Browse Kotlin Multiplatform libraries

On-device AI toolkit enabling LLM chat, streaming, speech-to-text, text-to-speech and full voice-assistant pipelines—offline, private, model download/progress, lightweight neural voices and GGUF model support.

Fast, lightweight inference framework for energy-efficient on-device AI: numerical computation graph API, OpenAI-compatible inference engine, INT8 optimizations and model/tooling for compact, low-power deployments.

Framework designed for building AI agents with tool interaction, complex workflows, semantic search, and persistent memory. Offers modular architecture, real-time processing, and comprehensive tracing.

Visual workflow automation running entirely locally with drag-and-drop builder, fully typed data lineage, ultra-fast native execution, AI-native orchestration, white-label embedding, and comprehensive audit trails.

Integrates modern AI capabilities, including large language models and image generation, into applications. Offers core libraries for essential AI services and complementary library integrations, inspired by LangChain and Hugging Face projects.

On-device and remote LLM inference via native llama.cpp bindings, offering embeddings, context-aware text generation (streaming & non-streaming), lightweight HTTP client/server and GGUF model support.

Code-first toolkit for building, evaluating, and deploying sophisticated AI agents; offers rich tool ecosystem, modular multi-agent orchestration, built-in development UI and cloud integrations.

Tracing, monitoring and evaluating AI features via a unified API that captures structured traces, follows OpenTelemetry Generative AI semantics, auto-instruments popular AI clients, and exports to observability backends.

Compiler-driven framework builds clients and servers using the Model Context Protocol, implementing JSON-RPC handlers, schema metadata, and lifecycle management. Features resource exposure, parameterized prompts, and transport logging.

Generates JSON Schema for serializable classes, enabling seamless integration with AI agents and large language models. Supports automatic instantiation from JSON input, facilitating complex data structure development.

Mock HTTP and LLM servers facilitate building, testing, and mocking API responses, offering features like response streaming, Server-Side Events, and support for simulating delays and OpenAI API integration.

Observability-first multi-agent framework emitting structured, queryable events for each cognitive phase, enabling real-time reactive coordination, auditable reasoning, memory-as-events, and human escalation on low confidence.

Turns natural-language prompts into full Material 3 themes at runtime — generating colors, typography, and shapes from LLM seeds, expanding via HCT, with per-key caching and presets.

Facilitates development of applications powered by large language models, offering interfaces for chat API providers, respondents, and chat models, with streaming capabilities and context-building tools.

Empowers developers to create and manage AI agents with a streamlined DSL, offering error handling, logging, and integration with the ecosystem to transition from PoC to production.

Run LLMs locally with model downloading, GGUF export, SDKs and a CLI for testing; optimized on-device inference enabling private, serverless chat and model management.

Single-block agent runtime orchestrating LLM conversation, native device tools and phases; streams tokens to Compose UI, enforces guardrails with confirmations, audit logging, circuit breakers and shared state.

Adapts Model Context Protocol to enable automatic MDC-compatible JSON Schema generation from serializable classes, overcoming limitations in expressing JSON Schema definitions.

Provides seamless access to a REST API for integrating chat functionalities, enabling configurable client setup, request handling, and streaming of response chunks for efficient data processing.

Leverages Firebase REST API for integrating authentication, real-time database, and Gemini AI in multiplatform applications. Facilitates seamless feature setup and initialization across various platforms.

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.

Connect tools, compose logic, and manage agents with capabilities for chat, memory, streaming responses, and tool integration. Supports interaction with large language models.

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.

Enables automatic detection of file content types for binary data, streamlining API interactions by setting MIME types and encoding data as base64 strings for AI platforms.

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

Facilitates simple or advanced chat interactions using customizable message structures and models, supporting both single and multi-chat scenarios with streaming or non-streaming outputs.

Framework-agnostic on-device LLM inference with a unified OnDeviceGenerator API: single-shot and streaming generation, model download/progress tracking, systemInstruction handling, and simple cancellation semantics.

Transparent proxy converting non-stream OpenAI Responses and Chat Completions requests into SSE upstream streams, aggregating events in memory and returning single JSON responses, while passing through streaming requests unchanged.

Enables OpenAI chat and assistant flows with integrated functions support, facilitating seamless interaction and automation within chat applications.