2,000+ miners online

Performance at scale for
semantic search

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

2,000+
Active miners
50M+
Vectors stored
<100ms
p95 latency
99.9%
Uptime
quickstart.py
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)

Why teams choose REM

Purpose-built for AI workloads. Decentralized by design.

Sub-100ms Latency

Queries routed to the nearest miner. Distributed caching ensures consistent low-latency responses globally.

Decentralized Network

2,000+ miners across the globe. No single point of failure. Your data is always available, always redundant.

Secure by Default

End-to-end encryption. Multi-replica storage. Hashed API keys. Your data never touches a centralized server.

Scale to Billions

From 1,000 to 1,000,000,000 vectors. The network grows with you — more miners, more capacity, same latency.

10x More Affordable

€20 free credit on signup. Pay-as-you-go pricing that's a fraction of centralized alternatives.

Enterprise Ready

SOC 2 compliant. GDPR ready. SLA guarantees. Dedicated support for business-critical workloads.

From zero to production in minutes

Three steps. No infrastructure to manage. No servers to provision.

STEP 01

Create a Collection

Define your vector dimension and distance metric. Your collection is automatically distributed across miners for redundancy.

STEP 02

Upsert Vectors

Upload embeddings with metadata using our SDK or REST API. Data is replicated across multiple miners in real-time.

STEP 03

Query at Scale

Search for similar vectors with sub-100ms latency. Queries are routed to the optimal miner automatically.

Simple, transparent pricing

Start free. Scale without surprises.

Free

€0/month

€20 free credit included

  • €20 free credit on signup
  • Pay-as-you-go after credit
  • Unlimited collections
  • 60 requests/min
  • Community support
Get Started

Business

€99.99/month

For production workloads

  • 10M vectors included
  • 100M queries included
  • 6,000 requests/min
  • Dedicated support
  • 99.99% uptime SLA
Upgrade to Business

Start building with REM

€20 free credit. No credit card required. Deploy your first vector collection in under 60 seconds.