Introducing AgentVectorDB
The Cognitive Core for Your AI Agents
Powered by LanceDB
Today, we're proud to announce the launch of AgentVectorDB (AVDB), a powerful open-source memory architecture for AI agents, built for the Agentic era.
🌟 Overview
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 that need to remember, recall, and reason with information.
👋 Why We Built AgentVectorDB
As AI agents move from reactive tools to autonomous collaborators, memory becomes essential. Just like humans, agents need to store, recall, and prioritize what they know, not just retrieve information, but reason with it.
That's where AgentVectorDB comes in.
AVDB is a specialized memory management system for agents, one that allows your systems to remember interactions, weigh importance, and query semantically to make better decisions. It's built by Superagentic AI on top of LanceDB, adding a cognitive layer tailor-made for AI agents.
🤝 Built with LanceDB
We extend LanceDB's robust foundation with agent-specific features:
Agent Memory Patterns
Support for episodic, procedural, and semantic memory.
Importance Scoring
Prioritize memories like a human brain.
Context Management
Efficient recall of relevant past events and actions.
Cognitive State Handling
Maintain and update agent mental states over time.
✨ 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
⏱️ 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]"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": "Memory usage peaked at 85%",
"type": "system_metric",
"metadata": {"metric": "memory"}
},
# Add more memories...
]
# Add batch
memories.add_batch(initial_memories)
# Query memories
results = memories.query(
query_text="user preferences",
k=2
)📢 What We Need From You
If you believe in building smarter, memory-aware agents, we'd love your help:
Star the GitHub repo
Help us reach more developers
Try it in your next project
Build something amazing with AVDB
Share feedback via issues or PRs
Help us improve and evolve
Spread the word
Tag us @SuperagenticAI
AgentVectorDB is just the beginning of Superagentic's cognitive infrastructure for the Agentic Era. Let's build a future where agents aren't just tools, they're intelligent partners.