AI Factory Operations Agent Headless

Use AI Factory Operations Agent without opening the browser UI. Invoke it through the headless HTTP API, packaged CLI, or stdio MCP server, and deploy it first when no service is available.

43 stars 18 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add NVIDIA/AI-Factory-Operations-Agent --skill ai-factory-operations-agent-headless
Manual install
git clone --depth 1 https://github.com/NVIDIA/AI-Factory-Operations-Agent.git /tmp/AI-Factory-Operations-Agent
mkdir -p ~/.claude/skills
cp -r /tmp/AI-Factory-Operations-Agent/docs/skills/ai-factory-operations-agent-headless ~/.claude/skills/ai-factory-operations-agent-headless

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI Factory Operations Agent Headless Service

Use this skill when a coding agent needs AI Factory Operations Agent to answer an operational question or use its tools from another agent runtime.

## Check For An Existing Service

Load `MOSAIC_UI_MACHINE_TOKEN` using the [headless setup commands](../../installation.md#headless-mode).

If `MOSAIC_URL` is already set, use it. Otherwise try the local default:

```bash
curl -fsS "${MOSAIC_URL:-http://127.0.0.1:3000}/api/openclaw/commands" \
  --header @<(printf 'Authorization: Bearer %s\n' "$MOSAIC_UI_MACHINE_TOKEN") >/dev/null
```

For a Kubernetes deployment, port-forward the UI service and set `MOSAIC_URL`:

```bash
kubectl -n aifoa port-forward svc/mosaic-ui 3000:3000
export MOSAIC_URL=http://127.0.0.1:3000
```

Use the target namespace instead of `aifoa` if the operator installed the service elsewhere.

## Invoke By CLI

Inside the `mosaic-ui` image, or anywhere the packaged CLI has been installed:

```bash
mosaic --session headless "summarize whether the cluster is healthy"
```

Useful options:

- `--url URL`: service URL. Defaults to `MOSAIC_URL` or `http://127.0.0.1:3000`.
- `--session KEY`: conversation key. Defaults to `MOSAIC_SESSION` or `headless`.
- `--timeout-ms MS`: maximum wait for a final answer. Defaults to `120000`.
- `--json`: return the full JSON response.
- `--concise`: request compact output.

## Invoke By HTTP

Use the headless API when the CLI is not installed:
Read the full skill on GitHub

Details

Skill name
ai-factory-operations-agent-headless
Path
docs/skills/ai-factory-operations-agent-headless/SKILL.md
License
Apache-2.0
Repo updated
17 November 2026

FAQ

What does the AI Factory Operations Agent Headless skill do?

Use AI Factory Operations Agent without opening the browser UI. Invoke it through the headless HTTP API, packaged CLI, or stdio MCP server, and deploy it first when no service is available.

How do I install the AI Factory Operations Agent Headless skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add NVIDIA/AI-Factory-Operations-Agent --skill ai-factory-operations-agent-headless. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is AI Factory Operations Agent Headless popular?

It lives in NVIDIA/AI-Factory-Operations-Agent, which has 43 GitHub stars and 18 forks.

Related skills

Bcm

43

NVIDIA/AI-Factory-Operations-Agent

Inspect Base Command Manager (BCM) inventory and health evidence, and make explicitly requested changes when Base Command Manager edit mode is enabled.

Other18

GPU Networking

43

NVIDIA/AI-Factory-Operations-Agent

Measure and diagnose distributed GPU networking performance: NCCL collectives, RDMA transport, PCIe topology, link health, IOMMU and ACS. Use for current bandwidth/latency questions and follow-up bottleneck investigations or corrections.

Finance & Crypto18

Grafana

43

NVIDIA/AI-Factory-Operations-Agent

Create and open Grafana dashboards for metrics, Loki logs, and mixed panels. Use when the user asks for a dashboard, visualization, chart, panel, or graph of GPU, Base Command Manager (BCM), node, network, InfiniBand, Prometheus metrics, or Loki logs.

Data & Analytics18

Clawguard Auditor

49

SafeAgent-Beihang/clawguard

ClawGuard v3 Auditor - 企业级 Skill 安全审计器,支持意图偏离检测、SAST、供应链安全、ML 异常检测。当用户要求审计、检测、安装前检查一个 Skill 的安全性时触发。

AI, LLMs & Agents

Sending

113

Hmbown/Wizards-of-the-Ghosts

Use this spell when you need to dispatch a message — the agent determines the right channel, formats for that medium, and sends with the user's approval.

AI, LLMs & Agents11

Clawguard Shield

49

SafeAgent-Beihang/clawguard

ClawGuard Shield v3 - Active defense with prompt injection detection, intent validation, zero-width character detection, and intent integrity verification

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.