Browse Kotlin Multiplatform libraries

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.

Library enables interaction with multiple large language model providers via a unified interface. Features include consumer-friendly API, secured key management, HTTP client flexibility, streaming capabilities, and configurable retry policies.

Lightweight OpenAI API client offering idiomatic, async-friendly calls for completions, chat, streaming and file uploads, plus simple configuration and request/response mapping.

Generative AI integration for Firebase offering model creation, content DSL, multi-turn chat with streaming, safety filters, Vertex AI backend support, and token-estimation tools.

Firebase Vertex AI integration enabling agent-framework LLM prompts with preconfigured Gemini model definitions, streaming responses, and simple executor adapters for easy backend connection.

OpenAI-compatible SDK offering chat completions (streaming and non-streaming), text embeddings, model browsing across 40+ models, SSE streaming, thread-safe singleton, and API-key redaction.

Blazing-fast AST-based Markdown engine with incremental parsing, token-by-token LLM streaming, full CommonMark coverage, theming, LaTeX math, linting, plugin directives and image loading.

Run offline LLMs with llama.cpp backend: real‑time token streaming, SHA‑256‑verified resumable downloads, chat templates, KV‑cache reuse across turns, and grammar‑constrained generation.

Multifaceted AI tooling library delivering typed agent and tool contracts, streaming text and structured outputs, provider/gateway adapters, embeddings and media primitives, telemetry, mocks, and utilities.

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.

Unifies diverse LLM providers behind a single OpenAI-style API: streaming-first chat/embeddings/voice/realtime/batch modalities, per-model health-aware fallback chains, outbound control-plane auth and extensibility.