We presented Bagel at the joint ROS / PX4 Meetup at Neros in El Segundo, CA about two weeks ago! It was an absolute blast connecting with the community in person!
Missed the demo? No worries! Here’s the scoop on what we unveiled (we showed it with PX4 ULogs, but ROS bags and ArduPilot Dataflash logs are fully supported!)
The problem? We felt the pain of wrestling with robotics data and LLMs. Unlike PDF files, we’re talking about massive sensor arrays, complex camera feeds, dense LiDAR point clouds – making LLMs truly useful here has been a real challenge… at least for us.
The solution? Meet Bagel ( GitHub - Extelligence-ai/bagel: Bagel is ChatGPT for physical data. Just ask questions and get answers. No Fuss. )! We built this powerful open-source tool to bridge that gap. Imagine simply asking questions about your robotics data, instead of endless parsing and plotting.
With Bagel, loaded with a PX4 ULog, you can ask things like:
-
“Are there any errors or warnings in this log?”
-
“Were there any hard decelerations detected in the IMU data?”
We currently support:
- Claude Code
- Cursor
- Gemini CLI
- and the list is growing…
Sound like something that could change your workflow? We’re committed to building Bagel in the open, with your help!
How to Get Involved
Bagel is a community-driven project, and we’d love for you to be a part of it. Your contributions are what will make this tool truly great.
Here are a few ways you can help:
-
Star us on GitHub: Show your support and help us grow by giving us a star.
-
File a bug report: If you find an issue, let us know so we can fix it.
-
Pitch a feature request: Have an idea for a new feature? We’d love to hear it.
-
Join us on Discord: Hang out with the community and chat directly with the Bagel team.
Many people have done so! The community found two bugs and filed two feature requests already!
Thank you for your support!