AgentVectorDB (AVDB)
The Cognitive Core for Your AI Agents - Powered by LanceDB
A specialized memory management system developed by Superagentic AI. Built on top of LanceDB's powerful vector database capabilities, it provides optimized cognitive architecture for AI agents.
Installation
Overview
🧠 AgentVectorDB (AVDB)
AgentVectorDB (AVDB) is a specialized memory management system developed by Superagentic AI. 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
File-based, no server required
Efficient ANN search with filtering
High-performance async/await API
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
},
{
"content": "User Prefer Purple color scheme",
"type": "preference",
"importance_score": 0.6
},
# Add more memories...
]
# Add batch
memories.add_batch(initial_memories)
# Query memories
results = memories.query(
query_text="user preferences",
k=2
)API Overview
AgentVectorDBStore
store = AgentVectorDBStore(db_path="./db")Methods:
- get_or_create_collection()
- list_collections()
- delete_collection()
AsyncAgentVectorDBStore
store = AsyncAgentVectorDBStore(db_path="./db")Advanced Usage
from agentvectordb.embeddings import BaseEmbeddingFunction
class CustomEmbedder(BaseEmbeddingFunction):
def __init__(self, dimension=384):
super().__init__(dimension=dimension)
def embed(self, texts):
# Your embedding logic here
return vectors
Code
There is more code on the documentation page
Use Cases
Personal AI Assistants
Create AI assistants that remember user preferences and previous interactions
Customer Service Bots
Build customer service bots that can recall customer issues and preferences
Research Agents
Create research assistants that can store and recall research findings
Task Automation
Develop task automation agents that remember previous workflows and processes
Knowledge Systems
Build knowledge management systems with semantic search capabilities
Learning Systems
Create systems that learn from interactions and improve over time
Memory Types
Episodic Memories
Events and experiences that happened at specific times and places
Semantic Knowledge
General facts and conceptual knowledge not tied to specific experiences
Procedural Information
How to perform specific tasks or actions
Short-term Observations
Recent observations and information that may be temporary
Long-term Knowledge
Persistent information that remains relevant over time
Roadmap
Upcoming features planned for future releases:
Enhanced filter builders
Advanced query filtering mechanisms
Reflection/summarization helpers
Tools for memory consolidation and analysis
Schema evolution support
Dynamic schema updates without data loss
Memory consolidation
Automated memory organization and compression
Extended embedding support
Integration with more embedding models
Performance optimizations
Improved speed and efficiency for large datasets
FAQ
Start Building with AgentVectorDB Today
Empower your AI agents with advanced memory management capabilities.
Ready to Get Started?
Build cognitive systems for your AI agents with AgentVectorDB's powerful memory management capabilities.