Computational Components

From ingest to Outcome.

SpaceCell processes live data and performs sub-millisecond computation within your existing environment. Its components are composable and built on open-source foundations, so teams can adopt only the parts they need.

SpaceCell

Engineered from Foundations.

SpaceCell is built from first principles to reduce dependency overhead and make better use of the underlying hardware. Its components are modular, so teams can adopt only what fits their existing stack. Because SpaceCell uses the Apache Arrow format, data remains portable across the wider ecosystem without creating lock-in. The core foundations are open source, auditable and designed for production use.

SpaceCell Lightning
Live analytics engine - 500+ statistical and data functions
Commercial
SpaceCell Liquid
Cross-Process Bridge Rust <-> Python < 30μs roundtrip. Full process isolation.
Commercial
open foundations
Lightstream
Arrow IPC transport - SIMD aligned + zero-copy from wire to operation
Open source
Minarrow
Arrow Data Foundations. Bridge Rust <-> Python in single digit μs. Single-process.
Open source
Components

What each layer does.

ComponentRoleLicence
Lightning A live analytics engine with more than 500 statistical and data functions for streaming and historical columnar data, using the same pipeline from backtesting to production feeds. Commercial Quant finance →
Liquid A process-isolated Python bridge for running models and inference inside Rust pipelines, with round-trip overhead of less than 30 μs and no need to rewrite Python research code. Commercial
Lightstream High-performance Arrow IPC streaming across multiple transports, with zero-copy paths from network buffers to SIMD-ready data structures. Open source
Minarrow A Rust-native, Apache Arrow-compatible columnar library with fully typed data structures, SIMD-ready buffers, direct in-process Rust–Python interoperability, a small dependency footprint, and a practical developer experience. Open source GitHub →
Engineered from Fundamentals

Why it's fast.

Performance comes from the full stack. SIMD-aligned buffers remain aligned across network, storage and memory boundaries. The columnar layout improves cache locality and reduces unnecessary data movement. Together, these choices deliver columnar throughput without giving up sub-millisecond latency.

[ diagram: SIMD alignment held wire → disk → memory → cache ]
Interoperable

Built to fit your stack.

Use individual components or the full platform. Lightning reads historical data from Parquet and Arrow IPC, consumes live data from your existing transport, and sends results back into the system tools you already operate.

Apache Arrow Parquet Kafka Aeron Python Rust
Who We Work With

For teams building live systems.

Lightning is an excellent fit for teams in quantitative finance, digital assets, payments, fraud detection and industrial monitoring.

We focus on latency-sensitive systems with a defined technical objective. Lightning is not intended for general data-warehouse modernisation, and we prioritise teams assessing it against a concrete workload.

Book a demo.

A confidential technical walkthrough. We respond within one business day.

Book a demo