Mljar Studio
local AI data analyst that saves analysis as notebooks
Details
- External ID
- 47985077
- Source
- HN
- Company
- —
- Product
- Mljar Studio
- Website domain
- mljar.com
- Launched
- May 2, 2026
- Cohort
- —
- Upvotes
- 73
- Upvotes percentile
- 0.8715670436187399
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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 conversation becomes a reproducible notebook (*.ipynb file). So instead of just chatting with data, you end up with something you can inspect, modify, and rerun.What MLJAR Studio does:- Sets up a local Python environment automatically, runs on Mac, Windows, and Linux- Installs missing packages during the conversation- Built-in AutoML for tabular data (classification, regression, multiclass)- Works with standard Python libraries (pandas, matplotlib, etc.)- Works with any data file: CSV, Excel, Stata, Parquet ...- Connects to PostgreSQL, MySQL, SQL Server, Snowflake, Databricks, and Supabase.For AI: use Ollama locally (zero data egress), bring your own OpenAI key, or use MLJAR AI add-on.I built this because I wanted something between Jupyter Notebook (flexible but manual) and AI tools that generate code but don’t preserve the workflow. Most tools I tried either hide too much or don’t give reproducible results and are cloud basedDemos:- 60-second demo: https://youtu.be/BjxpZYRiY4c- Full 3-minute analysis: https://youtu.be/1DHMMxaNJxIPricing is $199 one-time, with a 7-day trial.Curious if this is useful for others doing real data work, or if I’m solving my own problem here.Happy to answer questions.
Enrichment
- Theme
- database infrastructure and developer tools
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- B2C
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- local ai data analyst
- Manually corrected
- False
Could you build this?
Partial While the Electron/React desktop UI and LLM chat wrapper are easily vibe-coded, the underlying tabular AutoML engine (mljar-supervised) involves years of specialized ML research and algorithmic engineering.
What it would actually take: Desktop wrapper built on Electron or Tauri communicating with a local Python runtime executing Jupyter/IPython kernels and the `mljar-supervised` library. The hard part is the AutoML engine itself: ensemble algorithms, stacking, feature engineering heuristics, and robust hyperparameter search pipelines. Requires machine learning systems expertise and data science engineering to reproduce reliably.
Discussion
18 comments analyzed.
Competitors mentioned: Deepnote (cloud notebooks), Jupyter MCP Server (open source), marimo notebooks, Claude Code
Concerns raised: Notebooks aren't reproducible (out-of-order execution, hidden state), High-risk decisions without expert code review; LLM hallucination mistakes, Data scientists may lack skills to verify AI-generated analysis safely, Pricing ($200 USD) not justified vs. free local model alternatives, Data privacy/legal risks sending data to third parties
Feature requests: Better mechanisms to prevent mistakes when LLMs hallucinate, Support for code inspection without requiring expert code review skills
Competitors
Other products that read as similar to this one — 65 launches clear the similarity bar, closest 8 shown.
Attention rank: #7 of 66 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 180 days after the earliest competitor.
- I built a local data lake for AI powered data engineering and analytics · hn · 2026-04-08 · 14 upvotes · similarity 0.52
- MyMlLab · ph · 2026-09-12 · 1 upvotes · similarity 0.47
- Data Studio · hn · 2026-02-17 · 28 upvotes · similarity 0.47
- Tracecast · hn · 2026-05-18 · 6 upvotes · similarity 0.42
- AI Synthetic Data Studio · ph · 2026-09-25 · 1 upvotes · similarity 0.41
- Open source ML programming language playground · hn · 2026-09-02 · 11 upvotes · similarity 0.41
- FluentDB · ph · 2026-07-25 · 275 upvotes · similarity 0.41
- Quokka · ph · 2026-09-19 · 1 upvotes · similarity 0.41
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.