Editorial illustration for Google open-sources Always On Memory Agent, using SQLite over vector DBs
Google's Always On Memory Agent Redefines AI Data
Google open-sources Always On Memory Agent, using SQLite over vector DBs
Google’s product team just pushed a new open‑source project called the Always On Memory Agent, and it does something most LLM‑centric tools avoid: it skips the usual vector‑search stack entirely. Instead of relying on a dedicated similarity index, the agent writes every piece of structured data it receives straight into a SQLite file. It runs as a background service, pulling in files or API payloads on the fly, and then every half‑hour it consolidates those memories according to a built‑in schedule.
Developers can talk to it through a local HTTP endpoint or spin up a quick Streamlit UI to inspect what’s been stored. By swapping a heavyweight retrieval layer for a lightweight relational database, the team is betting on a leaner, more maintainable design. That choice underpins the next point—
---
*The architecture favors simplicity over a traditional retrieval stack.*
The architecture favors simplicity over a traditional retrieval stack According to the repository, the agent runs continuously, ingests files or API input, stores structured memories in SQLite, and performs scheduled memory consolidation every 30 minutes by default. A local HTTP API and Streamlit dashboard are included, and the system supports text, image, audio, video and PDF ingestion. The repo frames the design with an intentionally provocative claim: "No vector database.
Just an LLM that reads, thinks, and writes structured memory." That design choice is likely to draw attention from developers managing cost and operational complexity. Traditional retrieval stacks often require separate embedding pipelines, vector storage, indexing logic and synchronization work. Saboo's example instead leans on the model to organize and update memory directly.
In practice, that can simplify prototypes and reduce infrastructure sprawl, especially for smaller or medium-memory agents. It also shifts the performance question from vector search overhead to model latency, memory compaction logic and long-run behavioral stability.
Google has released an open‑source Always On Memory Agent under an MIT license, letting anyone embed a persistent memory layer into LLM‑driven applications. Built with the 2025 Agent Development Kit and Gemini 3.1 Flash‑Lite, the agent runs continuously, pulling files or API payloads into a SQLite store. Every thirty minutes it consolidates memories, then exposes a local HTTP endpoint and a Streamlit UI for inspection.
The design choice—favoring SQLite over a traditional vector database—prioritises simplicity and low‑cost deployment. Yet it is unclear whether a file‑based relational engine can handle the scale of embeddings that larger agents typically generate. The repository notes that the architecture “favors simplicity over a traditional retrieval stack,” suggesting a trade‑off between ease of use and retrieval performance.
For developers who need a lightweight, always‑on memory component, the project offers a ready‑made solution; for those with heavy‑weight retrieval demands, the suitability remains to be proven. Overall, the contribution adds a concrete, permissively‑licensed building block to the emerging toolkit for LLM agents.
Further Reading
- Papers with Code - Latest NLP Research - Papers with Code
- Hugging Face Daily Papers - Hugging Face
- ArXiv CS.CL (Computation and Language) - ArXiv
Related Reading
Browse all Google news →
Open Source UK PM vows action on Grok's deepfake scandal, Starmer condemns X
Open Source GPT-5 helps mathematicians offload tedious tasks, says Timothy Gowers
Open Source India proposes licensing and royalty rules for AI training by Google, OpenAI
Related Topic Gemini 3 Pro builds screenshot-to-code app in two prompts, fixes bugs
LLMs & Generative AI
Related Topic Gemini 3 Pro and GPT-5 stumble on graduate-level physics benchmark
LLMs & Generative AI
From Archives Meta AI glasses route private footage to Nairobi contractors for review
From Archives LangChain repo offers 11 portable skills for coding agents via repo
From Archives Google Workspace CLI merges Gmail, Docs, Sheets for AI agents, cutting glue code
Market Trends
From Archives Google sued over Gemini chatbot allegedly coaching 36‑year‑old to suicide
Policy & Regulation
Common Questions Answered
How does the Always On Memory Agent differ from traditional vector database approaches?
The Always On Memory Agent uniquely uses SQLite for data storage instead of a dedicated vector database, prioritizing simplicity and direct data ingestion. This approach allows for continuous memory capture and consolidation every 30 minutes, without the complexity of traditional retrieval stacks.
What types of data can the Always On Memory Agent ingest and store?
The agent supports multi-modal data ingestion, including text, image, audio, video, and PDF files. It can pull these files or API payloads directly into a SQLite storage system, creating a flexible and comprehensive memory management solution.
What are the key technical components of Google's Always On Memory Agent?
The agent is built with the 2025 Agent Development Kit and Gemini 3.1 Flash-Lite, runs as a continuous background service, and includes a local HTTP API and Streamlit dashboard for memory inspection. It consolidates memories every 30 minutes by default and is released under an MIT open-source license.