# AMP (Agent Memory Protocol)

> Use this tool when you need to enable AI agents to retain and recall information over time, solving problems related to knowledge retention and retrieval in applications such as conversational interfaces, decision support systems, and entity relationship modeling. AMP provides a robust interface for storing, searching, and querying memory nodes through natural language inputs, with outputs including relevance scores, semantic cluster visualizations, and consolidated insights. It is particularly useful in contexts where cloud-based services are not feasible or desirable, offering a self-contained solution for AI agent memory management.

Canonical page: https://skillsregistry.net/skills/akshayaggarwal99-amp  
JSON: https://api.skillsregistry.net/v1/skills/akshayaggarwal99-amp

## Description

AMP (Agent Memory Protocol) provides AI agents with persistent memory capabilities through a three-layer architecture mimicking human cognition: short-term memory for immediate context, long-term memory for consolidated insights, and a graph layer for entity relationships. Built with SQLite for storage and FastEmbed for local embeddings, it features hybrid vector and full-text search without requiring cloud APIs. Includes an interactive web dashboard with real-time semantic cluster visualization using D3.js physics simulation, showing how memory nodes cluster by meaning and topological connections between related concepts. Supports natural language querying with relevance scoring and memory consolidation processes that move thoughts from working memory to long-term storage.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/akshayaggarwal99-amp)
- **Repository:** <https://github.com/akshayaggarwal99/amp>

## 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": "akshayaggarwal99-amp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/akshayaggarwal99-amp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/akshayaggarwal99-amp/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