# cairntir

> cairntir — pnmcguire480-cairntir. Use this tool when you need to overcome cross-chat AI amnesia and ensure consistent memory recall in conversational AI models. The cairntir tool provides a memory-first reasoning layer, storing and retrieving information verbatim to inform prediction-bound decisions. It is ideal for applications requiring contextual understanding and reliable knowledge retention, such as chatbots and virtual assistants.

Canonical page: https://skillsregistry.net/skills/pnmcguire480-cairntir  
JSON: https://api.skillsregistry.net/v1/skills/pnmcguire480-cairntir

## Description

Local-first persistent memory MCP server for Claude Code, Codex, Cursor, Qwen Code, and AI coding agents. Cross-session, cross-agent SQLite memory.

## Trust

- **Trust score (0–1):** 0.77
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/pnmcguire480/cairntir)

## 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": "pnmcguire480-cairntir"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pnmcguire480-cairntir` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pnmcguire480-cairntir/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