Loading post…
ClickhouseAnnouncement
ClickHouse Agents: Claude-powered agentic analytics, now in public beta
Summary
ClickHouse announced the public beta of ClickHouse Agents, a fully managed agentic analytics service in ClickHouse Cloud powered by Claude. It provides a no-code builder for agents grounded in live ClickHouse data, plus a managed chat experience in the Cloud console, so users need no SQL or separate hosting setup. Built on LibreChat, the service supports natural-language questions, SQL and visualizations, sandboxed Bash, Python, and JavaScript execution, shareable artifacts, skills, memories, MCP-compatible connections, and multi-agent workflows. Claude Sonnet and Haiku are pre-configured, while enterprise controls include SSO, encrypted message storage, and governed data access. ClickHouse says its internal deployment handles roughly 70% of data warehouse queries and processes more than 45 million tokens daily, confirming its view that real-time analytics is a natural context for high-volume agent workloads.
Context
ClickHouse describes AI agents as a new user persona for real-time databases. Its production experience found that agents can generate 10 to 100 times the query volume of human analysts in bursts, while retries and timeouts add token consumption and system load. The company identifies sub-second latency on billions of rows, petabyte-scale storage, high concurrency, and cost efficiency as important for keeping agent traffic affordable.
Approach / What changed
ClickHouse Agents combines a no-code agent builder, managed multi-tenant chat, Claude Sonnet and Haiku, a sandboxed code interpreter, skills, memories, artifacts, and multi-agent workflows inside ClickHouse Cloud. It connects natively to ClickHouse and MCP-compatible systems, uses Cloud RBAC and enterprise security controls, and is built on the open-source LibreChat platform. Customers can also bring their own agents, models, and tools through the connectivity layer.
Takeaways
ClickHouse Agents is available in public beta to all ClickHouse Cloud customers through the SQL console.
The sandboxed code interpreter runs Bash, Python, and JavaScript against live query results within a conversation.
ClickHouse reports that its internal LibreChat-based deployment handles roughly 70% of data warehouse queries and processes more than 45 million tokens per day.
Source and freshness
- Source
- clickhouse.com
- Published
- Added to Yomu
- Last updated
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.