Browse Kotlin Multiplatform libraries

Streaming-text typewriter for LLM apps: renders streaming tokens with live progressive Markdown, per-language syntax-highlighted code blocks, human-like speed curves, configurable cursor, tap-to-skip, and accessibility support.

AI chat composer UI with multi-line auto-growing input, slash-command autocomplete, @mention dropdown, attachment chips/previews, unified Send/Sending/Stop state, voice support, templates and live token counter.

Facilitates real-time calculation of AI model API usage costs, leveraging monetary representation and big decimal arithmetic for precise accounting of input and output token expenses.

On-device AI runtime enabling speech recognition, TTS, and local LLM inference with offline RAG, auto model downloads, streaming generation, and GPU acceleration for low-latency, privacy-preserving apps.

Unofficial library facilitates access to OpenAI API, offering statically defined request and response types. Supports multiple platforms with simple and complex usage examples for fetching and streaming data.

Facilitates seamless connection to multiple AI providers through a user-friendly API client. Includes customizable settings, asynchronous execution, and provider-specific configurations for enhanced flexibility.

High-performance LLM application layer offering runtimes and CLI tools for Llama, Gemma, Qwen and BERT models; safetensors model loading and hardware-accelerated inference.

AI-native layout engine generating declarative UI layouts from plain English, synthesizing layout algorithms at runtime, caching compiled frames for fast rendering, and fully AI-generated implementation.

Addresses dynamic text rendering and multilingual translation challenges by integrating AI models for real-time English-Arabic translation and text prediction on TextViews, ensuring accuracy and readability.

Offers machine learning primitives for building complex neural networks. Features activation functions, layers, optimizers, and training methods, serving as educational resources for optimization and visualization techniques.

Automatic differentiation library enabling compile-time optimization of mathematical expressions, featuring multi-module architecture, KSP-based code generation, and computational graph visualization through Graphviz.

Recommendation algorithm powering The Earth App, generating personalized content rankings and suggestions with production-grade performance and straightforward integration into app workflows.

Interactive Jupyter notebook integration enabling deep-learning experimentation with type-safe tensors, inline image/Graphviz rendering, autograd graph visualization, SIMD-accelerated and quantized kernels.

Component for scanning barcodes with camera preview, based on ML Kit and CameraView2, available for Android legacy version, featuring a single SKScanner component.

Offers a multiplatform SDK for integrating Google's Gemini through Vertex AI, enabling text generation on Android and iOS. Suitable for prototyping, not production-ready.

Multiplatform face recognition library leveraging InspireFace for efficient biometric processing, suitable for diverse mobile platforms and applications.

On-device federated learning: collaborative training keeping raw data local while exchanging model updates; includes core APIs, FedAvg implementation, and Transport/Coordinator architecture roadmap.

On-device speech-to-text: extracts clean 16kHz audio, downloads and runs local models, returns transcripts with timing, language and confidence — no server or audio upload.

Koog-compatible on-device LLM client enabling offline Gemini Nano and Apple Foundation Models inference without API keys, supports hybrid cloud fallback, model download, warm-up and routing.