We've partnered with
@perplexity_ai to bring Perplexity Computer inside your compute boundary.
ACRA runs it on your infrastructure and enforces which data, tools and networks each workload can access.
You choose the open-weight model, such as Nemotron, GLM, Kimi, DeepSeek-R1 or Qwen, then connect the documents and systems each task needs. Your data stays where it already lives.