Google PM Open-Sources Always On Memory Agent with SQLite Storage, No Vector DB

What This Is

Google senior AI product manager Shubham Saboo has open-sourced an "Always On Memory Agent" on the official Google Cloud Platform GitHub page under MIT License. It's a reference implementation for an agent system that can ingest information continuously, consolidate it in the background, and retrieve it later without relying on conventional vector databases.

Technical Details

The agent runs continuously and ingests files or API input, storing structured memories in SQLite. It performs scheduled memory consolidation every 30 minutes by default. The system supports text, image, audio, video and PDF ingestion.

The repository frames the design with the claim: "No vector database. No embeddings. Just an LLM that reads, thinks, and writes structured memory." This shifts the performance question from vector search overhead to model latency, memory compaction logic and long-run behavioral stability.

The agent was built with Google's Agent Development Kit (ADK) introduced in Spring 2025 and uses Gemini 3.1 Flash-Lite, which Google introduced on March 3, 2026 as its fastest and most cost-efficient Gemini 3 series model.

Model and Performance

Gemini 3.1 Flash-Lite is priced at $0.25 per 1 million input tokens and $1.50 per 1 million output tokens. Google says it's 2.5 times faster than Gemini 2.5 Flash in time to first token and delivers a 45% increase in output speed while maintaining similar or better quality.

On Google's published benchmarks, the model posts an Elo score of 1432 on Arena.ai, 86.9% on GPQA Diamond and 76.8% on MMMU Pro. Google positions these characteristics as a fit for high-frequency tasks like translation, moderation, UI generation and simulation.

Architecture and Components

The repo appears to use a multi-agent internal architecture with specialist components handling ingestion, consolidation and querying. A local HTTP API and Streamlit dashboard are included. The project serves as a practical reference implementation for something many AI teams want but few have productionized cleanly.

ADK as a framework supports multi-agent systems, but this specific repo is best described as an always-on memory agent, or memory layer, built with specialist subagents and persistent storage.

Use Cases and Considerations

The release matters less as a product launch than as a signal about where agent infrastructure is headed. It packages a view of long-running autonomy that is increasingly attractive for support systems, research assistants, internal copilots and workflow automation.

The design choice to avoid vector databases can simplify prototypes and reduce infrastructure sprawl, especially for smaller or medium-memory agents. However, it brings governance questions into sharper focus as soon as memory stops being session-bound.