SereneDB Launches Krummelanke: The Fastest Search and Analytical Engine Enabling the Agentic Future

SereneDB, the fastest search & analytics database in the world, led by Alexander Malandin and Andrey Abramov, has launched Krummelanke, the first production-ready version of its real-time search analytics database, data infrastructure designed from the ground up for the workload that will define the next decade of computing: fleets of AI agents querying massive enterprise data at machine speed.

SereneDB Krummelanke is open source under the Apache 2.0 license and available now on GitHub.

The User of Enterprise Data Is Changing Faster Than the Infrastructure.

Enterprise databases were largely designed around human users, while AI agents can generate hundreds of queries per second and operate continuously. Nvidia CEO Jensen Huang has projected that Nvidia could eventually have millions of AI agents working alongside its human workforce, while Gartner reported a sharp increase in agentic-AI inquiries during 2025 and projects agentic AI software spending to reach $985 billion by 2030.

As AI agents become more prevalent, enterprise data infrastructure will need to support a growing volume of automated, continuous interactions.

“The agentic future is, above all, a data-load problem,” said Alexander Malandin, co-founder and CEO of SereneDB. “Today an AI agent is a single bee visiting a single flower. What is coming is the swarm: more agents than employees in every organization, each firing hundreds of queries a second. Infrastructure built for human users is neither fast enough nor cost-efficient enough to survive that load. The agentic future requires a new generation of database: ultra-fast search and ultra-fast analytics in one engine, where search operations are measured in nanoseconds and a question over billions of records comes back in milliseconds. One that treats agents as first-class users, withstands their scale, and reaches data wherever it lives. That is what we built, and with SereneDB Krummelanke we are putting it into production.”

Agents Ask Hybrid Questions. Databases Were Built to Answer Half of Them.

AI agents increasingly combine natural-language search with analytical queries, requiring systems to retrieve relevant information from unstructured data and compute over it in a single workflow. Traditionally, full-text search and analytical databases have operated as separate systems connected through pipelines and synchronization layers.

SereneDB combines full-text, vector search, and analytics in a single engine, enabling unified query execution without separate ETL pipelines. The approach is designed for AI workloads that require both information retrieval and analysis.

Cost-Efficiency by Architecture.

SereneDB uses a tiered storage architecture that keeps frequently accessed data in a local working set while storing less-active data in low-cost cloud object storage such as Amazon S3, where it remains searchable. Disk-based vector indexes extend the same approach to AI retrieval workloads.

The platform is designed to query petabyte-scale datasets and billions of vectors on a single node, supported in part by 10×+ adaptive hybrid compression. Scale-out currently uses federation, with multi-node compute over an elastic, decoupled storage layer planned for the future.

“We designed the fastest search engine in the world as proven by the benchmark results we announced today. Besides the speed, SereneDB is able to shrink the expensive part of your infrastructure to the size of your hot set, while everything else sits on object storage at a fraction of the cost — and stays searchable,” said Andrey Abramov, co-founder and CTO of SereneDB. “Everyone knows how to run analytics over S3. Search over S3 is the part nobody had really solved, and it is the part that changes the economics. In a design-partner deployment, a workload that cost about $2,500 a month in infrastructure now runs at roughly a tenth of that. Our benchmarks, configurations, and methodology are public and reproducible on GitHub — don't take our word for it, run them.”

SereneDB is compatible with Postgres and Elastic, allowing existing tools to connect without major rewrites and simplifying migration through replication. Its IResearch search engine has been in production development since 2014, with comparative benchmarks published against Postgres-based, Lucene-based, and analytical systems.

SereneDB also treats AI agents as a distinct class of database user, enforcing roles and access controls at the data layer. By indexing data in place rather than requiring copies in separate systems, the platform aims to support agent workloads while addressing security and data-sovereignty requirements.

From Adoption to Production in Days.

Among the teams building on SereneDB is Justee.ai, a legal AI platform that analyzes contracts, employment documents, and compliance materials for SMBs, founders, and in-house teams. The platform currently focuses on the U.S. market, with plans to expand into Commonwealth markets.

Zaykow’s experience points to a broader shift: AI-assisted development has made software creation more accessible, but working with large datasets has remained largely the domain of professional programmers. SereneDB Krummelanke aims to narrow that gap by allowing coding agents to connect directly to an enterprise database through a single MCP connection, without requiring a new query language.

The approach could make large datasets more accessible to builders working in fields such as biotech, genomics, and other data-intensive domains.

“SereneDB gave us something we didn't expect to find: an insanely fast, all-in-one database that was genuinely easy to adopt. Our coding agent worked directly against SereneDB's documentation, and we had search and analytics features live almost immediately — no lengthy migration, no new query language to learn. That speed matters a lot right now, as we build out legal document analysis for small and medium businesses across the Commonwealth. We're excited to keep growing with SereneDB as a partner,” said Max Zaykow, Founder, Justee.ai.

𝐑𝐞𝐦𝐨𝐭𝐞 𝐇𝐢𝐫𝐞 𝐨𝐫 𝐁𝐮𝐢𝐥𝐝 𝐖𝐢𝐭𝐡 𝐔𝐬: 𝐁𝐮𝐢𝐥𝐝𝐰𝐞𝐫𝐤𝐬 helps technology companies build in India: two ways. Hire vetted remote engineers, product leaders, designers, and GTM professionals directly onto your team. Or partner with a proven development studio to design, build, and ship your product end-to-end. Learn More At: menlotimes.com/buildwerks