homie-ai 0.2.0

Fully local, privacy-first personal AI assistant with background intelligence

H O M I E  A I

Your Local AI Companion
_{Fully local. Privacy-first. No cloud. No tracking. Just you and your homie.}

Website · Download · About · Privacy

---

▸ QUEST LOG

# 01 — Install
pip install homie-ai

# 02 — Setup (detects hardware, downloads a model)
homie init

# 03 — Say hey
homie chat

That's it. No accounts. No API keys. No cloud.

---

▸ EQUIPPED ABILITIES

Ability	Level	Description
VOICE	LVL MAX	Talk to your AI. It talks back. Wake word, push-to-talk, or full conversation.
MEMORY	LVL MAX	Learns your habits, remembers your context. Working, episodic & semantic memory.
PRIVACY	LVL MAX	AES-256 vault. Zero telemetry. Your data never leaves your machine. Ever.
PLUGINS	12 SLOTS	Browser, clipboard, IDE, git, terminal, health, music, notes — and more.
BEHAVIORAL AI	LVL MAX	Habit detection, routine observation, profile synthesis.
LOCAL INFERENCE	LVL MAX	GGUF models via llama.cpp with full GPU acceleration (CUDA/Metal).

---

▸ CHARACTER STATS

┌─────────────────────────────────────────────────┐
│  100% LOCAL    0 CLOUD CALLS    20+ MODULES     │
│                                                 │
│  ∞ PRIVACY     AES-256 VAULT    MPL-2.0 OPEN   │
└─────────────────────────────────────────────────┘

---

▸ SYSTEM COMMANDS

homie start            Start the assistant (alias for chat)
homie chat             Interactive chat mode
homie init             First-time setup wizard
homie model list       List installed models
homie model add        Register a local model file
homie model switch     Switch the active model
homie plugin list      List available plugins
homie plugin enable    Enable a plugin
homie backup --to      Create encrypted backup
homie restore --from   Restore from backup

---

▸ MODEL SETUP

Homie uses llama.cpp for local inference. Download the server binary from the releases page and place it in ~/.homie/llama-server/.

Models are auto-discovered in common locations (~/.lmstudio/models/, ~/.homie/models/), or register manually:

homie model add /path/to/model.gguf --name my-model --format gguf --params 35B
homie model switch my-model

---

▸ CONFIGURATION

# homie.config.yaml — in working directory or ~/.homie/

llm:
  backend: gguf
  model_path: /path/to/your/model.gguf
  context_length: 65536
  gpu_layers: -1       # -1 = offload all layers to GPU
  max_tokens: 2048
  temperature: 0.7

voice:
  enabled: false
  wake_word: "hey homie"
  mode: push_to_talk

storage:
  path: ~/.homie

Environment overrides: HOMIE_LLM_BACKEND, HOMIE_LLM_MODEL_PATH, HOMIE_LLM_GPU_LAYERS, HOMIE_VOICE_ENABLED, HOMIE_STORAGE_PATH, HOMIE_USER_NAME

---

▸ OPTIONAL MODULES

pip install homie-ai[model]      # HuggingFace model downloading
pip install homie-ai[voice]      # Voice pipeline (STT, TTS, wake word)    ~2 GB
pip install homie-ai[context]    # System context tracking
pip install homie-ai[storage]    # Vector DB and encrypted backups
pip install homie-ai[app]        # Dashboard, system tray, scheduling
pip install homie-ai[all]        # FULL SUIT

---

▸ MINIMUM SPECS

	Requirement
CPU	Any modern x86/ARM
RAM	8 GB minimum
GPU	Optional — CUDA/Metal (+10x speed)
DISK	2 GB + model size
PYTHON	3.11+
INTERNET	Only for install, then fully offline

---

▸ TECH INVENTORY

Component	Role
Python	Core
llama.cpp	Engine
SQLite	Storage
ChromaDB	Vectors
Whisper	Voice
AES-256-GCM	Vault

---

▸ LICENSE

Mozilla Public License 2.0

---

_{Built by MSG · heyhomie.app}