meme

Long-term memory for AI agents.

A Rust implementation of the SimpleMem three-stage pipeline:

1. Semantic Structured Compression — dialogues → compact memory entries
2. Online Semantic Synthesis — deduplication during write
3. Intent-Aware Retrieval Planning — multi-view hybrid retrieval

Memory is persistent across sessions — the vector store is stored on disk.

Quick Start

use meme::{Meme, MemeBuilder};

# async fn example() -> meme::error::Result<()> {
let meme = MemeBuilder::new()
    .api_key("sk-...")
    .model("gpt-4.1-mini")
    .build()
    .await?;

meme.add_dialogue("Alice", "Let's meet at 2pm tomorrow", None).await?;
meme.finalize().await?;

let answer = meme.ask("When will Alice meet?").await?;
# Ok(())
# }