RavenDB says its Quill AI context software means AI agents can access existing SQL databases without migrating the data to a new repository or building a custom AI software stack.
RavenDB is an Israeli company shipping the eponymous RavenDB, an open-source, NoSQL document database, with ACID transaction guarantees, used by more than 12,000 businesses. Quill is software that creates a live AI context layer on top of an existing SQL database - or databases - that’s constantly synchronized, using change data capture. The AI workload runs outside the SQL database, so nothing extra touches production. There is no data migration, and production is untouched. The Quill layer runs in a customer’s environment and only contains what the customer’s people put in it. The agents only see the synced data and they are restricted by source permissions.
Oren Eini, founder and CEO of RavenDB, said: "Anyone can stand up an AI demo in an afternoon, but getting that demo into production with data pipelines, semantic search, security, governance, all the plumbing a small proof of concept doesn't need until it has to run at scale, is the hard part."
AI agents typically talk to a SQL database using MCP and a tool layer.
Eini says: "Quill exists because we'd rather hand teams that plumbing already assembled than watch them rebuild the same project after project. You get access to the live data you need, decide the scope on day one, and change it as you go, instead of building everything from scratch."
Vector embeddings are generated and tuned automatically. Agents, RAG, vector search and generative AI are included. There is no vector database to run. Likewise there is no AI data pipeline to set up, starting with the SQL databases. Effectively Quill is the data pipeline.
Any AI assistants (LLMs) and agents can interrogate Quill. For example, customers ask about their account, order, or claim in plain language: "When's my next appointment?" "Order what I had last time." "Why was my claim denied?" And answers come from live operational data.
Customers can, RavenDB says, build agents on their data, with the actions they can take defined by the customer. Scopes are enforced in the layer, so an agent physically cannot reach data it wasn't given.
With Quill it’s possible to launch production-ready agents in weeks rather than the 18 to 24 months of a typical in-house build. The source system stays exactly where it is and remains authoritative, and the full AI stack, search, retrieval, and agents that can answer questions, are included. Agents built on Quill support web chat, WhatsApp, Telegram, Slack, and Discord out of the box.
Customers decide exactly what an agent can and cannot see, independent of the source database's own permissions. In a healthcare setting, for example, an agent can answer a patient's question about an upcoming appointment, while prescription data is never part of the dataset it can query.
Quill is now available for organizations running PostgreSQL, SQL Server, or MySQL, with more databases to be supported in the future, and can be deployed in the cloud or on-premises to meet data-residency or regulatory requirements.
Find out more here.