# cogmem

> cogmem — dcondrey-cogmem. Use this tool when you need to enhance the memory capabilities of AI coding agents, enabling them to learn and improve from experience. The cogmem tool solves problems related to knowledge retention and code optimization, providing a verifiable memory layer that integrates with git for secure and reliable storage. It accepts code and experience data as inputs and outputs optimized, self-improved code solutions.

Canonical page: https://skillsregistry.net/skills/dcondrey-cogmem  
JSON: https://api.skillsregistry.net/v1/skills/dcondrey-cogmem

## Description

A self-improving, verifiable memory layer for AI coding agents.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/dcondrey/cogmem)

## 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": "dcondrey-cogmem"
    }
  }
}
```

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