Lazzaro

Scalable Memory System Library for AI Agents

Lazzaro is a high-performance Python library for long-term, structured agent memory. It goes beyond simple vector search by implementing a graph-based architecture with semantic sharding, hierarchical clustering, and biological-inspired decay. It evolves a multi-domain user profile through continuous conversation consolidation.

Installation

pip install lazzaro

• Extensions: google-generativeai, together (LLMs), langchain-core (Integrations), matplotlib (Visualization).

Core Architecture

Lazzaro organizes memory as a multi-layered graph optimized for scale:

• Semantic Shards: Topic-based subgraphs (e.g., "coding", "health") that provide natural isolation and accelerated retrieval.
• LanceDB Backed: Persistent storage of the entire graph (nodes, edges, profile) with sub-millisecond vector performance.
• Hierarchical super-nodes: Summary nodes representing large clusters, allowing for abstract reasoning and fast top-down search.
• Multi-User Factory: Native multi-tenant support with B-Tree optimized user partitioning.

Memory Lifecycle

1. Episodic Buffer: Immediate caching of conversations for short-term context.
2. Background Consolidation: Asynchronous LLM extraction of atomic facts, deduplication via LanceDB, and associative graph linking.
3. Temporal Decay & Pruning: Biological-inspired pruning where weak associations fade and salience decays non-linearly to prevent memory bloat.

User Profile & Retrieval

Lazzaro evolves a structured persona across five domains (Preferences, Personality, Knowledge, Style, and Experiences). Retrieval uses a hybrid approach:

• Sharded Semantic Search: Narrowing the search space to relevant subgraphs.
• Associative Boosting: High-salience nodes pull their neighbors into the current context buffer.
• Optimized Retrieval: Combines vector similarity with hierarchical pathing and frequency metrics.

Usage

Provider Configuration

from lazzaro.core.memory_system import MemorySystem
from lazzaro.core.providers import GeminiLLM, GeminiEmbedder

# Initialize providers
llm = GeminiLLM(api_key="API_KEY", model="gemini-1.5-flash")
embedder = GeminiEmbedder(api_key="API_KEY")

# Initialize Memory System
ms = MemorySystem(
    llm_provider=llm, 
    embedding_provider=embedder,
    enable_sharding=True,
    enable_hierarchy=True,
    max_buffer_size=100
)

# Chat with built-in memory retrieval
ms.start_conversation()
response = ms.chat("I'm working on a Rust project and I prefer using async-std.")
print(response)

# Finalize and trigger background consolidation
print(ms.end_conversation())

Visual Dashboard

For a high-fidelity, interactive experience, Lazzaro includes a custom web-based dashboard:

lazzaro-dashboard

The dashboard will be available at http://localhost:5299 and features:

• Live Force-Graph: Interactive visualization of your memory shards and node relationships.
• Real-time Metrics: Monitor LLM calls, embedding costs, and retrieval latency.
• Profile Explorer: View your evolved user persona domains in a sleek side drawer.

Integrations

LangChain

from lazzaro.integrations import LazzaroLangChainMemory
from langchain.chains import ConversationChain

memory = LazzaroLangChainMemory(memory_system=ms)
chain = ConversationChain(llm=chat_model, memory=memory)

LangGraph

from lazzaro.integrations import LazzaroLangGraph

lg = LazzaroLangGraph(ms)
builder.add_node("retrieve", lg.get_memory_node())
builder.add_node("record", lg.get_record_node())

CLI Reference

Launch the interactive shell:

lazzaro-cli

Command Table

Parameter Reference

Persistence and Safety

• LanceDB Native Persistence: Lazzaro maintains its entire state (Graph + Vector + Profile) within LanceDB tables inside the db/ directory.
• Atomic Updates: Database operations are atomic, preventing state corruption during unexpected shutdowns.
• Version Control: LanceDB's internal versioning allows for reliable multi-process access and synchronization.
• JSON Export: Human-readable snapshots can be exported using the /save command or save_state() method for easy debugging and porting.

Development

Run tests:

pytest tests/

License

This project is licensed under the MIT License.