# Decay Memory

> Use this tool when you need to provide AI agents with persistent memory that naturally forgets over time, enabling them to learn from experience and adapt to changing environments. It solves problems of information overload and outdated knowledge by implementing layered decay and semantic search capabilities. Ideal for use cases requiring autonomous learning and decision-making, such as chatbots, virtual assistants, or robotic agents.

Canonical page: https://skillsregistry.net/skills/trssantos-decay-memory  
JSON: https://api.skillsregistry.net/v1/skills/trssantos-decay-memory

## Description

An MCP server that gives AI agents persistent, forgetting memory with layered decay, semantic search via token overlap, and zero external dependencies.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/mw2nj5wwr8)
- **Repository:** <https://github.com/trssantos/decay-memory>

## 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": "trssantos-decay-memory"
    }
  }
}
```

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