# a-memory

> a-memory — cipher208-a-memory. Use this tool when you need to implement a secure and efficient memory system for AI agents, solving problems related to knowledge storage and retrieval. It provides a 4-tier memory structure with hybrid search capabilities and encryption, accepting knowledge graphs and other data as inputs and producing secure and organized outputs. Ideal for local AI applications requiring robust and private memory management.

Canonical page: https://skillsregistry.net/skills/cipher208-a-memory  
JSON: https://api.skillsregistry.net/v1/skills/cipher208-a-memory

## Description

a-memory: 4-tier AI agent memory in plain SQLite — 5 MCP primitives, hybrid FTS5+binary search, knowledge graphs, envelope encryption. Local-only.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Cipher208/a-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": "cipher208-a-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cipher208-a-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cipher208-a-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