jamro/tiny-engineer

A small desktop robot that brings an AI coding assistant to life, physically acting out when it reads files, thinks, writes code, and finishes work.

What it solves

It provides a physical manifestation for AI coding agents. Instead of relying on a status bar or spinner in an IDE, users can have a 3D-printable desktop robot that visually signals what the AI is doing—such as reading, thinking, or typing—allowing the user to monitor the agent's progress without staring at the screen.

How it works

The system consists of a 3D-printed robot powered by an ESP32-C3 microcontroller. The robot exposes a REST API over Wi-Fi, which allows external tools to trigger specific animations. Integrations (such as hooks for the Cursor editor or the Antigravity CLI) translate AI agent lifecycle events into HTTP requests that tell the robot to move its servos, update its OLED display, or play audio.

Who it’s for

Developers who use AI coding agents and want a tangible, physical way to track their agent's activity on their desk.

Highlights

  • Open-source hardware: Includes 3D-printable parts and a detailed bill of materials for DIY assembly.
  • Simple Integration: Uses a standard REST API, making it compatible with any tool that can send HTTP requests.
  • Multi-modal feedback: Combines five servos for movement, an OLED screen for facial expressions/status, and a speaker for audio.
  • Ready-made hooks: Provides specific integration paths for tools like Cursor and Antigravity.

Related

  • Project
    fujitatomoya/ros2ai

    A command line interface extension for ROS 2 that allows users to query and execute robotics commands using natural language via OpenAI or Ollama.

  • Project
    amazon-far/abc

    A scalable behavior cloning framework for robotics that provides training pipelines and evaluation tools for Diffusion Transformer (DiT) and Vision-Language-Action (VLA) models.

  • Project
    ACFR-RPG/DynOSAM

    DynoSAM is a Stereo/RGB-D Visual Odometry pipeline for Dynamic SLAM that estimates camera poses and object motions while mapping static backgrounds.

  • Project
    InternRobotics/VLAC

    A Vision-Language-Action-Critic model that provides dense reward feedback and trajectory quality screening for real-world robotic reinforcement learning.