Loading post…
ClickhouseAnnouncement
ClickHouse Agents is now available for Managed Postgres
Summary
ClickHouse Agents is now available for all Managed Postgres services in ClickHouse Cloud, extending its plain-English agent interface to operational data. The beta service, powered by Claude and built on LibreChat, combines an agent builder and chat interface with a sandboxed code interpreter; it is read-only by default and supports MCP-compatible systems. Agents can inspect Postgres schemas, run read-only queries, return the SQL used, and reason across Postgres and ClickHouse by querying each engine independently before merging results. Additional skills guide migration from Postgres to ClickHouse through discovery, access-pattern analysis, schema design, type mapping, CDC ingestion, and validation, while other workflows use metrics, Query Insights, and EXPLAIN to rank performance fixes. Planned extensions include scheduled recommendations and safe automated remediation, but the current release focuses on exploration, analysis, monitoring, and guided database work.
Context
ClickHouse Agents was previously available for data in ClickHouse Cloud, and this release extends the agentic experience to Managed Postgres. The stated motivation is to let teams explore operational data, combine OLTP and OLAP information, monitor and tune databases, and support migrations from Postgres to ClickHouse through a unified data stack.
Approach / What changed
The service connects agents directly to Managed Postgres using tools including run_postgres_select_query, get_postgres_metrics, and list_postgres_slow_query_patterns. Agents parse schemas, execute read-only queries, combine independent Postgres and ClickHouse results, and use skills for migration or performance tuning. The migration workflow covers discovery, access-pattern analysis, ClickHouse schema design, type mapping, CDC ingestion, and validation; tuning uses Query Insights, EXPLAIN, and service metrics.
Takeaways
Managed Postgres agents are read-only by default and return the SQL used for plain-English questions, allowing operational data exploration without changing data.
An agent can query Postgres and ClickHouse independently, align the results, and answer requests spanning transactional and analytical data.
The migration skill covers Postgres-to-ClickHouse discovery, data modeling, type mapping, ClickPipes or PeerDB CDC ingestion, and validation.
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.