# sostenuto

> Use this tool when you need to enhance AI companions with persistent memory capabilities, solving problems of knowledge retention and recall in conversational interfaces. It provides structured recall, reinforcement, and time-decayed retrieval through an MCP interface, accepting input parameters and returning relevant memory entries. Ideal for use cases requiring contextual understanding and adaptive learning in AI agents.

Canonical page: https://skillsregistry.net/skills/llu929-sostenuto  
JSON: https://api.skillsregistry.net/v1/skills/llu929-sostenuto

## Description

Provides a selective persistent memory layer for AI companions, enabling structured recall, reinforcement, and time-decayed retrieval through an MCP interface.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/motxt96r9o)
- **Repository:** <https://github.com/llu929/sostenuto>

## 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": "llu929-sostenuto"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/llu929-sostenuto` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/llu929-sostenuto/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