# mynd

> mynd — oxhive-mynd. Use this tool when you need to persist project context and architectural decisions for AI coding agents, enabling seamless recall of preferences and continuity across sessions. It solves the problem of lost context and duplicated effort, supporting integration with popular coding platforms like Claude Code and Codex. With mynd, inputs include project context and architectural decisions, and outputs include recalled preferences and stored project information, streamlining AI coding workflows.

Canonical page: https://skillsregistry.net/skills/oxhive-mynd  
JSON: https://api.skillsregistry.net/v1/skills/oxhive-mynd

## Description

Persistent memory MCP server for AI coding agents. Injects project context at session start, stores architectural decisions, and recalls preferences works with Claude Code, Cursor, Windsurf, OpenCode, Kimi, and Codex.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-27

## Source

- **Source listing:** [GitHub](https://github.com/oxHive/mynd)

## 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": "oxhive-mynd"
    }
  }
}
```

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