Back to directory

ContextSDK for Swift

An on-device context and insights SDK for Swift apps that reads real-world signals on the device, without collecting personally identifiable information, to help an app respond to a user's real-world context.

ContextSDK for Swift

ContextSDK brings on-device, real-world context signals into an app, aimed at improving conversions, engagement and user experience while avoiding collection of personally identifiable information. This repository distributes the Swift build as a Swift Package with pre-built .xcframework binaries; other platforms such as Flutter and Android, and other installation methods such as CocoaPods, are covered by separate distributions described in the vendor's documentation.

It is added to a project as a Swift Package Manager dependency, either through Xcode's Add Package Dependencies flow or directly in a project's Package.swift file, pinned to a version.

Using ContextSDK in production requires signing up with the vendor to receive a license key.

More in Mobile

See all 90
  • Dart and Flutter bindings for the Zvec in-process vector engine, letting mobile and desktop apps run on-device semantic search, retrieval-augmented generation and similarity queries with no separate server.

  • Mobile Claw

    github.com

    A Capacitor plugin that embeds a native Rust AI agent engine directly on Android and iOS, running Claude with file tools, code execution, git and extensible MCP device tools, on-device vector memory and background scheduling, with no cloud relay.

  • A Swift package for streaming, on-device speech recognition on iOS, built on a custom Rust inference runtime (VoxRT) rather than ONNX Runtime or PyTorch Mobile, running a 32-million-parameter FastConformer model with roughly 90ms per-chunk latency on an iPhone 13 Pro Max.