Open-source agentic data engineering harness.

100+ deterministic tools for SQL, lineage, dbt, FinOps, and warehouse connectivity. Works with Claude Code, Cursor, VS Code, and any MCP client. MIT licensed.

$npm install -g altimate-code

#1 on the leading agentic data benchmarks

ADE-Bench

dbt analytics-engineering tasks

78.0%altimate-code

altimate-code(DeepSeek V4 Pro)78%

Cortex Code CLI(Opus 4.6)65%

dbt Labs(Sonnet 4.5)59%

Claude Code(Sonnet 4.6 · baseline)40%

DAB Bench

multi-database agent tasks

63.2%altimate-code

altimate-code(GPT-5.5 + Sonnet 4.6)63.2%

MinusX(Sonnet 4.6 + GPT-5.5-mini + Haiku 4.5)63.1%

Spacedock (Recce)(Opus 4.6)57.7%

Pi Coding Agent(Opus 4.6)56%

100+ purpose-built, deterministic tools for data agents — SQL analysis, column-level lineage, dbt, FinOps, and warehouse connectivity.

Works with your data stack

Snowflake

BigQuery

Databricks

PostgreSQL

dbt

Airflow

GitHub

Redshift

MySQL

Jira

Linear

DuckDB

Dagster

Google Sheets

Snowflake

BigQuery

Databricks

PostgreSQL

dbt

Airflow

GitHub

Redshift

MySQL

Jira

Linear

DuckDB

Dagster

Google Sheets

Bring your own LLM

Anthropic

OpenAI

Google

AWS Bedrock

Azure

Ollama

OpenRouter

Mistral

Groq

xAI

Copilot

Anthropic

OpenAI

Google

AWS Bedrock

Azure

Ollama

OpenRouter

Mistral

Groq

xAI

Copilot

Why altimate-code

Everything your AI agent needs to work with data — built in.

Bring Your Own LLM

Works with Anthropic, OpenAI, Google, AWS Bedrock, Azure, Ollama, and 10+ more providers. No vendor lock-in.

Cross-Platform

Claude Code, Cursor, Windsurf, VS Code, and any MCP-compatible client. One install, everywhere.

100+ Deterministic Tools

SQL analysis, column-level lineage, dbt integration, FinOps, warehouse connectivity — no hallucinations.

Column-Level Lineage

Trace data flow across your entire warehouse — from source to mart, column by column.

FinOps & Cost Optimization

Identify expensive queries, get optimization recommendations, and track warehouse spend.

Data Governance

Built-in governance checks, policy enforcement, and compliance validation across your data stack.

See it in action

Real-world pipelines built end-to-end with a single prompt

US Home Sales Data Science Dashboard

$Download all available public US home sales data sets. Process and merge them into a unified format. Perform advanced data science — K-means, OLS regressions, and more. Build a single interactive dashboard.

Snowflake vs Databricks Benchmark

$Deploy the NovaMart platform to both Snowflake and Databricks, testing multiple warehouse sizes on each. Run the full data pipeline and benchmark queries, capturing execution time, credits/DBUs consumed, and bytes scanned.

NYC Taxi Coverage Dashboard

DuckDBdbtAirflow

$Take the New York City taxi cab public dataset, bring up a DuckDB instance, and build a dashboard showing areas of maximum coverage and lowest coverage. Set up a complete dbt project with staging, intermediate, and mart layers, and create an Airflow DAG to orchestrate the pipeline.

Olist E-Commerce Analytics Pipeline

$Build an end-to-end e-commerce analytics pipeline using the Olist Brazilian E-Commerce dataset. Use Azure Data Factory to ingest CSV files from Blob Storage into Snowflake raw tables, then orchestrate Snowflake stored procedures to transform data through raw → staging → mart layers.

Global CO2 & Climate Explorer

$Build me an interactive Global CO2 & Climate Explorer dashboard using DuckDB-WASM running entirely in the browser, sourcing data from Our World in Data’s CO2 dataset.

NYC Taxi Coverage Dashboard

Curious to know more? Check out the examples

Join the Community

altimate-code is built in the open. Get involved.

Open source. MIT licensed. One install.

Get Started Read the Docs GitHub