#140140th of 206 in ML frameworks and librariesFor science, health and research, robotics
donkeycar
Python library for building and training self-driving RC cars
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.5k
- License
- MIT
- Last commit
- Aug 2026
- Last release
- Aug 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Donkeycar is a modular Python library for building small self-driving cars, aimed at hobbyists and students. A car is a pipeline of parts (camera, GPS, controller, motors, data store, autopilot) run in order on each vehicle-loop pass, configured mostly through myconfig.py. It supports deep-learning, GPS path-following and computer-vision autopilots, and ships a GUI and a simulator.
Who it is for: Hobbyists, students and educators building self-driving RC cars
Strengths
- Deep-learning autopilots on TensorFlow, TensorFlow Lite or PyTorch, plus GPS and computer-vision autopilots
- Includes a simulator, so you can train and test before building hardware
- Parts pipeline lets you write custom parts and add them to templates
- Broad hardware support: several camera types, lidar, game controllers, ESC/servo and differential drive
Weaknesses
- Raspberry Pi is the preferred target, and camera support needs system packages outside PyPI
- Real use assumes building a physical RC car; hardware setup is outside this README
- Separate install extras for Pi, Mac and PC, with different Python versions (3.13 on Pi, 3.12 elsewhere)
- Narrow scope: small-scale RC driving, not a general robotics or ML framework
What it needs
- Docker
- Needs uv, Raspberry Pi (preferred on-board computer), picamera2, libcamera
- Models: TensorFlow, TensorFlow Lite, PyTorch
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |