# Audrey

> Use this tool when you need to manage and secure AI agent memory, ensuring local-first data handling and robust recall capabilities. Audrey solves problems related to data integrity, validation, and contradiction handling, providing a reliable interface for storing and retrieving memory capsules. It is ideal for use cases requiring secure, localized AI data management, with inputs including AI agent requests and outputs comprising validated, stored data.

Canonical page: https://skillsregistry.net/skills/evilander-audrey  
JSON: https://api.skillsregistry.net/v1/skills/evilander-audrey

## Description

Local-first memory firewall and MCP server for AI agents. Audrey provides recall, memory capsules, preflight checks, reflexes, validation, tool-trace learning, contradiction handling, and SQLite/sqlite-vec storage.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a186ld9x67)
- **Repository:** <https://github.com/Evilander/Audrey>

## 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": "evilander-audrey"
    }
  }
}
```

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