SensiML Analytics Toolkit Suite

Rapid Prototyping for the IoT Edge in Days or Weeks

Transform Your IoT Device From Merely Connected to Truly Intelligent

SensiML brings real-time event detection to the IoT sensing endpoint with a platform that is accessible to any application developer.

Algorithms are created using the SensiML AutoML analytics engine to generate an optimized, device-ready algorithm that balances the desired accuracy with the resource constraints of the target hardware.

These algorithms are automatically compiled to edge platform machine code that can run in real time on the target embedded platform… not in the cloud.

The result is code that runs faster, provides insight where events occur, requires less network performance, and is more secure through better partitioning of data processing tasks.

  • AI in Network or Cloud
  • No Edge Insight
  • High Power Consumption
  • High Latency and Network Bandwidth
  • Source Data Less Secure
  • AI at the Extreme Edge
  • Local Real-time Intelligence
  • Power Optimized
  • Bandwidth Optimized
  • Source Data More Secure

Significant Benefits for Both Product and Development Process

  • Significant TTM Gains: 5x faster development over hand-coded algorithms
  • AI Without Data Science Complexity: AutoML tool usable by mainstream developers
  • Runs on MCUs: Enabling practical AI application on embedded wireless IoT devices
  • Maximize Your Hardware: Smart compilation optimizes for MCU, DSP, and FPGA
  • Extensibility and Flexibility: Add algorithms, change hardware, customize code as desired
  • Proven Solution: Launched in 2016 by Intel, now independent and greatly expanded

SensiML’s platform brings the firmware and data science expertise so that you can go from PoC to production rapidly and with confidence.


SensiML Toolkit enables AI for a broad array of resource constrained time-series sensor endpoint applications. These include a wide range of consumer and industrial sensing applications.

The SensiML Endpoint AI Workflow

Raw Signal Capture to Data Insight Labeling (Data Capture Lab Phase) to Algorithm Generation to Firmware Code Generation (Analytics Studio Phase) to Test, Validation and Support (Test App) Watch The Workflow Video


  • QuickLogic – QuickAI Accelerated AI Platforms
  • ST – STM32 & SensorTile Development Kit
  • NXP i.MX RT1050 Crossover MCU and i.MX RT1050 Eval Kit
  • Nordic Semiconductor – nRF52 & Nordic Thingy IoT Sensor Kit
  • Intel Atom E Processors
  • ARM Cortex-M Series Processors
  • Raspberry Pi 3/3Bs



Predictive Maintenance, Anomaly Detection, Process Control and Inspection, and Industrial Wearables


Occupancy Aware Smart Lighting, Smart City Infrastructure


Motion and Audio Sensor Event Detection, Estrus monitoring, Lameness, Activity Monitoring for Livestock Wearables


Activity Recognition, Gesture Recognition, Audio Event Detection, Motion Analytics for Smart Devices