Edge AI Stack

Powerful products that work together to accelerate your AI development from prototype to production with local, on-device processing.

Agentic AI

AI Agents SDK

Powerful C++ SDK for building intelligent agents that can reason, plan, and execute tasks autonomously.

Learn About AI Agents SDK

SDK Features

  • Multi-modal autonomous agents
  • Extensible tools
  • High performance
  • Robust workflows
  • Evaluation & Optimization tools

Agent Capabilities

  • In-vehicle Voice Assistant
  • Mobile Device Assistant
  • Surgical AI Assistant
  • Manufacturing Ops Assistant
  • Offline Emergency Services Voice Assistant

Voice AI

Voice AI Stack

Complete on-device voice pipeline — speech-to-text, text-to-speech, and voice activity detection, all running locally with low latency and full privacy.

Learn About Voice AI

Voice Stack

  • Text-to-speech with multiple expressive voices
  • Real-time speech-to-text with webhook events
  • Voice activity detection
  • Streaming LLM-to-speech pipeline
  • HTTP API with token-based auth

Use Cases

  • On-device voice assistants
  • Offline speech processing
  • Privacy-first voice interfaces
  • Push-to-talk and continuous listening modes

Curated Models

Model Catalog

Open-weight language models from 1B to 35B parameters, curated for prompt adherence, tool calling, and reasoning — optimized for on-device deployment.

Browse Model Catalog

Size Tiers

  • Ultra-Light (1–4B) — phones, IoT, embedded
  • Small (4–14B) — laptops, Jetson, single GPU
  • Edge Server (14–35B) — workstations, edge servers

Selected For

  • Reliable tool calling and function execution
  • Chain-of-thought reasoning
  • Multimodal capabilities (vision, audio)
  • Open weights with HuggingFace availability