# mosaic

> mosaic — hexxla-mosaic. Use this tool when you need to manage and retrieve agent memory data, leveraging features like ring retrieval, embeddings, and lexical search. It solves problems related to data storage and querying, providing a robust interface for inputs and outputs through localhost HTTP transport and YAML persistence policy. Ideal for use cases requiring efficient data management and retrieval, such as agent training and development.

Canonical page: https://skillsregistry.net/skills/hexxla-mosaic  
JSON: https://api.skillsregistry.net/v1/skills/hexxla-mosaic

## Description

MCP server for agent memory over HexxlaDB—ring retrieval, embeddings + lexical search, seams, facets, YAML persistence policy, localhost HTTP transport.

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/hexxla/mosaic)

## 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": "hexxla-mosaic"
    }
  }
}
```

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