🧠 AgentVectorDB (AVDB)

(opens in a new tab)

The Cognitive Core for Your AI Agents - Powered by LanceDB

🌟 Overview

AgentVectorDB (AVDB) is a specialized memory management system developed by Superagentic AI (opens in a new tab). Built on top of LanceDB's powerful vector database capabilities, it provides optimized cognitive architecture for AI agents.

🤝 Built with LanceDB

We extend LanceDB's robust foundation with agent-specific features:

• Agent memory patterns
• Importance scoring
• Context management
• Cognitive state handling

✨ Key Features

Core Capabilities

• 📝 Persistent Storage: File-based, no server required
• 🔍 Semantic Search: Efficient ANN search with filtering
• ⚡ Async Support: High-performance async/await API
• 🎯 Agent-Optimized: Purpose-built for AI systems

Advanced Features

• 🔄 Memory Lifecycle: Complete CRUD operations
• 📊 Batch Processing: Efficient bulk operations
• 🧹 Smart Pruning: Intelligent memory management
• 🔧 Flexible Schema: Dynamic Pydantic schemas
• ⏱️ Time Tracking: Automatic timestamps

📦 Installation

# Basic installation
pip install agentvectordb
 
# With all extras (recommended)
pip install "agentvectordb[all]"
 
# Development installation
git clone https://github.com/superagenticai/agentvectordb.git
cd agentvectordb
pip install -e ".[dev]"

🚀 Quick Start

from agentvectordb import AgentVectorDBStore
from agentvectordb.embeddings import DefaultTextEmbeddingFunction
 
# Initialize store
store = AgentVectorDBStore(db_path="./agent_db")
ef = DefaultTextEmbeddingFunction(dimension=384)
 
# Create collection
memories = store.get_or_create_collection(
    name="agent_memories",
    embedding_function=ef
)
 
# Add memories (minimum 8 recommended)
initial_memories = [
    {
        "content": "User prefers dark mode",
        "type": "preference",
        "importance_score": 0.8
    },
    # Add more memories...
]
 
# Add batch
memories.add_batch(initial_memories)
 
# Query memories
results = memories.query(
    query_text="user preferences",
    k=2
)

🧠 Cognitive Architecture

Our cognitive architecture is designed to mirror human memory systems, providing both short-term and long-term memory capabilities with intelligent retrieval mechanisms.

• Long-term memory storage
• Short-term context management
• Importance-based retrieval
• Semantic search capabilities

This architecture ensures that your AI agents can remember and prioritize information like a human, vastly improving their interaction quality and decision-making processes.

🔧 Technical Excellence

AgentVectorDB is built with a focus on technical superiority, offering a range of features that ensure flexibility, performance, and ease of use.

• Async/sync API support
• Custom schema definitions
• Advanced filtering options
• Batch operations support

These technical features provide developers with the tools needed to implement complex memory management scenarios with ease, whether in synchronous or asynchronous environments.

📊 Performance Metrics

We understand that performance is key to user satisfaction and operational efficiency. AgentVectorDB is engineered to deliver outstanding performance metrics.

• Sub-millisecond query times
• Efficient vector indexing
• Minimal memory footprint
• Optimized storage format

Such performance ensures that your applications remain responsive and efficient, even as they scale.

🎯 Start Building Now

🛠️ Use Cases

AgentVectorDB powers a wide range of applications across different industries. From personal AI assistants to enterprise-scale systems, our solution adapts to various use cases while maintaining optimal performance.

🤖 AI Agents

• Personal AI assistants
• Customer service bots
• Research agents
• Task automation agents

AgentVectorDB provides the necessary memory management capabilities that allow AI agents to perform complex tasks, learn from interactions, and provide personalized experiences.

💼 Enterprise Applications

• Knowledge management systems
• Customer experience platforms
• Decision support systems
• Process automation

In enterprise settings, AgentVectorDB excels by managing vast amounts of contextual data, thus enhancing knowledge workers' productivity and decision-making quality.

🔬 Research & Development

• AI research projects
• Cognitive architecture development
• Agent behavior studies
• Performance benchmarking

Researchers benefit from AgentVectorDB's ability to handle experimental data and agent simulations, providing insights into AI behavior and system performance.

Join our community to connect with other users, share your experiences, and get support from the AgentVectorDB team.

📄 License & Attribution

AgentVectorDB shares the same Apache 2.0 License as LanceDB, maintaining full compatibility and open-source principles. We're proud to build upon and extend LanceDB's capabilities for agent-specific use cases.

🚀 Start Building Your AI Agents Now