pgEdge Announces pgEdge Agentic AI Toolkit for Postgres

Alexandria, VA – December 17, 2025 – pgEdge, the leading open source enterprise Postgres company, today announced the beta release of pgEdge Agentic AI Toolkit for Postgres, enterprise-grade Postgres based infrastructure for developers building Agentic AI applications in environments with strict requirements for high availability, security, data sovereignty and/or global deployment.

Until now, developers wanting to use Postgres as the data infrastructure for their Agentic AI applications have had to pursue their own solutions for moving agentic AI applications from prototyping environments to standard open source, enterprise-grade Postgres infrastructure.  Additionally many developers have been unable to pursue Agentic AI initiatives at all, since many of these environments exist only as managed cloud or SaaS services, which can be off limits because of security or regulatory issues.

The pgEdge Agentic AI Toolkit for Postgres includes a full featured MCP Server that works with all standard versions of Postgres, opening up both new and existing Postgres databases for use with AI application builders and code generators such as Claude Code, Replit and Cursor.

As with other pgEdge Postgres products the pgEdge Agentic AI Toolkit for Postgres is fully open source via the Postgres license. It also offers flexible deployment options including on-premises (even air-gapped), self-managed cloud, or a managed cloud service via pgEdge Cloud.

Key components include:

• A highly performant and full featured MCP Server, providing LLMs and agents with a secure connection to access Postgres databases and obtain detailed information about database structure and schemas, allowing them to reason about the data, schema, and performance metrics held within. The pgEdge MCP Server works with most versions of Postgres, including standard community Postgres and implementations such as Amazon RDS. 
• Natural Language Agents for querying data, available via a command line interface (CLI) or a web user interface. 
• pgEdge-vectorizer, a Postgres extension that automatically chunks text content and generates vector embeddings using background workers, providing a simple SQL interface for enabling vectorization on any table. Vector embeddings are automatically kept updated as the content changes.  
• pgEdge RAG Server, a dedicated API Server for performing Retrieval-Augmented Generation (RAG) of text based on content from a PostgreSQL database using pgvector.  
• pgEdge-docloader, a utility that makes it easy to bring initial material online and make it searchable by agents and can be used in conjunction with the pgEdge RAG Server and pgEdge Vectorizer. No external services or third-party pipelines are required beyond an embedding LLM provider. 
• VectorChord-bm25, a Postgres extension implementing BM25 ranked search for hybrid semantic and full-text searching. Also included are the pgvector, pg_tokenizer.rs and pg_vectorize extensions.

Additionally, the pgEdge AI Toolkit also includes the following features:

• Support for locally hosted models (e.g. Ollama) or Internet-based frontier models such as Claude Sonnet 4.5 and OpenAI GPT-5. 
• High availability for both distributed and non-distributed workloads. pgEdge Distributed Postgres supports globally deployed agentic AI applications requiring a data sovereignty solution and/or a low latency experience for highly distributed users. 
• Full support for PostgreSQL v16, v17 and v18

“We’ve had the benefit of collaborating on real-world AI applications the past two years with a number of leading customers,” said Phillip Merrick, Chairman and Chief Product Officer of pgEdge. “We’ve been able to draw on this experience to deliver a compelling suite of AI tools that coupled with our standard Postgres platform products meet their demanding enterprise class requirements. We are excited to see the new Agentic AI applications more of our customers will build on this foundation.”

Product Availability

pgEdge Agentic AI Toolkit for Postgres is available for free to all Postgres users. pgEdge customers with paid subscriptions for pgEdge Enterprise Postgres or pgEdge Distributed Postgres receive support at no extra cost.  For self-hosted and self-managed deployment the product can be downloaded here. It will be available within the pgEdge Cloud managed service in Q1 2026.

About pgEdge

pgEdge, the leading open source enterprise Postgres company, is on a mission to make it easy for developers to build and deploy highly scalable and distributed database applications across global networks. Founded by industry veterans with decades of both core and advanced PostgreSQL expertise, pgEdge is headquartered in Northern Virginia. Its customers include prominent enterprises such as Bertelsmann, Qube RT, Jobot, European Parliament, and several U.S. government agencies. pgEdge’s investors include Akamai Technologies, Inc., Qube RT, Rally Ventures, Sands Capital Ventures, Grotech Ventures, and Sand Hill East.

For more information, visit www.pgedge.com.