Cerebro 🧠

A blazing-fast, storage-agnostic Memory Layer for AI Agents, written in pure Rust.

Cerebro functions as the Hippocampus for autonomous AI. It natively understands Agentic Memory structures (Working, Episodic, and Semantic memory) with pluggable storage backends.

With SwarmForge, it provides a built-in multi-agent orchestration engine — enabling teams of specialized AI agents to collaborate through its three-tier memory system.

Quick Start

[dependencies]
cerebro = "1.1.2"

Memory Engine + Hybrid Search

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

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

    engine.ingest_document(Document::new("Rust ensures memory safety.")).await.unwrap();

    let results = engine.query("memory safety", 1).await.unwrap();
    println!("Match: {}", results[0].0.chunk.text);
}

SwarmForge — Multi-Agent Orchestration

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

#[tokio::main]
async fn main() {
    // 1. Initialize Memory Bus
    let engine = Arc::new(MemoryEngine::new(
        Arc::new(RecursiveCharacterChunker::new(512, 50)),
        Arc::new(MockEmbedder::new(8)),
        Arc::new(MemoryVectorStore::new()),
    ));
    let memory = Arc::new(CerebroMemoryBus::new(engine, Arc::new(MemoryKVStore::new())));
    
    // 2. Run Swarm
    let mut swarm = SwarmOrchestrator::new(memory);

    swarm.register_agent(AgentConfig {
        id: "analyst".into(),
        name: "Security Analyst".into(),
        system_prompt: "Analyze code for vulnerabilities.".into(),
        model: LlmProvider::Ollama { model: "llama3".into(), base_url: "http://localhost:11434".into() },
        tools: vec![], handoff_targets: vec![], max_steps: 10,
    });

    let result = swarm.execute(
        SwarmPattern::Sequential { agent_order: vec!["analyst".into()] },
        "Review this code snippet",
    ).await.unwrap();
}

Features

• Three-tier memory: Working (KV), Episodic (Conversation), Semantic (Vector).
• SwarmForge: Sequential, parallel, and hierarchical multi-agent pipelines.
• Universal LLM: Support for Ollama, OpenAI, Gemini, Anthropic, and any OpenAI-compatible API (Groq, etc).
• Hybrid Search: Reciprocal Rank Fusion (RRF) combining keyword and vector retrieval.
• MCP Server: Native Model Context Protocol support (cerebro-mcp).

License

MIT