Open source · Apache-2.0

Better Claude Code for data engineers.

Everything you love about Claude Code, skills, MCP, self-evolving memory, rebuilt for the data stack. Model-neutral, governed, and wired into your warehouse from the first command.

Quickstart View on GitHub Read the docs

Claude Code parity

All of Claude Code's power, in your data terminal.

Datus CLI keeps the general agent capabilities you already rely on, and adds nothing you have to relearn.

Self-evolving agent

Skills, knowledge, and memory that iterate on their own, every run sharpens the next.

Knowledge base

MCP & Skills, in full

Complete support for the MCP ecosystem and the Skill system. Bring any tool, ship any skill.

MCP Skills

IM Gateway

Drive the agent from where your team already works, Slack and Lark channel integration built in.

IM Gateway

Where Datus goes further · 01

Model-neutral by design.

Not locked to one vendor. Route each subagent to the model that fits its job, or run an all-Claude lineup. See the full supported-models list in the docs.

Supported models

Subagent

Model

Why

extract_knowledge · feedback

DeepSeek

Long context, low cost

complex ETL tasks

GPT-5.5

Strongest coding

ask_metrics subagents

Gemini 3 Flash

Blazing fast, cheap

30%

of the cost

90%

of the quality

50%

faster

Prefer one family? Mix Claude Haiku, Sonnet, Opus, and Fable across the same agents, your call.

Where Datus goes further · 02

Guardrails the data stack actually needs.

Agents touch production data. Datus puts three layers of real control between the model and your warehouse.

Tool permission modes

How much power the agent gets, set per session or per subagent:

normalRead-onlyExplore, query, and plan. Nothing gets written.

autoEditingEdits and ships within its lane, no prompt per step.

dangerousData sandboxFull-power operations, contained to a sandbox.

Reference

Query-time scoping

What a subagent can see at run time, scope it down to just:

MetricsOnly the metric definitions in play

Reference SQLCurated example queries to learn from

Reference templatesReusable, vetted query templates

TablesThe exact tables it's allowed to read

Customized subagents

Data access policy

Enforced outside the model, on every query the agent runs:

Row access policyFilter rows by role, team, or tenant

Column masking policyMask sensitive columns before they reach the model

SQL-injection detection & blockUnsafe SQL is caught and stopped

Audit trailEvery query logged and reviewable

SQL policy

Where Datus goes further · 03

Built for the big-data ecosystem.

Warehouses, semantic layers, schedulers, BI, Datus plugs into the stack you already run, and its built-in skills and subagents cover the whole development lifecycle.

Connect your stack

Snowflake, Databricks, StarRocks, ClickHouse, MetricFlow, Airflow, Superset, Grafana, and more.

Full-lifecycle skills

Built-in skills and subagents take you from exploration to metrics to production ETL, end to end.

One evolving context

Schemas, semantics, and validated SQL captured into portable memory that powers every integration.

Browse all integrations

Fine, we know you still love Claude Code, you can use datus-mcp right inside it. Learn how ↗

Start with the open-source CLI.

Free, Apache-2.0, your data and model. Five minutes from install to your first validated query.

Quickstart View on GitHub

Bring your own warehouse & model