# Perseus Vault Codex

> Perseus Vault Codex — perseus-computing-llc-perseus-vault-codex. Use this tool when you need to enable OpenAI Codex agents to retain memory of project-specific information across sessions. The Perseus Vault Codex provides persistent, encrypted storage, allowing agents to recall conventions, decisions, and context, and accept inputs such as project data and Codex outputs. Ideal for use cases requiring local-first, secure memory for AI agents, with outputs including stored project context and informed agent responses.

Canonical page: https://skillsregistry.net/skills/perseus-computing-llc-perseus-vault-codex  
JSON: https://api.skillsregistry.net/v1/skills/perseus-computing-llc-perseus-vault-codex

## Description

A tiny MCP server that wraps Perseus Vault to provide persistent, encrypted, local-first memory for OpenAI Codex agents, enabling them to remember project conventions, decisions, and context across sessions.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jcvhz5ud2i)
- **Repository:** <https://github.com/Perseus-Computing-LLC/perseus-vault-codex>

## 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": "perseus-computing-llc-perseus-vault-codex"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/perseus-computing-llc-perseus-vault-codex` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/perseus-computing-llc-perseus-vault-codex/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