# open-compute

> open-compute — ellmos-ai-open-compute. Use this tool when you need to standardize interactions between AI agents and compute resources, solving integration problems across different models and backends. It provides a normalized interface for agents like Claude and OpenAI CUA, with a central safety gate for secure and controlled interactions. This core functionality enables seamless communication and action execution, making it ideal for use cases requiring model-agnostic compute resource management.

Canonical page: https://skillsregistry.net/skills/ellmos-ai-open-compute  
JSON: https://api.skillsregistry.net/v1/skills/ellmos-ai-open-compute

## Description

Model-agnostic computer-use core: one agent loop for Claude, OpenAI CUA, and a mock backend — normalized coordinates, canonical action schema, central safety gate.

## Trust

- **Trust score (0–1):** 0.72
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## 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/ellmos-ai/open-compute)

## 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": "ellmos-ai-open-compute"
    }
  }
}
```

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