# memoryguard

> memoryguard — merakosiris-memoryguard. Use this tool when you need to manage and govern memory for coding agents like Codex, Claude Code, and others, to prevent data duplication and ensure compliance with shared rules. It provides features like deduplication, token insights, audit, and rollback, making it ideal for coding projects that require memory optimization and version control through git. By using Memoryguard, you can ensure efficient and secure memory management for your coding agents.

Canonical page: https://skillsregistry.net/skills/merakosiris-memoryguard  
JSON: https://api.skillsregistry.net/v1/skills/merakosiris-memoryguard

## Description

Local-first MCP memory governance for coding agents — Codex, Claude Code, Cursor, Grok, and Trae. Shared rules, deduplication, token insights, audit, and rollback.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/MerakOsiris/memoryguard)

## 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": "merakosiris-memoryguard"
    }
  }
}
```

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