# Memory OS

> Use this tool when you need to implement a robust memory system that enables efficient information retrieval and storage across multiple projects and sessions. It solves problems related to knowledge management, information overload, and context switching by providing semantic search, automatic chat extraction, and cross-project knowledge linking. It takes in unstructured data and outputs relevant information, making it ideal for use cases that require persistent memory storage and retrieval, such as chatbots, virtual assistants, and knowledge graphs.

Canonical page: https://skillsregistry.net/skills/romainsantoli-memory-os  
JSON: https://api.skillsregistry.net/v1/skills/romainsantoli-memory-os

## Description

Implements an adaptive memory layer with FAISS-based semantic search, automatic chat extraction, and cross-project knowledge linking. Enables persistent memory storage and retrieval across sessions and projects, with support for contextual recall and memory consolidation.

## 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:** search
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/romainsantoli-memory-os)
- **Repository:** <https://github.com/romainsantoli-web/memory-os-ai>

## 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": "romainsantoli-memory-os"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/romainsantoli-memory-os` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/romainsantoli-memory-os/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