AlloyDB AI
cloud.google.com
- Free trial
- Linux
- Web
- API
- Self-hosted
6.8 Club score Visit cloud.google.com
Plans
Every plan and priceAlloyDB for PostgreSQL, pay-as-you-go
—
30-day trial
What the maker publishes
- Agent connectivity
- AlloyDB includes a fully managed remote MCP server for providing agents access to data. source
- AI functions
- AlloyDB AI functions let SQL queries generate embeddings, perform similarity searches, call AI models, analyze sentiment, generate content, and run forecasts. source
- Certifications
- Google lists AlloyDB certifications including ISO 27001, ISO 27017, ISO 27018, ISO 27701, SOC 1, SOC 2, SOC 3, PCI DSS, and HIPAA. source
- Deployment
- AlloyDB Omni is a downloadable AlloyDB edition for on-premises, air-gapped, edge, or multicloud deployments. source
- Encryption
- AlloyDB encrypts cluster data at rest by default and supports customer-managed encryption keys, Cloud KMS Autokey, and Cloud External Key Manager. source
- Framework integrations
- The product page names Agent Development Kit, LangChain, and LlamaIndex as orchestration framework integrations. source
- Model access
- Users can access Gemini or other foundation models hosted on Gemini Enterprise Agent Platform and register endpoints on any platform for calls from AlloyDB SQL functions. source
- Natural language
- QueryData lets data agents translate natural-language questions into SQL and disambiguate questions when needed. source
- Network security
- AlloyDB supports TLS 1.3, VPC Service Controls, and private connectivity options; its default endpoint is not publicly routable. source
- Notable pricing limit
- CPU and memory are priced per vCPU and GiB, pricing varies by location, and an instance can have up to 288 vCPUs and 2,232 GiB memory per node. source
- Purpose
- AlloyDB AI integrates vector embeddings, high-performance vector search, and natural language into a PostgreSQL-compatible database for building AI agents and apps. source
- SQL and vector queries
- The ScaNN index integrates with the PostgreSQL query planner, and adaptive filtering coordinates filters, joins, and vector indexes. source
- Vector search
- Its ScaNN index supports pgvector-compatible semantic search and is described as scaling to over 10 billion vectors. source
- Who it is for
- The product is presented for developers building AI applications and agents grounded in structured and unstructured enterprise data. source
Checked against the maker's pages on 9 Oct 2026.