The decentralized vector database delivering relevant results at any scale. Powered by a global network of miners — not a single cloud provider.
Trusted in production
from rem_sdk import REMClient
# Connect to the decentralized network
client = REMClient(api_key="rem_xxx")
# Create a collection — auto-distributed across miners
client.create_collection("products", dimension=384, metric="cosine")
# Upsert vectors with metadata
client.upsert("products", vectors=[
{"id": "p1", "values": [0.1, 0.2, ...], "metadata": {"category": "electronics"}},
])
# Query — routed to nearest miner for lowest latency
results = client.query("products", vector=[0.1, ...], top_k=10)Purpose-built for AI workloads. Decentralized by design.
Queries routed to the nearest miner. Distributed caching ensures consistent low-latency responses globally.
2,000+ miners across the globe. No single point of failure. Your data is always available, always redundant.
End-to-end encryption. Multi-replica storage. Hashed API keys. Your data never touches a centralized server.
From 1,000 to 1,000,000,000 vectors. The network grows with you — more miners, more capacity, same latency.
€20 free credit on signup. Pay-as-you-go pricing that's a fraction of centralized alternatives.
SOC 2 compliant. GDPR ready. SLA guarantees. Dedicated support for business-critical workloads.
Three steps. No infrastructure to manage. No servers to provision.
Define your vector dimension and distance metric. Your collection is automatically distributed across miners for redundancy.
Upload embeddings with metadata using our SDK or REST API. Data is replicated across multiple miners in real-time.
Search for similar vectors with sub-100ms latency. Queries are routed to the optimal miner automatically.
Start free. Scale without surprises.
€20 free credit included
For growing applications
For production workloads
€20 free credit. No credit card required. Deploy your first vector collection in under 60 seconds.