No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by off-grid-ai · MCP Server · ★ 119
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is OGAD safe to install? View the security audit →
Off Grid AI Private, on-device AI. Your models, your data — no cloud, no accounts, no API keys. A local-first AI runtime + studio — run open models (text, vision, image, voice, speech) entirely on your machine, behind one OpenAI-compatible gateway. Plus an always-on layer that sees, remembers, reflects, and acts — all on-device. Download (macOS · Windows) · Features · getoffgridai.co · Get Pro <img alt="coverage functions 96%" src="https://img.shields.io/badge/functions-96%25-34D399" /
| Stars | 119 |
| Forks | 25 |
| Language | TypeScript |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 66.0840620421193/100 |
| Open Issues | 22 |
| Last Updated | 2026-10-04 |
| Created | 2026-01-19 |
| Platforms | mcp, node |
| Est. Tokens | ~17k |
These tools work well together with OGAD for enhanced workflows:
Looking for a OGAD alternative? If you're comparing OGAD with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Memory that learns what works.
Open-source iOS app connecting Meta Ray-Ban smart glasses to AI — 5 backends (on-device MLX models, Apple Inte
The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a s
Aser is a lightweight, self-assembling AI Agent frame.
On-device AI for Android — LLM chat (GGUF/llama.cpp), vision models (VLM), image generation (Stable Diffusion)
Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Pe
Explore other popular mcp server tools:
OGAD is Your private, on-device personal AI assistant for macOS and Windows. Chat, create, search files, and connect tools with local models. Includes an OpenAI-compatible API. Opt-in Pro sees, remembers, ref. It is categorized as a MCP Server with 119 GitHub stars.
OGAD is primarily written in TypeScript. It covers topics such as ai-assistant, ai-memory, ai-second-brain.
You can find installation instructions and usage details in the OGAD GitHub repository at github.com/off-grid-ai/OGAD. The project has 119 stars and 25 forks, indicating an active community.
OGAD is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to OGAD on Agent Skills Hub include roampal, OpenVision, lilbee. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: