechanism ablation evidence (E1 v3). LongMemEval R@10 98.4% / MRR 0.9124 (n=500). LoCoMo R@1. It is categorized as a MCP Server with 37 GitHub stars.

What programming language is Cortex written in?

Cortex is primarily written in Python. It covers topics such as agent-memory-system, anthropic, artificial-intelligence.

How do I install or use Cortex?

You can find installation instructions and usage details in the Cortex GitHub repository at github.com/cdeust/Cortex. The project has 37 stars and 8 forks, indicating an active community.

View on GitHub → Browse MCP Server tools