Skip to content

Mid-weight Python AI Agent 鈥?rich ecosystem support, runs on $50 SBCs like Raspberry Pi. Regional gateway for L2 edge networks.

License

Notifications You must be signed in to change notification settings

Clawland-AI/nanoclaw

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

NanoClaw

Mid-weight Python AI Agent with rich ecosystem support. Runs on $50 SBCs like Raspberry Pi.

Part of the Clawland ecosystem.


Overview

NanoClaw bridges the gap between the ultra-lightweight PicClaw and the full-featured MoltClaw. Built in Python, it leverages the massive Python ecosystem for ML, computer vision, data processing, and automation — all on affordable single-board computers.

Key Features

  • Python Ecosystem — Full access to NumPy, OpenCV, TensorFlow Lite, scikit-learn, and more
  • Local ML Inference — Run small models directly on edge hardware
  • Rich I/O — GPIO, I2C, SPI, Serial, Camera, Microphone support
  • Agent Capabilities — Tool use, memory, multi-step reasoning
  • Cloud Sync — Report to MoltClaw, receive orchestration commands

Hardware Requirements

Component Minimum Recommended
RAM 100MB 512MB+
Storage 200MB 1GB+
Hardware Raspberry Pi Zero 2W Raspberry Pi 4/5
Cost ~$15 ~$50

Use Cases

  • Smart Camera — Person/object detection with Pi Camera + TFLite
  • Voice Assistant — Local wake-word + cloud LLM hybrid
  • Data Collector — Aggregate sensor data from multiple MicroClaw nodes
  • Lab Monitor — Temperature, humidity, air quality with ML anomaly detection

Status

🚧 Pre-Alpha — Architecture design phase. Looking for contributors!

Contributing

See the Clawland Contributing Guide.

Core contributors share 20% of product revenue. Read the Contributor Revenue Share terms.

License

Apache License 2.0 — see LICENSE for details.

About

Mid-weight Python AI Agent 鈥?rich ecosystem support, runs on $50 SBCs like Raspberry Pi. Regional gateway for L2 edge networks.

Topics

Resources

License

Code of conduct

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •