The SETI Institute and Breakthrough Listen have deployed agentic AI systems at the Allen Telescope Array in Northern California to process live radio telescope data in the search for extraterrestrial intelligence, according to an NVIDIA blog post. AI agents can now steer the telescope instrument, enhance and correct incoming data, and apply AI models to the data stream using natural language requests.
The system uses the NVIDIA Holoscan platform to process massive sensor data streams. The DAQIRI library pulls terabits per second of data directly into GPU memory for processing in flight rather than filling hard drives. CyberEther, a signal-processing framework developed at the SETI Institute, performs calculations using NVIDIA CUDA-X libraries including cuFFT and cuBLAS. According to the institute, the system can handle 2.4 terabits per second on NVIDIA RTX PRO 6000 Blackwell GPUs.
Nexus, a web-based observatory orchestrator, serves as the agent harness, providing agents access to instrument state, compute resources and pipelines. Researchers can monitor packet loss, read live spectrograms and rewrite signal-processing blocks through natural language prompts.
“As our new agentic observatories reach out into the universe, what they find may have much more in common with themselves than with the humans who created them,” said Andrew Siemion, Bernard M. Oliver chair for SETI at the SETI Institute and principal investigator of Breakthrough Listen. “But this isn’t something to fear. Rather, it’s a breakthrough in translation.”
The SETI Institute says the approach aims to create a faster, more adaptable search for potential signals from extraterrestrial life and technologies. Radio telescopes generate enormous data volumes, creating challenges for scientists who need to identify potentially interesting signals as observations unfold.