# mimirs

> mimirs — thewinci-mimirs. Use this tool when you need to provide AI coding agents with a persistent and searchable memory of your codebase, enabling them to access and learn from your project's history and context. It solves problems related to code knowledge retention and retrieval, allowing agents to make more informed decisions. With mimirs, you can input your Git repository and output a searchable database of your codebase.

Canonical page: https://skillsregistry.net/skills/thewinci-mimirs  
JSON: https://api.skillsregistry.net/v1/skills/thewinci-mimirs

## Description

Local MCP server that gives AI coding agents persistent, searchable memory of your codebase

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** search
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/TheWinci/mimirs)

## 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": "thewinci-mimirs"
    }
  }
}
```

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