Open Source Elixir Data Management Systems

SortedSet NIF is a performant and reliable sorted set data structure for Elixir, implemented in Rust using the Rustler crate to take advantage of native performance while maintaining seamless integration with the BEAM ecosystem. It provides ordering and uniqueness guarantees, with all terms stored according to Elixir’s built-in sorting rules. Internally, it uses a vector of vectors layout rather than a single vector to minimize costly reallocations, allowing efficient bucket pointer copying instead of expensive term copying during growth. This design achieves a balance between performance and simplicity, and developers can customize bucket sizes for specific workloads, with a default of 500 offering solid performance across common scenarios. SortedSet extends beyond traditional set semantics by providing indexing, random access, and slice operations thanks to its deterministic ordering.

Explorer brings series (one-dimensional) and data frames (two-dimensional) to Elixir for fast data exploration.

TeslaMate is an open-source self-hosted data logger that collects and visualizes data from Tesla vehicles in real time. It provides detailed insights into driving, charging, efficiency, and battery health through intuitive dashboards powered by Grafana. TeslaMate is ideal for Tesla owners who want full control of their vehicle data, avoid cloud reliance, and access rich analytics for personal tracking or troubleshooting.

ExAws is a comprehensive Elixir client library for interfacing with AWS services. It provides low-level request builders for nearly all AWS APIs—like S3, EC2, Lambda, DynamoDB, SQS, SES, Route 53, and more—while supporting streaming, request configuration overrides, telemetry, flexible HTTP clients, and codecs. Its modular architecture enables importing only the services you need with separate packages (e.g., ex_aws_s3, ex_aws_ec2).

GenStage is a specification and set of behaviours for building demand-driven data pipelines on the BEAM. It formalizes the roles of producers, consumers, and producer-consumers, using back-pressure so that fast producers don’t overwhelm downstream stages. Developers implement callbacks like handle_demand and handle_events to control how items are emitted, transformed, and consumed across asynchronous boundaries. Because stages are OTP processes, you gain fault tolerance, supervised restarts, and concurrency tuned via configurable demand and partitioning. GenStage underpins higher-level libraries like Flow and Broadway, but it can also be used directly for custom pipelines where timing and throughput matter. Its clear separation of concerns encourages testable, composable stages that can be rearranged as requirements evolve. In production, this leads to predictable, resilient dataflows for event ingestion, batching, and parallel processing.