Show HN: Mljar Studio – local AI data analyst that saves analysis as notebooks
Local AI data analyst that keeps your data private and your workflow reproducible. MLJAR Studio turns chat-with-data into auditable Jupyter notebooks.
Why it matters
A developer shipped a product that bridges the gap between manual data analysis (Jupyter) and black-box AI tools—solving the reproducibility problem that plagues enterprise AI workflows. This matters for teams that need audit trails and data sovereignty.
The key facts
16 to knowLocal execution with Ollama (zero data egress option)
Converts natural language queries into executable Python code + Jupyter notebooks
Built-in AutoML for tabular data (classification, regression, multiclass)
Supports 6 database connectors: PostgreSQL, MySQL, SQL Server, Snowflake, Databricks, Supabase
Works with CSV, Excel, Stata, Parquet file formats
$199 one-time pricing with 7-day trial
Cross-platform: Mac, Windows, Linux
Automatic package installation during conversation
Creator built on top of open-source mljar-supervised AutoML library
Product: Desktop app (Mac, Windows, Linux) for natural language data analysis
Local execution with Ollama, or BYO OpenAI key, or MLJAR AI add-on
Database connectors: PostgreSQL, MySQL, SQL Server, Snowflake, Databricks, Supabase
Output: Reproducible Jupyter notebooks (*.ipynb)
Pricing: $199 one-time with 7-day trial
Positioning: Alternative to Jupyter (manual) and cloud-based AI tools (opaque)
Status: Show HN launch (early traction: 11 points, 1 comment as of publish)
Go to the source
Hacker Newsmljar.com
Publisher excerpt: Hi HN, I’ve been working on mljar-supervised (open-source AutoML for tabular data) for a few years. Recently I built a desktop app around it called MLJAR Studio. The idea is simple: you talk to your data in natural language, the AI generates Python code, executes it locally, and the whole…