Flagged: curl | sh installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by hoornet · Agent Tool · ★ 96
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is home-mind safe to install? View the security audit →
Home Mind []() []() AI assistant for Home Assistant with cognitive memory. Adds learning capabilities, persistent memory, and voice control to your smart home. The Problem Current Home Assistant AI integrations suffer from: No persistent memory - Forgets corrections and preferences between sessions No learning capability - Can't remember sensor baselines or user preferences Stateless interactions - Every conversation starts from zero The Solution Home Mind provides: Cognitive memory with semantic search and natural decay (via Shodh Memory) Learning from corrections and user preferences Voice control via HA Assist (Wyoming protocol) Multi-LLM support — Anthropic (Claude), OpenAI, or Ollama (local inference) Home Layout Index — reads your HA floor/room assignments and injects them into every prompt, so the AI always knows which floor a device is on Device Capability Index — pre-scans your lights at startup so the AI always uses the right color params on the first try Self-hosted and privacy-focused Memory in Action Unlike stateless AI assistants, Home Mind learns and remembers across conversations: First Conversation: User: Wha
| Stars | 96 |
| Forks | 6 |
| Language | TypeScript |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 70.1241808234747/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-09 |
| Created | 2026-01-12 |
| Platforms | node |
| Est. Tokens | ~17k |
These tools work well together with home-mind for enhanced workflows:
Looking for a home-mind alternative? If you're comparing home-mind with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Independent Claude Skills for the whole smart home: Home Assistant, ESPHome, Node-RED, custom integrations, da
Control and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Home Assistant add-on: Claude Code, OpenAI/GPT, Gemini
An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c
This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
Explore other popular agent tool tools:
home-mind is OSS AI memory layer for Home Assistant (AGPL). The conversation server inside the Nives addon was forked from this project — they're independent now.. It is categorized as a Agent Tool with 96 GitHub stars.
home-mind is primarily written in TypeScript. It covers topics such as ai-assistant, anthropic, cognitive-memory.
You can find installation instructions and usage details in the home-mind GitHub repository at github.com/hoornet/home-mind. The project has 96 stars and 6 forks, indicating an active community.
home-mind is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to home-mind on Agent Skills Hub include aurora-smart-home, hass-mcp, ha-claude. 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: