# AgentOS

> Use this tool when you need to create and manage autonomous agents with robust safety guarantees, enforcing policies such as PII protection and cost control. AgentOS provides a kernel-inspired architecture for deterministic policy enforcement, ensuring reliable safety guarantees for agent operations. It is ideal for use cases requiring strict control and oversight of autonomous agents, including those involving sensitive data or high-stakes decision-making.

Canonical page: https://skillsregistry.net/skills/agentos  
JSON: https://api.skillsregistry.net/v1/skills/agentos

## Description

Brings the AgentOS safety framework to Claude Desktop and other compatible clients. Provides tools to create, deploy, and manage autonomous agents with deterministic policy enforcement including PII protection, rate limiting, cost control, and human-in-the-loop approval workflows. Uses a kernel-inspired architecture where policies are enforced programmatically rather than through prompts, achieving reliable safety guarantees for agent operations.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-08-31

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentos)
- **Repository:** <https://github.com/imran-siddique/agent-os/tree/HEAD/extensions/mcp-server>

## 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": "agentos"
    }
  }
}
```

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