Features
Portable deployment: edge, on-prem, hybrid, cloud
Sub-15ms local vector search with ANN indexing
99% recall at 10M vectors
Offline operation with sync-on-connect
CRUD operations for vector embeddings
Metadata filtering on vector search
Deploy on Raspberry Pi, NVIDIA Jetson
HIPAA/GDPR-compliant on-premises deployment
Consistent architecture from prototype to production
Integration with Actian Data Intelligence Platform
MCP (Model Context Protocol) server support
Python, JavaScript, Go client libraries
No environment-specific rewrites
Supports disconnected and air-gapped deployments
Distributed tracing for LLM agents
Capture prompts, retrievals, tool calls, outputs
Human annotations on traces
Create datasets from traces
Run experiments to compare changes
OpenTelemetry-native instrumentation
Self-host locally, Docker, or Kubernetes
Cloud instances with free tier
Vendor agnostic: any model or framework
3M+ monthly downloads, 9k+ GitHub stars
