# shared-memory

> shared-memory — l0s0s-mcp. Use this tool when you need to access and manage a unified knowledge base across multiple AI clients, solving problems of data fragmentation and inconsistency. It provides a persistent storage interface for inputs like facts, preferences, and decisions, and outputs relevant information through semantic search. Ideal for use cases requiring shared context and continuous learning across AI agents.

Canonical page: https://skillsregistry.net/skills/l0s0s-mcp  
JSON: https://api.skillsregistry.net/v1/skills/l0s0s-mcp

## Description

Provides a shared long-term memory across multiple AI clients, enabling persistent storage and retrieval of facts, preferences, decisions, and snippets with semantic search.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rayymhmo0v)
- **Repository:** <https://github.com/l0s0s/mcp>

## 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": "l0s0s-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/l0s0s-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/l0s0s-mcp/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