Crate elizaos_plugin_local_ai 

elizaOS Local AI Plugin - Rust Implementation

Provides local LLM inference using GGUF models via llama.cpp bindings.

Features

• llm - Enable actual inference with llama_cpp_rs
• cuda - Enable CUDA GPU acceleration
• metal - Enable Metal GPU acceleration (macOS)

Example

use elizaos_plugin_local_ai::{LocalAIPlugin, LocalAIConfig, TextGenerationParams};

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let plugin = LocalAIPlugin::from_env()?;
    let response = plugin.generate_text("Hello, world!").await?;
    println!("{}", response);
    Ok(())
}

Re-exports

pub use error::LocalAIError;

pub use error::Result;

pub use types::*;

Modules

error

types

xml_parser

Structs

LocalAIConfig

Configuration for the Local AI plugin.

LocalAIPlugin

The main Local AI plugin struct.