Hi ROS devs!
I built something to bridge the gap between AI agents and ROS robots. Instead of writing custom interfaces for every LLM integration, this gives you a universal bridge with zero boilerplate.
**Key features:**
- Auto-generates Python classes from .msg/.srv files
- One decorator = ROS action/service/actionlib
- gRPC + WebSocket APIs for remote agents
- Works with ROS1 and ROS2 (humble/jazzy tested)
- Full Docker playground with 4 examples
**The examples:**
1. **Talking Garden** — LLM monitors/controlls IoT plants via ROS topics
2. **Mars Colony** — Multi-robot coordination (excavator, builder, solar, scout)
3. **Theater Bots** — AI director + robot actors with scripted behaviors
4. **Art Studio** — Human and robot painters collaborating on canvas
**Quick start:**
```bash
pip install agent-ros-bridge
# In your Python code:
from agent_ros_bridge import ROSBridge
bridge = ROSBridge(ros_version=2)
@bridge.action(“move_to”)
def move_to(x: float, y: float):
\# Your robot movement code
pass
```
GitHub: GitHub - webthree549-bot/agent-ros-bridge
PyPI: Client Challenge
Open to issues, PRs, and feedback!