# hmem

> hmem — bumblebiber-hmem. Use this tool when you need to provide AI agents with humanlike persistent memory, enabling them to store and recall information across interactions. The hmem tool solves problems of knowledge retention and recall, allowing agents to learn and adapt over time. It accepts inputs from various interfaces, including Claude Code and Gemini CLI, and outputs stored data through a 5-level lazy-loaded SQLite memory.

Canonical page: https://skillsregistry.net/skills/bumblebiber-hmem  
JSON: https://api.skillsregistry.net/v1/skills/bumblebiber-hmem

## Description

Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-06-18

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-23

## Source

- **Source listing:** [GitHub](https://github.com/Bumblebiber/hmem)

## 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": "bumblebiber-hmem"
    }
  }
}
```

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