[{"data":1,"prerenderedAt":258},["ShallowReactive",2],{"project-47985077":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":41,"post_text":43,"what":44,"said":83,"maker_in_thread":154,"shape":164,"grid":168,"attempts":211,"same_week":220,"maker_shows":249,"maker_hidden":250,"reader_version":251,"card":252},"47985077","Mljar Studio","local AI data analyst that saves analysis as notebooks","title","Show HN: Mljar Studio – local AI data analyst that saves analysis as notebooks","https:\u002F\u002Fmljar.com\u002F","mljar.com","pplonski86",1777717291,2026,73,18,913,4366,21,"notable","ai","ai data analyst","desktop_app",[21,24,25,26,27],"automl","local llm","jupyter notebook","tabular data","roasted",-0.417,{"positive":31,"neutral":32,"mixed":33,"critical":34},0,2,1,4,7,{"idea":37,"design":38,"execution":39,"privacy":40},{"positive":31,"critical":32},{"positive":31,"critical":33},{"positive":31,"critical":33},{"positive":31,"critical":31},[33,31,42,31,33,31,42,31,31,31,33,31,33,42,31,31,31,31,31],3,"Hi HN,\n\nI’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.\n\nThe 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.\n\nWhat MLJAR Studio does:\n\n- Sets up a local Python environment automatically, runs on Mac, Windows, and Linux\n\n- Installs missing packages during ",{"problem":45,"audience":51,"pricing":60,"motivation":64,"time_to_build":68,"stack":69,"openness":82,"stage":82,"team_size":82},{"value":46,"source":47,"evidence":48},"Analyzing data via natural language without losing a reproducible workflow","maker",[49],{"id":50},"post",{"value":52,"source":47,"evidence":53},"People with domain knowledge but limited programming skills",[54,57],{"id":55,"by":11,"text":56},"48005925","The goal of MLJAR Studio is to make it easy to analyze data for people with large domain knowledge but lack of programming skills. We do not focus on notebooks. Python notebook…",{"id":58,"by":11,"text":59},"48005953","Thanks for sharing! MLJAR Studio was created for people with domain knowledge but not much technical expertise. For them, setting up a Python environment, installing required…",{"value":61,"source":47,"evidence":62},"$199 one-time with 7-day trial",[63],{"id":50},{"value":65,"source":47,"evidence":66},"Wanted something between Jupyter and AI code tools that preserves workflow",[67],{"id":50},null,[70,74,78],{"value":71,"source":47,"evidence":72},"Python",[73],{"id":50},{"value":75,"source":47,"evidence":76},"Ollama",[77],{"id":50},{"value":79,"source":47,"evidence":80},"OpenAI",[81],{"id":50},"unknown",{"praise":84,"objections":85,"requests":122,"questions":123,"alternatives":135},[],[86,98,109,115],{"value":87,"source":88,"evidence":89},"Notebooks are not reproducible, so the format doesn't solve reproducibility","commenter",[90,94],{"id":91,"by":92,"text":93},"47986712","MSaiRam10","Notebooks as the output format is funny because notebooks are famously bad for reproducibility. Out of order execution, hidden state, etc. You're solving \"chat isn't…",{"id":95,"by":96,"text":97},"48008345","trymamboapp","\"AI saves analysis as notebooks\" is fighting the wrong fight ig. The reproducibility issue with notebooks isn't the format. it's out-of-order cell execution and silent kernel…",{"value":99,"source":88,"evidence":100},"Human-in-the-loop checking of AI-generated code is hard",[101,105],{"id":102,"by":103,"text":104},"47985192","2ndorderthought","This is one of those product areas I would call high-risk without a human in the loop. So I am glad you kept a person in the loop. It's really easy to lose tons of money making…",{"id":106,"by":107,"text":108},"47988381","arriemeijer","My guess is you can't. the best you can do is show them the code and hope they catch mistakes. Data scientists who can't read code probably shouldn't be running AI generated…",{"value":110,"source":88,"evidence":111},"Price of $200 is hard to justify when local models are free to run",[112],{"id":113,"by":103,"text":114},"47986424","Not the op or affiliated but. You really shouldn't and often cannot legally send off data or information about data to 3rd parties. Maybe schemas are okay but 1 mistake and your…",{"value":116,"source":88,"evidence":117},"Product may be easily replicated with Claude Code",[118],{"id":119,"by":120,"text":121},"47985672","estetlinus","This is one shot with Claude Code. What’s the moat?",[],[124,131],{"value":125,"source":88,"evidence":126},"How does it compare to open source Deepnote?",[127],{"id":128,"by":129,"text":130},"47986873","hasyimibhar","How does this compare to open source Deepnote[0]? We use the hosted version at my previous company to replace self-hosted Jupyter notebooks, and it's pretty great. [0]…",{"value":132,"source":88,"evidence":133},"What is the moat?",[134],{"id":119,"by":120,"text":121},[136,140,147],{"value":137,"source":88,"evidence":138},"Deepnote",[139],{"id":128,"by":129,"text":130},{"value":141,"source":88,"evidence":142},"Jupyter MCP Server with Claude",[143],{"id":144,"by":145,"text":146},"47985755","amirathi","Really cool. If somebody doesn't want to adopt a new platform, take a look at open source Jupyter MCP Server[1]. Once integrated with Claude, it can execute code on the live…",{"value":148,"source":88,"evidence":149},"marimo notebooks",[150],{"id":151,"by":152,"text":153},"47987662","msp26","I like starting most of my projects on marimo notebooks now and slowly moving parts of it to the main codebase + db. By the end of it I might remove the notebook entirely but…",{"comments":155,"answered":32,"key":156},6,[157,160,161],{"id":158,"text":159},"48005848","Python notebooks are not reproducible when used by humans. When notebook format is used to store conversations for AI data analysis, it preserves the chat history and is ideal…",{"id":55,"text":56},{"id":162,"text":163},"48019076","Thank you! I will check them out. It is worth to mention that MLJAR Studio is a desktop application, which is easy to install. It is running locally, and support local LLMs so…",{"commenters":165,"max_depth":34,"maker_replies":155,"first_comment_mins":166,"lifespan_hours":167},12,19,69,[169,171,173,175,177,180,182,184,186,188,189,191,194,196,198,200,203,204,207],[91,31,33,170,92,31],"project\u002Fcritical\u002Fidea",[158,31,31,172,11,33],"commenter\u002Fneutral\u002Fidea",[128,33,42,174,129,31],"project\u002Fneutral\u002Fnone",[55,33,31,176,11,33],"maker\u002Fneutral\u002Fidea",[178,33,33,179,129,31],"48017452","project\u002Fcritical\u002Fdesign",[162,33,31,181,11,33],"maker\u002Fneutral\u002Fdesign",[102,32,42,183,103,31],"project\u002Fneutral\u002Fidea",[185,32,31,176,11,33],"48006062",[144,42,31,187,145,31],"other\u002Fneutral\u002Fnone",[58,42,31,176,11,33],[95,34,33,190,96,31],"project\u002Fcritical\u002Fexecution",[192,34,31,193,11,33],"48009070","maker\u002Fneutral\u002Fexecution",[119,195,33,170,120,31],5,[113,195,42,197,103,31],"project\u002Fmixed\u002Fprivacy",[106,195,31,199,107,31],"commenter\u002Fcritical\u002Fidea",[201,155,31,187,202,31],"47986566","jiggunjer",[151,155,31,187,152,31],[205,35,31,187,206,31],"47987630","HollowRidge427",[208,35,31,209,210,31],"47987654","other\u002Fcritical\u002Fdesign","amarcheschi",[212,215,219],{"id":213,"t":214,"points":32,"comments":31},"13302699",1483378445,{"id":216,"t":217,"points":218,"comments":166},"19672217",1555406310,51,{"id":4,"t":12,"points":14,"comments":15},[221,226,231,235,240,244],{"id":222,"name":223,"points":224,"category":225},"47972511","WhatCable",566,"hardware",{"id":227,"name":228,"points":229,"category":230},"48038257","Hallucinopedia",317,"creative",{"id":232,"name":233,"points":234,"category":230},"48026342","PaletteInspiration",215,{"id":236,"name":237,"points":238,"category":239},"48037724","Tilde.run",205,"dev_tools",{"id":241,"name":242,"points":243,"category":20},"47995037","ml-sharp-web",185,{"id":245,"name":246,"points":247,"category":248},"48038019","Templatical",169,"productivity",14,false,"v2",{"id":253,"name":5,"line":6,"ai":250,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":254,"top":18,"kw":255,"maker":11,"domain":10,"tier":19,"attempts":42,"strip":256,"url":9,"mix":257,"praise":-1,"objection":87,"sub":21},47985077,-0.42,[21,24,25,26,27],"1030103000101300000",[31,32,33,34],1794036700261]