Most AI brokers overlook. They course of a request, reply it, then drop the context. Google Cloud’s generative-ai repository now ships a pattern that tackles this straight. It’s the All the time-On Reminiscence Agent, a reference implementation that treats reminiscence as a operating course of.
All the time-On Reminiscence Agent
Basically, the undertaking is a light-weight background agent that by no means stops. It runs 24/7 as a steady course of, not a one-shot name. It’s constructed with Google ADK (Agent Improvement Package) and Gemini 3.1 Flash-Lite. Notably, it makes use of no vector database and no embeddings. As a substitute, an LLM reads, thinks, and writes structured reminiscence into SQLite. The mannequin selection targets low latency and low value for steady background work.
How It Works: Ingest, Consolidate, Question
Architecturally, an orchestrator routes each request to considered one of three specialist sub-agents. Every sub-agent owns its personal instruments for studying or writing the reminiscence retailer.
First, the IngestAgent handles incoming content material. It makes use of Gemini’s multimodal capabilities to extract a abstract, entities, matters, and an significance rating. That structured file then lands within the recollections desk.
Subsequent, the ConsolidateAgent runs on a timer, each half-hour by default. Like sleep cycles, it opinions unconsolidated recollections and finds connections between them. Then it writes a synthesized abstract, one key perception, and people connections to the database. Consequently, the agent builds new understanding whereas idle, with no immediate.
Lastly, the QueryAgent solutions questions. It reads all recollections and consolidation insights, then synthesizes a response. Importantly, it cites the reminiscence IDs it used as sources.
