AlgoX2 is a streaming operating system that unifies data ingestion, ordering, fan‑out, transformation, and durable storage into a single fault‑tolerant engine. It offers a partition‑free API with deterministic global ordering, native multicast fan‑out, and multi‑protocol support (Kafka, NATS, MQTT, Redis, HTTP, WebSocket), delivering sub‑10 µs latency and up to 100 M messages per second per node while materializing streams to lakehouse tables for real‑time analytics.
Funding
$3.5M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Enterprises that require ultra‑low‑latency, high‑throughput data streaming—such as financial exchanges, trading platforms, and AI‑driven real‑time applications—face fragmented infrastructure, costly scaling, and risk of data loss when using traditional stacks composed of separate message brokers, processing engines, and storage systems.
Solution
AlgoX2 provides a unified streaming operating system that consolidates ingestion, ordering, fan‑out, transformation, and durable storage into a single fault‑tolerant engine. By eliminating Kafka‑style partitions and offering a partition‑free API, producers publish to a single logical stream while the platform ensures deterministic global ordering and replication. Native multicast fan‑out delivers one write to thousands of consumers without duplicate network or CPU work, achieving sub‑10 µs latency and up to 100 M messages per second per node. Integrated compute‑storage separation lets CPU, network, and NVMe/object storage scale independently, while built‑in support for multiple protocols (Kafka, NATS, MQTT, Redis, HTTP, WebSocket) removes the need for external connectors. The system also materializes streams as Iceberg, Delta, or Hudi tables in S3‑compatible storage, enabling real‑time analytics without separate ETL pipelines.
Target Audience
Primary customers are high‑frequency trading firms, exchange operators, market‑data distributors, and AI‑focused enterprises that need deterministic, sub‑microsecond streaming at massive scale, as well as cloud and on‑premise infrastructure teams seeking to replace complex Kafka‑based pipelines.
Features
- Partition‑free API with internal ordering, supporting 100K+ logical streams without rebalancing overhead
- Native multicast fan‑out that serves thousands of consumers from a single write, reducing bandwidth and CPU costs
- Compute‑storage separation with policy‑driven tiering across NVMe and object storage for independent scaling
- EXEC framework allowing arbitrary code (Python, Rust, C++, Go) to run inside the stream for ultra‑low‑latency transforms
- Multi‑protocol bridging (Kafka, NATS, MQTT, Redis, HTTP, WebSocket) with no external connectors or schema registries
- Automatic lakehouse materialization to Iceberg, Delta, or Hudi tables in Parquet format for instant analytical queries
- Zero‑data‑loss architecture with three‑copy append‑only log and transactional semantics
- Enterprise‑grade security including fine‑grained ACLs, TLS/mTLS, quotas, and audit logging