mm-argus is an open-source, real-time multimodal AI agent package for understanding screens, video, audio, and conversations. It is distributed through PyPI for developers building local AI agents and multimodal applications.
mm-argus is a Frameworks & runtimes project. It focuses on building real-time AI agents that can interpret screen, video, audio, and conversational inputs. mm-argus is an open-source project aimed at AI developers. The project is open source (MIT). mm-argus is available on the command line, and it can be self-hosted.
Argus202608 builds and maintains mm-argus, and it first shipped in 2025. Development happens publicly on GitHub with 13.8k commits in the last 90 days. Key capabilities include screen understanding, video understanding, and audio understanding.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do