[{"data":1,"prerenderedAt":573},["ShallowReactive",2],{"project-39372159":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":29,"sentiment":30,"stance_mix":31,"scored_comments":36,"aspects":37,"strip":48,"post_text":50,"what":51,"said":90,"maker_in_thread":251,"shape":260,"grid":265,"attempts":534,"same_week":535,"maker_shows":40,"maker_hidden":565,"reader_version":566,"card":567},"39372159","Reor","An AI note-taking app that runs models locally","title","Show HN: Reor – An AI note-taking app that runs models locally","https:\u002F\u002Fgithub.com\u002Freorproject\u002Freor","github.com","samlhuillier",1707930052,2024,411,102,107,3515,4,"legend","productivity","note-taking app","desktop_app",[24,25,26,27,28],"local llm","note taking","rag","obsidian","vector search","mixed",-0.088,{"positive":32,"neutral":33,"mixed":34,"critical":35},13,21,3,19,56,{"design":38,"idea":41,"execution":43,"performance":46,"docs":47},{"positive":39,"critical":40},5,1,{"positive":42,"critical":39},7,{"positive":44,"critical":45},0,9,{"positive":40,"critical":18},{"positive":44,"critical":44},[39,44,44,39,44,44,44,40,44,39,34,40,49,40,44,34,44,34,34,40,39,34,34,40,40,40,34,40,34,40,49,40,39,40,34,40,39,34,39,49],2,"Reor is an open-source AI note-taking app that runs models locally.\n\nThe four main things to know are:\n\n1. Notes are connected automatically with vector search. You can do semantic search + related notes are automatically connected.\n\n2. You can do RAG Q&A on your notes using the local LLM of your choice.\n\n3. Embedding model, LLM, vector db and files are all run or stored locally.\n\n4. Point it to a directory of markdown files (like an Obsidian vault) and it works seamlessly alongside Obsidian.\n\nUnder the hood, Reor uses Llama.cpp (node-llama-cpp integration), Transformers.js and Lancedb to powe",{"problem":52,"audience":58,"pricing":66,"motivation":67,"time_to_build":66,"stack":74,"openness":87,"stage":88,"team_size":89},{"value":53,"source":54,"evidence":55},"Searching and connecting notes with AI while keeping data private and local","maker",[56],{"id":57},"post",{"value":59,"source":60,"evidence":61},"Note-takers who want private, local AI features, including Obsidian users","inferred",[62,63],{"id":57},{"id":64,"by":11,"text":65},"39373643","Thank you for your feedback! Working hard on improving the chunking to improve related notes section. RAG is fairly naive right now, with lots of improvements coming in the next…",null,{"value":68,"source":54,"evidence":69},"Support private, local AI for knowledge management",[70,71],{"id":57},{"id":72,"by":11,"text":73},"39374662","Thank you!",[75,79,83],{"value":76,"source":54,"evidence":77},"Llama.cpp via node-llama-cpp",[78],{"id":57},{"value":80,"source":54,"evidence":81},"Transformers.js",[82],{"id":57},{"value":84,"source":54,"evidence":85},"LanceDB",[86],{"id":57},"open_source","beta","unknown",{"praise":91,"objections":118,"requests":159,"questions":192,"alternatives":221},[92,107],{"value":93,"source":94,"evidence":95},"Local, private design and plain Markdown files","commenter",[96,100,104],{"id":97,"by":98,"text":99},"39373913","kepano","This is a good reminder of why storing Obsidian notes as individual Markdown files is much more useful than stuffing those notes in a database and having Markdown as an export…",{"id":101,"by":102,"text":103},"39374645","toddmorey","Yes it was one of the best product decisions y'all made. Been so useful to have direct access to the files and options on how my data is processed and backed up.",{"id":105,"by":102,"text":106},"39374626","\"crucially, that AI should run as much as possible privately & locally\" Just wanted to say thank you so much for this perspective and fighting the good fight.",{"value":108,"source":94,"evidence":109},"Useful project with good goals",[110,114],{"id":111,"by":112,"text":113},"39380035","dvorka","Rear is a really interesting project with admirable goals. I believe this is just the beginning, but you have already done a great job! I have been working on my note-taking…",{"id":115,"by":116,"text":117},"39372546","wbogusz","Great to see something like this actualized. I’m a huge fan of Obsidian and its graph based connections for note taking. Always see parallels drawn between Obsidian note…",[119,130,145,155],{"value":120,"source":94,"evidence":121},"Related-notes and RAG answers often weak or inaccurate",[122,126],{"id":123,"by":124,"text":125},"39373062","humbleferret","Great job! I played around with this on a couple of small knowledge bases using an open Hermes model I had downloaded. The “related notes” feature didn't provide much value in my…",{"id":127,"by":128,"text":129},"39372507","fastball","Does the future of knowledge management involve using lots of AI to organize pieces of knowledge? I think \"here be dragons\", and that over-relying on AI to do all your…",{"value":131,"source":94,"evidence":132},"Crashes and failures on several platforms",[133,137,141],{"id":134,"by":135,"text":136},"39375206","erickf1","I like the idea. Unfortunately, could not get it to work on Linux. Making a note caused a crash. Searching notes crashed. LLM chat would cause crash. Hope to see it work some time.",{"id":138,"by":139,"text":140},"39395117","yosito","Seems promising, but I couldn't get it to work at all. Seems like I'm not the only one having issues: https:\u002F\u002Fgithub.com\u002Freorproject\u002Freor\u002Fissues",{"id":142,"by":143,"text":144},"39376343","2024throwaway","Running with a Local LLM on a Mac M1, this completely locked up my system for minutes. I tried to let it run, because the progress bar was ticking every now and then, but after…",{"value":146,"source":94,"evidence":147},"Does not use GPU yet",[148,152],{"id":149,"by":150,"text":151},"39373755","gavmor","Seems cool, but didn't utilize my GPU? At any rate, definitely a futuristic POC, and prototype for the way I see desktop software going in the next few years.",{"id":153,"by":11,"text":154},"39373833","Yes unfortunately not implemented yet. Will be coming soon though :)",{"value":156,"source":94,"evidence":157},"Over-reliance on AI may harm thinking",[158],{"id":127,"by":128,"text":129},[160,170,178,185],{"value":161,"source":54,"evidence":162},"Multiple vaults",[163,167],{"id":164,"by":165,"text":166},"39373185","CrypticShift","Some suggestions : - Create multiple independent \"vaults\" (like obsidian). - Append links to related notes, so you can use (Obsidian's) graph view to map the AI connections. -…",{"id":168,"by":11,"text":169},"39374292","Thanks for your feedback! - Multiple vaults is in fact in a PR right now: https:\u002F\u002Fgithub.com\u002Freorproject\u002Freor\u002Fpull\u002F28 - Manual linking is coming. - Minimizing the UI to chat is…",{"value":171,"source":94,"evidence":172},"Support for PDFs and other formats",[173,174],{"id":164,"by":165,"text":166},{"id":175,"by":176,"text":177},"39374896","mrtesthah","It doesn't seem to view my plain text notes. What file formats are currently supported, if plain text is not?",{"value":179,"source":94,"evidence":180},"Hardware requirements in README",[181],{"id":182,"by":183,"text":184},"39381533","poulpy123","since LLM are computer intensive, you should add some hardware requirements in the README",{"value":186,"source":94,"evidence":187},"Mobile version",[188],{"id":189,"by":190,"text":191},"39378677","donclark","How would I use this as a mobile user?",[193,200,211],{"value":194,"source":94,"evidence":195},"Which local model works best",[196],{"id":197,"by":198,"text":199},"39377557","outside1234","Which local model works best for folks? Sort of intimidated by the large number of models on Hugging Face and it is hard to conceptualize which of the variants work the best. I…",{"value":201,"source":94,"evidence":202},"Can it import OneNote or Logseq notes safely",[203,207],{"id":204,"by":205,"text":206},"39372474","frankcort","Wow cool, can I import my One Note notebooks?!!??",{"id":208,"by":209,"text":210},"39380456","elcombato","I really like this idea and the app, but beware when using your existing logseq folder it will mess up the structure\u002Findentation\u002Fbullet-points of the notes.",{"value":212,"source":94,"evidence":213},"Does it work with existing Obsidian vaults",[214,218],{"id":215,"by":216,"text":217},"39372819","SamBam","So if I point this at my existing Obsidian library, what happens? Does this add to existing files, or add new files, to store the output of things generated by the AI? Doe the…",{"id":219,"by":11,"text":220},"39372923","It's filesystem mapping 1:1. Basically the same thing Obsidian does when you open a vault. You can create new files with Reor, create directories and edit existing files.…",[222,230,237,244],{"value":223,"source":94,"evidence":224},"Obsidian",[225,226],{"id":123,"by":124,"text":125},{"id":227,"by":228,"text":229},"39372630","dkarras","I had been researching stuff related to this for some time. Interesting project! Why not an obsidian plugin to tap into the ecosystem?",{"value":231,"source":94,"evidence":232},"Obsidian Smart Connections",[233],{"id":234,"by":235,"text":236},"39373501","mcbetz","Interesting project, wishing you all the best! If you are using Obsidian, Smart Connections in v2 (1) does also support local embeddings and shows related notes based on semantic…",{"value":238,"source":94,"evidence":239},"Logseq",[240],{"id":241,"by":242,"text":243},"39377725","iansinnott","Not OP but Obsidian (as mentioned) and Logseq are both good options.",{"value":245,"source":94,"evidence":246},"Joplin",[247],{"id":248,"by":249,"text":250},"39375119","Ringz","That was the reason why I gave up Joplin very quickly. The last Joplin thread, here on Hacker News, has also shown once again that some still do not understand why \"But Joplin…",{"comments":252,"answered":253,"key":254},14,10,[255,258,259],{"id":256,"text":257},"39373977","Absolutely! Really respect the work you folks are doing.",{"id":72,"text":73},{"id":64,"text":65},{"commenters":261,"max_depth":262,"maker_replies":252,"first_comment_mins":263,"lifespan_hours":264},71,6,23,127,[266,268,270,274,276,280,282,284,286,287,288,292,295,296,299,301,304,307,310,313,317,320,323,326,329,331,332,334,336,340,344,346,350,352,353,356,360,363,366,368,371,373,376,379,382,383,385,389,393,396,398,401,402,405,407,410,414,415,418,420,423,426,430,432,434,438,441,443,446,449,450,454,456,459,461,462,464,467,469,472,473,476,478,481,484,486,488,490,493,497,499,503,506,509,512,514,518,521,523,526,529,532],[97,44,39,267,98,44],"project\u002Fpositive\u002Fdesign",[256,44,44,269,11,40],"maker\u002Fpositive\u002Fnone",[271,44,44,272,273,44],"39374611","commenter\u002Fneutral\u002Fnone","michaelmior",[275,44,44,272,98,44],"39374694",[277,44,44,278,279,44],"39377722","commenter\u002Fneutral\u002Fprivacy","dietr1ch",[281,44,44,272,273,44],"39386483",[283,44,44,272,98,44],"39389095",[285,44,44,272,273,44],"39397885",[101,44,39,267,102,44],[248,44,39,267,249,44],[289,44,44,290,291,44],"39375158","other\u002Fneutral\u002Fnone","traverseda",[293,44,44,290,294,44],"39376116","erybodyknows",[241,44,44,290,242,44],[297,44,44,290,298,44],"39379895","msravi",[300,44,44,290,249,44],"39380307",[302,44,44,290,303,44],"39380630","mjochim",[305,44,44,290,306,44],"39393361","__rito__",[308,44,44,290,309,44],"39436505","lobocinza",[311,44,44,290,312,44],"39376004","xenodium",[314,44,40,315,316,44],"39378127","project\u002Fcritical\u002Fdesign","pokstad",[318,44,44,272,319,44],"39379400","lannisterstark",[321,44,44,272,322,44],"39380212","TeMPOraL",[324,44,44,272,325,44],"39379573","snthpy",[327,44,39,267,328,44],"39382468","pipnonsense",[105,40,39,330,102,44],"maker\u002Fpositive\u002Fidea",[72,40,44,269,11,40],[123,49,34,333,124,44],"project\u002Fmixed\u002Fexecution",[64,49,44,335,11,40],"maker\u002Fneutral\u002Fexecution",[337,49,40,338,339,44],"39377106","project\u002Fcritical\u002Fexecution","monkmartinez",[341,49,34,342,343,44],"39378344","project\u002Fneutral\u002Fperformance","ilaksh",[345,49,34,342,124,44],"39382515",[347,49,40,348,349,44],"39381679","project\u002Fcritical\u002Fidea","dax_",[234,34,34,351,235,44],"project\u002Fneutral\u002Fidea",[127,18,40,348,128,44],[354,18,44,355,11,40],"39372880","maker\u002Fneutral\u002Fidea",[357,18,44,358,359,44],"39373005","commenter\u002Fneutral\u002Fidea","bhpm",[361,18,44,272,362,44],"39373901","OJFord",[364,18,44,272,365,44],"39374063","davidy123",[367,18,44,358,128,44],"39378237",[369,18,34,351,370,44],"39373906","ParetoOptimal",[372,18,44,358,128,44],"39378220",[374,18,44,272,375,44],"39380068","hgomersall",[377,18,44,290,378,44],"39385212","turnsout",[380,18,34,351,381,44],"39381959","GTP",[164,39,34,351,165,44],[168,39,44,384,11,40],"maker\u002Fneutral\u002Fnone",[386,39,40,387,388,44],"39382739","project\u002Fcritical\u002Fperformance","zarathustreal",[390,262,39,391,392,44],"39376546","project\u002Fpositive\u002Fidea","haswell",[394,262,40,348,395,44],"39376857","sofixa",[397,262,44,272,392,44],"39377373",[399,262,44,290,400,44],"39380033","WildGreenLeave",[115,42,39,391,116,44],[403,404,39,391,365,44],"39374094",8,[406,404,44,384,11,40],"39374309",[408,404,44,290,409,44],"39380268","jddj",[411,45,34,412,413,44],"39374695","project\u002Fmixed\u002Fdesign","nerdjon",[197,253,34,342,198,44],[416,253,44,290,417,44],"39390351","stuartriffle",[208,419,40,338,209,44],11,[421,419,40,338,422,44],"39388372","syncbehind",[424,419,44,272,425,44],"39409190","nerdyadventurer",[427,428,40,348,429,44],"39374049",12,"bemusedthrow75",[431,428,44,358,291,44],"39374130",[433,428,44,272,429,44],"39383792",[435,32,34,436,437,44],"39377987","project\u002Fneutral\u002Fnone","dev_tty01",[439,252,40,338,440,44],"39376093","rcarmo",[442,252,40,338,440,44],"39380567",[111,444,39,445,112,44],15,"project\u002Fpositive\u002Fperformance",[215,447,34,448,216,44],16,"project\u002Fneutral\u002Fexecution",[219,447,44,335,11,40],[451,452,40,338,453,44],"39403927",17,"kingkongjaffa",[227,455,34,351,228,44],18,[457,455,34,351,458,44],"39372807","cfcfcf",[460,455,44,355,11,40],"39372996",[138,35,40,338,139,44],[142,463,40,387,143,44],20,[465,463,34,342,466,44],"39376416","tarruda",[468,463,40,387,143,44],"39376522",[470,463,34,342,471,44],"39381868","raxxorraxor",[134,33,40,338,135,44],[149,474,34,475,150,44],22,"project\u002Fmixed\u002Fperformance",[153,474,44,477,11,40],"maker\u002Fneutral\u002Fperformance",[479,263,39,267,480,44],"39372436","calebdre",[482,263,44,483,11,40],"39372652","maker\u002Fpositive\u002Fdesign",[485,263,34,355,480,44],"39372895",[175,487,40,338,176,44],24,[489,487,44,448,11,40],"39430696",[182,491,34,492,183,44],25,"project\u002Fneutral\u002Fdocs",[494,495,34,436,496,44],"39378013",26,"nextaccountic",[498,495,44,384,11,40],"39430689",[500,501,40,348,502,44],"39379683",27,"sigmonsays",[504,501,39,391,505,44],"39379759","infectoid",[507,501,39,391,508,44],"39382585","PeterisP",[510,511,34,351,190,44],"39378692",28,[513,511,44,384,11,40],"39430692",[515,516,34,342,517,44],"39376294",29,"lenerdenator",[519,516,34,342,520,44],"39376320","alsetmusic",[204,522,39,391,205,44],30,[524,522,44,525,11,40],"39372685","maker\u002Fneutral\u002Fdocs",[527,522,34,492,528,44],"39373280","clscott",[189,530,34,531,190,44],31,"project\u002Fneutral\u002Fdesign",[533,530,40,387,508,44],"39382595",[],[536,541,546,551,556,560],{"id":537,"name":538,"points":539,"category":540},"39339249","Bitwise Liminal",450,"creative",{"id":542,"name":543,"points":544,"category":545},"39333309","SimpleKVM",397,"infrastructure",{"id":547,"name":548,"points":549,"category":550},"39365135","Athena Crisis",276,"games",{"id":552,"name":553,"points":554,"category":555},"39304068","traderjoes",274,"data",{"id":557,"name":558,"points":559,"category":540},"39314153","CueCam Presenter",246,{"id":561,"name":562,"points":563,"category":564},"39331383","Keyboard Connect",224,"learning_science",false,"v2",{"id":568,"name":5,"line":6,"ai":565,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":569,"top":18,"kw":570,"maker":11,"domain":10,"tier":19,"attempts":44,"strip":571,"url":9,"mix":572,"praise":93,"objection":120,"sub":21},39372159,-0.09,[24,25,26,27,28],"5005000105312103033153311131312151315352",[32,33,34,35],1794036649692]