# Memory Crystal

> Use this tool when you need to enhance AI context understanding and knowledge retention, solving problems like information loss and irrelevant responses. The Memory Crystal provides a two-layer memory system, accepting input messages and outputting relevant context-injected responses, with a vector-indexed knowledge graph interface. Ideal for use in conversational AI applications requiring robust contextual awareness and knowledge management.

Canonical page: https://skillsregistry.net/skills/memorycrystal  
JSON: https://api.skillsregistry.net/v1/skills/memorycrystal

## Description

Provides a two-layer memory system with short-term message storage and long-term extracted knowledge backed by a vector-indexed knowledge graph. The context engine runs before every AI response, combining time-ordered recent messages, semantic search across both memory layers, and graph-based memory ranking to inject relevant context. Ships as an MCP server, OpenClaw plugin, Next.js dashboard, and Convex-backed multi-tenant cloud service. Published on npm as crystal-memory.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/memorycrystal)
- **Repository:** <https://github.com/memorycrystal/memorycrystal/tree/HEAD/mcp-server>

## 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": "memorycrystal"
    }
  }
}
```

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