# Cortex

> Cortex — cdeust-cortex. Use this tool when you need to enhance Claude Code with persistent memory, leveraging 41 neuroscience papers and 20 biological mechanisms to improve retrieval performance. It solves problems of knowledge retrieval and information storage, accepting inputs from git and outputting optimized results through PostgreSQL and pgvector. Use Cortex in contexts where advanced memory and retrieval capabilities are required, such as complex coding projects or data-intensive applications.

Canonical page: https://skillsregistry.net/skills/cdeust-cortex  
JSON: https://api.skillsregistry.net/v1/skills/cdeust-cortex

## Description

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 consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/cdeust/Cortex)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cdeust-cortex"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cdeust-cortex` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cdeust-cortex/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt