# rekal

> rekal — janbjorge-rekal. Use this tool when you need to enhance the long-term memory of large language models (LLMs) by storing and retrieving information from a hybrid search-backed SQLite database. It solves the problem of knowledge retention and recall for LLMs, allowing them to learn from past interactions and maintain context over time. The rekal tool accepts input from LLMs and git, and outputs relevant information, making it ideal for use cases where persistent memory and knowledge retention are crucial.

Canonical page: https://skillsregistry.net/skills/janbjorge-rekal  
JSON: https://api.skillsregistry.net/v1/skills/janbjorge-rekal

## Description

Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/janbjorge/rekal)

## 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": "janbjorge-rekal"
    }
  }
}
```

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