Agents need real-time ingestion, fast aggregation, flexible handling of semi-structured events, low-latency concurrency, and economics that still work at massive scale. ClickHouse already has this foundation

ClickHouse is a leading platform for open-source columnar database technology and real-time analytics. With ClickHouse, developers can delve into documentation, case studies, and performance benchmarks to learn how to build highly scalable and performant analytical systems. It provides tips about ClickHouse's storage engine, query execution, and distributed architecture. Developers can gain insights into their data in real-time, enabling them to make informed decisions and extract  business insights.

ClickHouse

ClickHouse outlines its strategy for serving AI agents as a new class of database users. The post covers the 'Agentic Data Stack' reference architecture combining LibreChat, ClickHouse with MCP, and Langfuse for observability. Key releases include open-source and remote MCP servers, chDB 4 with a Pandas-like API, ClickHouse Agent Skills for encoding best practices, IDE integrations for Cursor and Kiro, and agent-friendly documentation with llms.txt support. The post also highlights internal usage via DWAINE (an AI-first data warehouse serving 250+ users) and external adoption by OpenAI, Anthropic, and Character.AI for petabyte-scale workloads.

How we’re building a data platform for a new user: agents

Releases for agents and agentic developers #

AI runs on data, and that data runs on ClickHouse #