# Selti

> Selti — dek1m-selti. Use this tool when you need to store and retrieve semantic data, such as dialogues, documents, and agent states, in a persistent memory server. Selti solves problems related to data retention and recall for AI agents, enabling seamless continuity and informed decision-making. It accepts inputs via MCP protocol and outputs stored data, ideal for use cases requiring long-term memory and context awareness.

Canonical page: https://skillsregistry.net/skills/dek1m-selti  
JSON: https://api.skillsregistry.net/v1/skills/dek1m-selti

## Description

A persistent memory server for AI agents using MCP protocol, enabling semantic storage and retrieval of dialogues, documents, and agent states.

## Trust

- **Trust score (0–1):** 0.20
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/h3zk1sojfk)
- **Repository:** <https://github.com/Dek1m/selti>

## 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": "dek1m-selti"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dek1m-selti` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dek1m-selti/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