the-ai-merge/multimodal-agents-course
A free open-source course teaching how to build MCP multimodal agents that process video, images, audio, and text using Pixeltable, Groq, and Opik.

The Kubrick Course is a collaborative educational resource from The Neural Maze and Neural Bits, designed to teach developers to build production-ready AI agent systems. The course focuses on Model Context Protocol (MCP) to connect agents with external tools and data sources. Learners build a complete multimodal agent using FastMCP for the server side, a custom Groq-powered client, Pixeltable for video and multimodal data processing, and Opik for observability and prompt versioning.
Frequently asked
- What is the-ai-merge/multimodal-agents-course?
- A free open-source course teaching how to build MCP multimodal agents that process video, images, audio, and text using Pixeltable, Groq, and Opik.
- Is multimodal-agents-course open source?
- Yes — the-ai-merge/multimodal-agents-course is open source, released under the Apache-2.0 license.
- What language is multimodal-agents-course written in?
- the-ai-merge/multimodal-agents-course is primarily written in Python.
- How popular is multimodal-agents-course?
- the-ai-merge/multimodal-agents-course has 576 stars on GitHub.
- Where can I find multimodal-agents-course?
- the-ai-merge/multimodal-agents-course is on GitHub at https://github.com/the-ai-merge/multimodal-agents-course.