SensiML Piccolo AI

Free Open-Source AutoML Solution for Edge AI

Create accurate ML pattern-recognition code for sensor-equipped IoT devices
using powerful AutoML for simplified and automated data science.

Power Up Your IoT Sensing Devices with Real-Time Intelligence

  • Keyword spotting
  • Sound recognition
  • Voice command
  • Speaker Identification
  • Activity Recognition
  • Gesture Detection
  • Presence Detection
  • Gait/Motion Analysis

Machine Monitoring and Analytics

  • Vibration classification
  • Anomaly Detection
  • Process Monitoring
  • Machine State Analysis

Ultra-Compact Edge ML Code

Generating models as small as 5KB with built-in profiling estimator to show RAM, Flash, and Stack memory as well as model latency

No-Code GUI or Python SDK

Choose your preferred interface and switch freely between point-and-click and programmatic pipeline workflows.

AutoML Model Generation

Automated model generation with optional fine-grained user control allows productive ML development for data scientists and AI novices alike.

C Source Code Output

No RTOS or external code dependencies. Model outputs are self-contained, highly portable model libraries with multiple levels of inference interfacing to your code.

Broad Platform Support

Espressif ESP32

Intel ISA x32/x64

Microchip PIC

RISC-V Core

* All third-party trademarks, logos, and brand names shown are the property of their respective owners

SensiML Piccolo AI open-source solution

Our time-tested code base opened up for community contribution

SensiML has open-sourced its Piccolo AI toolkit to foster a thriving edge AI developer community, drive innovation, and extend AI’s reach to billions of IoT devices through efficient, distributed intelligence.

Piccolo AI features include IoT edge-optimized modeling, automated model pipeline development via AutoML, GUI and Python SDK interfaces, and full C source code generation.

SensiML invites community contributions to expand Piccolo AI’s capabilities, such as:

  • Generative AI model tuning
  • Synthetic dataset augmentation
  • Local LLM support
  • Image and video object recognition
  • Advanced edge model optimization
  • New hardware integrations
  • More pre-trained model templates for practical applications

Get Started With Piccolo AI Today

Piccolo AI runs as a web application served from a Linux server endpoint running locally on your own system. Piccolo can therefore be run on a Linux system or Windows desktop PC.

You can get started building intelligent sensor algorithms for edge IoT devices in as little as 20 minutes using our convenient step-by-step installation video.

Watch the How-To Install Video

Got Questions?

Most Popular Questions:

Yes, Piccolo AI is free to use. It is released under the GNU Affero General Public License (AGPLv3) an open-source license, allowing you to use, modify, and distribute the software in compliance with the license terms specified on the project site.

Determining the exact amount of data required to achieve a desired level of accuracy in a machine learning model is challenging, as it depends on the specific use case and the variability of influencing factors. Each application has unique contributing factors that affect model outcomes and the degree of data variance across those factors.

The role of the domain expert is crucial. They should:

  • Identify all potential influencing factors.
  • Rank these factors by their expected impact on the model’s performance.
  • Decide which factors can be controlled or eliminated outside of the model.
  • Develop a reasonable testing methodology based on these considerations.

We recommend an iterative approach:

  1. Start with a Small Dataset: Begin with a modest amount of data to build an initial model. This helps gain insights into which factors contribute most to model errors.
  2. Analyze and Adjust: Use the initial model to understand errors and identify influential factors.
  3. Expand Data Collection: Based on insights gained, collect additional data focusing on the most impactful factors. Conduct this in stages, alternating between data collection, analysis, and model refinement.

Initial model development can sometimes be performed with a small number of samples—perhaps 50–100 per class—to gain preliminary insights. However, the specific amount can vary widely depending on the complexity of the problem and the desired accuracy. Generally, more data leads to better-performing and more reliable models.

Piccolo AI’s open-source license may permit commercial use. However, you should review the specific licensing terms provided on the project site to ensure compliance with all requirements for commercial applications.

Commercial users desiring proprietary license terms and full enterprise-level support can license SensiML Analytics Studio, the commercial variant of Piccolo AI that allows use without copyleft license obligations and provides premium features and various direct support options. More information on SensiML Analytics Studio can be found at sensiml.com or by contacting info@sensiml.com

Piccolo AI is an open-source project developed by SensiML that provides tools and libraries for implementing AI algorithms on resource-constrained devices. It extends SensiML’s mission of enabling intelligent IoT solutions by offering a community-driven platform for developers.

Yes, comprehensive documentation and tutorials are available on the Piccolo AI project site. These resources include getting-started guides, API references, and example projects to help you effectively use the platform.