# fleet-memory

> fleet-memory — holetron-lab-fleet-memory. Use this tool when you need to enable efficient shared memory for a team of AI agents, solving scalability and cost problems by providing a self-hosted, hierarchical storage solution with fast read paths. It accepts inputs from AI agents and outputs shared memory access, with a simple interface for storing and retrieving data. Ideal for use cases where multiple AI models require access to common data, reducing the need for redundant private stores.

Canonical page: https://skillsregistry.net/skills/holetron-lab-fleet-memory  
JSON: https://api.skillsregistry.net/v1/skills/holetron-lab-fleet-memory

## Description

RCLL — self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. We publish the measured cost of one shared store versus ten private ones. Fork of vectorize-io/hindsight (MIT).

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/Holetron-lab/fleet-memory)

## 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": "holetron-lab-fleet-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/holetron-lab-fleet-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/holetron-lab-fleet-memory/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