Google Cloud 推出 Always-On Memory Agent，用 LLM 持续整合替代 RAG 与向量数据库

Fundamentally, the project is a lightweight background agent that never stops. It runs 24/7 as a continuous process, not a one-shot call. It is built with Google ADK (Agent Development Kit) and Gemini 3.1 Flash-Lite. Notably, it uses no vector database and no embeddings. Instead, an LLM reads, thinks, and writes structured memory into SQLite. The model choice targets low latency and low cost for continuous background work.

How It Works: Ingest, Consolidate, Query

Architecturally, an orchestrator routes every request to one of three specialist sub-agents. Each sub-agent owns its own tools for reading or writing the memory store.

First, the IngestAgent handles incoming content. It uses Gemini’s multimodal capabilities to extract a summary, entities, topics, and an importance score. That structured record then lands in the memories table.

Next, the ConsolidateAgent runs on a timer, every 30 minutes by default. Like sleep cycles, it reviews unconsolidated memories and finds connections between them. Then it writes a synthesized summary, one key insight, and those connections to the database. Consequently, the agent builds new understanding while idle, with no prompt.

Finally, the QueryAgent answers questions. It reads all memories and consolidation insights, then synthesizes a response. Importantly, it cites the memory IDs it used as sources.

Supported Inputs

Beyond text, the IngestAgent accepts 27 file types across five categories. Simply drop any supported file into the ./inbox folder for automatic pickup.

How It Compares to RAG, Summaries, and Knowledge Graphs

To clarify the difference, it frames three common memory approaches. Each solves part of the problem, yet leaves a gap.

Unlike RAG, this agent processes memory actively, not only on retrieval.

Use Cases With Examples

Practically, the pattern fits any workload needing durable, evolving context. Consider three examples.

• A research assistant ingests PDFs, meeting audio, and screenshots all week. Later, it links a cost target to a reliability problem on its own.
• A personal knowledge base absorbs notes, articles, and images continuously. Over time, consolidation surfaces themes you never explicitly connected.
• A support agent stores past tickets as structured memories. Then it answers new questions with cited references to earlier cases.

Getting Started

With the design clear, setup stays minimal for early-level engineers. Install dependencies, set your key, then start the process.

pip install -r requirements.txt
export GOOGLE_API_KEY="your-gemini-api-key"
python agent.py

Once running, the agent watches ./inbox, consolidates every 30 minutes, and serves an HTTP API on port 8888. Therefore, you can also feed it over HTTP.

# Ingest text
curl -X POST http://localhost:8888/ingest \
  -H "Content-Type: application/json" \
  -d '{"text": "AI agents are the future", "source": "article"}'

# Ask a question
curl "http://localhost:8888/query?q=what+do+you+know"

Additionally, the API exposes /status, /memories, /consolidate, /delete, and /clear. An optional Streamlit dashboard adds ingest, query, browse, and delete controls. CLI flags change the watch folder, port, and consolidation interval.

python agent.py --watch ./docs --port 9000 --consolidate-every 15

Key Takeaways

• No vector DB, no embeddings — an LLM reads, thinks, and writes structured memory into SQLite.
• Runs 24/7 on Google ADK + Gemini 3.1 Flash-Lite as a lightweight background process.
• Three sub-agents under one orchestrator: Ingest, Consolidate, and Query.
• Consolidates every 30 minutes — links related memories and writes new insights while idle.
• Ingests 27 file types across text, images, audio, video, and PDFs, dropped into ./inbox.