# kerebrom

> kerebrom — ulianbass-kerebrom. Use this tool when you need to provide local-first persistent memory for AI agents, solving data consistency and availability issues in applications like Claude, Codex, and Cursor. It offers a simple interface with a single Go binary installation, supporting shared SQLite/FTS5 memory and lifecycle hooks. Ideal for use cases requiring reliable, local data storage and retrieval in AI-driven projects, with integration capabilities via git.

Canonical page: https://skillsregistry.net/skills/ulianbass-kerebrom  
JSON: https://api.skillsregistry.net/v1/skills/ulianbass-kerebrom

## Description

Local-first persistent memory for AI agents. One Go binary installs MCP, lifecycle hooks, and shared SQLite/FTS5 memory for Claude, Codex, Cursor, and more.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/ulianbass/kerebrom)

## 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": "ulianbass-kerebrom"
    }
  }
}
```

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