“Agent memory”

Fully managed AWS service that gives agents short-term memory within a session and long-term memory across sessions.

AWS platform for deploying and operating production AI agents with any framework and any model.

CPU and GPU machines and sandboxes for agents, billed by the millisecond, with VMs that pause with memory intact.

Conversational AI engine that lets any LLM listen and reply in real time, with ASR and TTS selection, interruption handling and noise suppression.

Launch computers for agents, code sandboxes and apps on hardware-virtualized Fly Machines.

Perpetual sandboxes that idle to standby and resume in about 25 milliseconds, with shared agent storage.