# caura

> caura — caura-ai-caura. Use this tool when you need to manage and govern shared memory for fleets of AI agents, enabling secure and efficient collaboration across multiple agents and tenants. Caura solves problems related to data sharing, access control, and knowledge retrieval in multi-agent systems, providing features like trust tiers and audit trails. It accepts knowledge graph inputs and outputs retrieval results, ideal for use cases requiring self-improving information management and secure data exchange.

Canonical page: https://skillsregistry.net/skills/caura-ai-caura  
JSON: https://api.skillsregistry.net/v1/skills/caura-ai-caura

## Description

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

## Trust

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

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/caura-ai/caura)

## 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": "caura-ai-caura"
    }
  }
}
```

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