# Mind Keg

> Use this tool when you need to retain knowledge and insights across coding sessions, solving problems of lost context and duplicated effort. The Mind Keg stores and retrieves atomic learnings, such as debugging insights and codebase conventions, through a local SQLite database with semantic search capabilities. It is ideal for use in multi-repository environments where persistent memory and access control are crucial.

Canonical page: https://skillsregistry.net/skills/carloluisito-mind-keg  
JSON: https://api.skillsregistry.net/v1/skills/carloluisito-mind-keg

## Description

Provides persistent, cross-session memory for AI coding agents by storing atomic learnings — debugging insights, architectural decisions, and codebase conventions — in a local SQLite database. Supports semantic search via FastEmbed or OpenAI embeddings with keyword fallback, three scoping levels (repository, workspace, global), and API key authentication for multi-repository access control.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/carloluisito-mind-keg)
- **Repository:** <https://github.com/carloluisito/mindkeg-mcp>

## 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": "carloluisito-mind-keg"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/carloluisito-mind-keg` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/carloluisito-mind-keg/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