cerebro-0.1.0 has been yanked.

Cerebro 🧠

Cerebro is a blazing-fast, universal, and storage-agnostic "Memory Layer" for AI Agents and LLM Applications, written in pure Rust.

Why Cerebro?

While typical vector database wrappers just push raw vectors into a database, Cerebro functions as the Hippocampus for autonomous AI. It natively understands Agentic Memory structures:

Short-Term Episodic Memory (Conversations)
Working Memory (KV State)
Long-Term Semantic Memory (Vector Search with Temporal Decay)

It bridges the gap between raw document parsing and multi-agent frameworks (like LangChain, Auto-GPT, Cursor).

Key Features

🚀 Zero-Cost Abstractions: Powered by Rust, designed for massive async parsing and embedding workloads.
🔌 Universal Storage: Trait-based backends — swap between MemoryVectorStore, PgVectorStore, or Qdrant.
🧠 Pluggable Compute: Route embeddings through local models (Candle) or remote APIs (OpenAI, Anthropic).
🔄 Active Consolidation: Background "Sleep Cycle" worker for autonomous memory pruning and semantic organization.
🔍 Hybrid Search: Native RRF (Reciprocal Rank Fusion) combining keyword and vector retrieval for highest precision.
🌐 MCP Ready: Native Model Context Protocol server (cerebro-mcp) for AI desktop apps.
🦀 Multi-Language: Native Python (PyO3) and WASM bindings.
📄 Complex Ingestion: PDF extraction and HTML-aware semantic chunking.

Getting Started

[dependencies]
cerebro = "0.1.0"

Basic Example

use cerebro::prelude::*;
use std::sync::Arc;

#[tokio::main]
async fn main() {
    let chunker = Arc::new(RecursiveCharacterChunker::new(512, 50));
    let embedder = Arc::new(MockEmbedder::new(1536));
    let store = Arc::new(MemoryVectorStore::new());

    let engine = MemoryEngine::new(chunker, embedder, store);

    let doc = Document::new("The Rust programming language ensures memory safety.");
    engine.ingest_document(doc).await.unwrap();

    let memories = engine.query("What language is safe?", 5).await.unwrap();
    
    for (node, score) in memories {
        println!("Match: {} (Score: {})", node.chunk.text, score);
    }
}

Contributing

See ARCHITECTURE.md for how the library is structured and USER_GUIDE.md for in-depth examples.