# MARM Systems

> Use this tool when you need to provide AI agents with a unified memory layer that persists across sessions, enabling features like semantic search, auto-classification, and smart recall. It solves problems related to knowledge retention, information retrieval, and session continuity, and accepts inputs via HTTP, STDIO, and WebSocket transports. Ideal for use cases requiring reusable instructions, session logging, and enhanced AI agent memory and recall capabilities.

Canonical page: https://skillsregistry.net/skills/lyellr88-marm  
JSON: https://api.skillsregistry.net/v1/skills/lyellr88-marm

## Description

MARM (Memory Accurate Response Mode) provides a unified, persistent memory layer for AI agents that survives across sessions. Features include semantic search using AI embeddings, auto-classification of content, smart recall with vector similarity, notebook management for reusable instructions, and session logging. Supports HTTP, STDIO, and WebSocket transports.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/lyellr88-marm)
- **Repository:** <https://github.com/lyellr88/marm-systems>

## 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": "lyellr88-marm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lyellr88-marm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lyellr88-marm/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