# elefante

> Use this tool when you need to manage and store memories for MCP agents in a portable and auditable way. Elefante solves the problem of memory consistency and human-editability across different AI agents by storing memories as Markdown files in a Git repository. It takes in memory data as input and outputs human-readable Markdown files, making it ideal for use cases requiring transparent and version-controlled memory management.

Canonical page: https://skillsregistry.net/skills/amenophis1er-elefante  
JSON: https://api.skillsregistry.net/v1/skills/amenophis1er-elefante

## Description

Open, Git-native memory protocol for MCP agents: stores memories as Markdown files in a Git repo, enabling portability, auditability, and human-editable memory across different AI agents.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/oomivjff04)
- **Repository:** <https://github.com/amenophis1er/elefante>

## 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": "amenophis1er-elefante"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/amenophis1er-elefante` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/amenophis1er-elefante/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