The open platform for AI on real-time data

From chat to agents to MCP and beyond, ClickHouse Platform for AI is the open, end-to-end stack that brings AI to your data, enabling agentic analytics in real time, at any scale.

Why ClickHouse for AI

Open platform for managed agentic analytics, powered by Claude

Power AI agents on real-time data

Achieve sub-second latency cost effectively across billions of rows and petabytes of data while handling thousands of concurrent requests.

Deliver agentic analytics in minutes

Deploy complete and production-ready agentic analytics instantly. Eliminate the complexity of infrastructure management and third-party stitching.

Build with full control of your AI stack

Maintain flexibility with an open data and AI stack with ClickHouse, LibreChat, MCP connectivity, and Langfuse. Make your AI stack portable and free from vendor lock-in.

What’s inside

Chat natively, build, or bring any agents to your real-time data, with zero lock-in.

ClickHouse platform for AI

Observability(ClickStack)

Connectivity layer

MCP

ClientsCLIPlugins

Agentic layer

ClickHouseAssistant

ClickHouseAgents

+ Code Interpreter

Data layer

Context management (skills)

Managed Ingestion

LLM Engineering(Langfuse)

See customers in action delivering agentic analytics

LibreChat powers reflexive AI use across Shopify. With near universal adoption and thousands of custom agents, teams use it to solve real problems, increase productivity, and keep the quality bar high. By connecting more than 30 internal MCP servers, it democratizes access to critical information across the company

By leveraging the ClickHouse, MCP, and LibreChat stack, we rapidly delivered a prototype to cBioPortal users that empowered them to ask entirely new questions about cancer genomics and treatment trajectories, get quick answers, and explore data in ways not possible through the existing UI. It puts discovery at cancer researchers' fingertips.

We built our new product, FAST by Fetch, on ClickHouse to help users instantly discover insights and drive efficient activation. We see agentic analytics as the future of data interaction, enabling more intuitive, dynamic, and impactful use of information. With its unmatched speed and scalability, ClickHouse is well-positioned to power this new generation of agentic experiences, and we’re thrilled to grow our partnership together.

With LibreChat, Daimler Truck is making the power of modern AI available to all employees. This enables the company to bring innovation and progress into everyday work – simply, transparently, securely, and full of new opportunities.

Capabilities

Chat interface

Ship production-ready agentic analytics on your ClickHouse data in minutes with no configuration needed.

No-Code Agent Builder

Build and share specialized, governed agents for every team and workflow, without writing a line of code.

ClickHouse Assistant

Write SQL faster, debug queries, and learn ClickHouse directly in the Cloud console.

Sandboxed Code Interpreter

Run Python or JavaScript against live ClickHouse query results inside any conversation to model, transform, and visualize inline.

MCP Connectivity

Connect with any agent, IDE, or BI tool to ClickHouse over the open MCP protocol. Keep full control with no lock in.

Multi-agent Workflows & Sub-agents

Orchestrate teams of specialist sub-agents to run end-to-end analytical workflows concurrently.

ClickHouse welcomes Langfuse: The future of open-source LLM observability

Built for Production AI
Close the AI Engineering loop.

Trace full agent workflows, from prompts to tool calls and responses

Evaluate agent outputs with custom scoring and human feedback

Monitor quality, cost, and latency across every LLM call

Build with Open Source

Compose your own AI stack, open at every layer

Chat with your data in a familiar, open-source UI, powered by LibreChat

Connect to your favorite tools over the open Model Context Protocol (MCP)

Trace, evaluate, and ship better agents with LLM observability using Langfuse

Learn more about the Agentic Data Stack

Explore how the Agentic Data Stack enables AI agents to query, reason, and act on data in real time. Dive into practical examples, architectural deep dives, and product updates from the teams building agent-native analytics at ClickHouse.

You’ll learn about:

How agents interact with data using MCP and open standards

Designing analytics systems built for AI-first workflows

Real-world use cases for agent-facing analytics

The open-source foundations behind the Agentic Data Stack

View documentation ->->