Local AI Plugin

elizaos plugins add @elizaos/plugin-local-ai

// Automatically loads when these are not set:
// - GOOGLE_GENERATIVE_AI_API_KEY
// - OLLAMA_API_ENDPOINT  
// - OPENAI_API_KEY

# Optional configuration
LOCAL_AI_MODEL_PATH=/path/to/models
LOCAL_AI_THREADS=4
LOCAL_AI_CONTEXT_SIZE=4096

{
  "name": "MyAgent",
  "plugins": ["@elizaos/plugin-local-ai"]
}

// Models are cached in:
// ~/.eliza/models/

# Use more threads
LOCAL_AI_THREADS=8

# Enable AVX2 (if supported)
LOCAL_AI_USE_AVX2=true

# Limit context size
LOCAL_AI_CONTEXT_SIZE=2048

# Use quantized models
LOCAL_AI_QUANTIZATION=q4_0

{
  "plugins": ["@elizaos/plugin-local-ai"],
  "settings": {
    "local_ai": {
      "model_size": "small",
      "fast_mode": true
    }
  }
}

{
  "plugins": ["@elizaos/plugin-local-ai"],
  "settings": {
    "local_ai": {
      "model_size": "large",
      "disable_telemetry": true
    }
  }
}

{
  "plugins": ["@elizaos/plugin-local-ai"],
  "settings": {
    "local_ai": {
      "preload_models": true,
      "cache_responses": true
    }
  }
}

# Clear model cache
rm -rf ~/.eliza/models/

# Download models manually
eliza download-models