Stats
Actions
Available In
Tags
Plugin
chdb
In-process ClickHouse SQL + DataStore for AI agents. Run analytical SQL or pandas-style queries on parquet, csv, S3, Postgres, MongoDB, ClickHouse Cloud, Iceberg, and Delta Lake — no server, no ETL.
What's Inside
Skills2
chdb-datastore
/chdb-datastore
Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake as DataFrames and joining across sources. TRIGGER when: user mentions DataFrame, parquet, csv, "fast pandas", "speed up pandas", or cross-source DataFrame joins; user imports `chdb.datastore` or `from datastore import DataStore`. SKIP this skill for raw SQL syntax (use chdb-sql instead), ClickHouse server administration, or non-Python DataStore API work.
chdb-sql
/chdb-sql
Use when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB — embedded ClickHouse SQL in Python with 1000+ functions, Session for stateful multi-step pipelines, parametrized queries, and cross-source joins via `s3()`, `mysql()`, `postgresql()`, `iceberg()`, `deltaLake()`, `remoteSecure()` table functions. TRIGGER when: user wants SQL on parquet/csv/files or across remote analytical sources; uses ClickHouse SQL features (window functions, windowFunnel, geoToH3, JSON path ops, Session, parametrized queries); imports `chdb` or calls `chdb.query()`. SKIP this skill for pandas-style DataFrame method-chaining (use chdb-datastore instead) or ClickHouse server administration.
README
chdb-agent-plugin
Cross-IDE agent plugin bundle for chDB — an in-process
ClickHouse SQL engine for Python. One repo distributes the chDB skill set,
MCP server, and project-level AGENTS.md to every major coding-agent IDE.
Install
Pick your IDE — one command, same plugin:
# Claude Code
/plugin marketplace add chdb-io/chdb-agent-plugin
/plugin install chdb@chdb-agent-plugin
# Codex CLI (v0.121+)
codex marketplace add chdb-io/chdb-agent-plugin
# Copilot CLI
copilot plugin marketplace add chdb-io/chdb-agent-plugin
# Droid
droid plugin marketplace add chdb-io/chdb-agent-plugin
What's inside
chdb-agent-plugin/
├── .claude-plugin/marketplace.json # Anthropic Skills marketplace catalog
├── .codex-plugin/plugin.json # OpenAI Codex Plugin Directory manifest
└── plugins/chdb/
├── plugin.json # Plugin metadata
├── AGENTS.md # Project-level agent instructions
├── skills/ # chdb-datastore + chdb-sql skills
└── mcp/ # bundled chdb-mcp server config
The packaged plugin gives agents:
chdb-sql— embedded ClickHouse SQL on parquet / csv / S3 / Postgres / MongoDB / ClickHouse Cloud / Iceberg / Delta Lake, with 1000+ functions (windowFunnel, geoToH3, JSON path ops, Session, parametrized queries) and cross-source joins vias3()/mysql()/postgresql()/iceberg()/deltaLake()/remoteSecure()table functions.chdb-datastore— pandas-API drop-in backed by the ClickHouse engine for DataFrame / parquet / csv / Arrow analytics with cross-source joins.chdb-mcp— MCP server exposing chDB query, file-attach, and remote ClickHouse Cloud federation tools.AGENTS.md— concise project-level instructions agents read at the start of every session.
Status
🚧 Initial scaffold. Skill content and MCP wiring will be synced from
chdb-io/chdb and
chdb-io/chdb-mcp in follow-up PRs.
License
Apache 2.0 — see LICENSE.
Stats
Version0.1.0
LanguagePython
Stars0
MaintenanceGood
LicenseApache-2.0
Last Commit
Added
Available In
