Cortex — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by cdeust · MCP Server · ★ 73

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Cortex safe to install? View the security audit →

About Cortex

Getting Started · What's New · <a href="#the-sci

agent-memory-systemagent-skillscausal-inferenceclaude-codecodexcognitive-architecturecognitive-scienceepisodic-memorygemini-clihopfield-network

Quick Facts

Stars73
Forks13
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score64.4564990076477/100
Open Issues7
Last Updated2026-10-02
Created2026-03-18
Platformsclaude-code, cli, codex, gemini, mcp, python
Est. Tokens~21k

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%)
  • 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%)

Cortex alternative? Top 6 similar tools

Looking for a Cortex alternative? If you're comparing Cortex with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Zikkaron by amanhij · ⭐ 62

    Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, pr

  • iai-mcp by CodeAbra · ⭐ 119

    The best-benchmarked open-source memory system for AI coding assistants

  • mneme by slow-stack · ⭐ 138

    🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in

  • claude-mem-lite by sdsrss · ⭐ 61

    Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across

  • roampal-core by roampal-ai · ⭐ 51

    Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo

  • Ori-Mnemos by aayoawoyemi · ⭐ 328

    Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

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 Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based conso. It is categorized as a MCP Server with 73 GitHub stars.

What programming language is Cortex written in?

Cortex is primarily written in Python. It covers topics such as agent-memory-system, agent-skills, causal-inference.

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 73 stars and 13 forks, indicating an active community.

What license does Cortex use?

Cortex is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to Cortex?

The top alternatives to Cortex on Agent Skills Hub include Zikkaron, iai-mcp, mneme. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools