One SDK. Every device.
LLMs, vision, speech, voice agents, RAG, embeddings, and image generation, running locally on phones, browsers, desktops, and servers.
Private by default. Offline by design. Accelerated by whatever silicon the device has.

_{Eight SDKs, one C++ core. A capability registry routes every call to the best engine on the device, and the Console manages your fleet from above.}

Every capability below runs fully on-device behind one semantic API across the eight SDKs. Call RunAnywhere.capabilities() (v4) to discover what the current package and device can actually execute — enum presence alone does not mean an engine is installed.

• LLM chat: Llama, Qwen, Gemma, Phi, LFM, SmolLM, DeepSeek, and more, with token streaming, multi-turn history, and LoRA adapters
• Structured output: schema-validated JSON; constrained decoding where the engine supports it (generateStructured + enforcement mode)
• Tool calling: local function tools with stable call IDs and an agent loop (parallel calls when the engine/capability reports support)
• Vision (VLM): image understanding, live camera description, and photo Q&A
• Computer-use action parser (CUA): parse Fara1.5-style action strings into viewport-scaled coordinates — not a full autonomous agent framework
• Speech-to-Text: Whisper and Moonshine transcription, batch and live frame streams
• Text-to-Speech: neural voices from Piper, Kokoro, Kitten, MeloTTS, and Magpie
• Voice agents: VAD, STT, LLM, and TTS in one pipeline with SpeechHandle-scoped playback (wake-word detection is not implemented)
• Embeddings: L2-normalized vectors for search and retrieval
• RAG: local document ingestion and retrieval-augmented answers, with streaming
• Image generation: Stable Diffusion on Core ML, plus inpainting on the Hexagon NPU (platform/backend gated)

Your code rarely picks hardware. Engines register what they can run, and the highest-priority engine that fits the device wins: QHexRT