[{"data":1,"prerenderedAt":469},["ShallowReactive",2],{"project-41457633":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":47,"post_text":48,"what":49,"said":81,"maker_in_thread":210,"shape":223,"grid":228,"attempts":432,"same_week":433,"maker_shows":33,"maker_hidden":461,"reader_version":462,"card":463},"41457633","AnythingLLM","Open-Source, All-in-One Desktop AI Assistant","title","Show HN: AnythingLLM – Open-Source, All-in-One Desktop AI Assistant","https:\u002F\u002Fgithub.com\u002FMintplex-Labs\u002Fanything-llm","github.com","tcarambat1010",1725550845,2024,368,77,132,3515,4,"legend","ai","desktop ai assistant","desktop_app",[24,25,26,27],"rag","local llm","chat with docs","vector database","curious",0.246,{"positive":31,"neutral":32,"mixed":33,"critical":34},13,22,2,3,40,{"idea":37,"docs":39,"execution":41,"design":42,"pricing":44,"privacy":45,"performance":46},{"positive":18,"critical":38},0,{"positive":40,"critical":38},1,{"positive":38,"critical":33},{"positive":43,"critical":38},5,{"positive":38,"critical":38},{"positive":38,"critical":40},{"positive":38,"critical":38},[43,34,38,38,43,34,34,34,34,43,38,38,38,38,38,38,38,38,43,43,38,40,43,43,34,34,34,34,40,34,34,34,43,43,34,34,38,34,34,43],"Hey HN!\n\nThis is Tim from AnythingLLM (https:\u002F\u002Fgithub.com\u002FMintplex-Labs\u002Fanything-llm). AnythingLLM is an open-source desktop assistant that brings together RAG (Retrieval-Augmented Generation), agents, embeddings, vector databases, and more—all in one seamless package.\n\nWe built AnythingLLM over the last year iterating and iterating from user feedback. Our primary mission is to enable people with a layperson understanding of AI to be able to use AI with little to no setup for either themselves, their jobs, or just to try out using AI as an assistant but with *privacy by default*.\n\nFrom these i",{"problem":50,"audience":56,"pricing":64,"motivation":72,"time_to_build":76,"stack":77,"openness":78,"stage":79,"team_size":80},{"value":51,"source":52,"evidence":53},"Lets non-experts use LLMs with little setup while keeping data private on their device","maker",[54],{"id":55},"post",{"value":57,"source":52,"evidence":58},"Laypeople, individual users, and organizations wanting private AI assistants",[59,60],{"id":55},{"id":61,"by":62,"text":63},"41466050","hm-nah","I’ve been attempting to deploy a customized AnythingLLM instance within an enterprise env. TimC (and presumably dev crew) are top notch and very responsive. Waiting for EntraID…",{"value":65,"source":66,"evidence":67},"Open source; a hosted plan at $50\u002Fmo was mentioned by a commenter","commenter",[68],{"id":69,"by":70,"text":71},"41461974","indigodaddy","Question on the anythingllm hosted. So is the $50\u002Fmo just basically you are logging into some sort of Remote Desktop environment and run an anythingllm instance from there that…",{"value":73,"source":52,"evidence":74},"Make AI usable by people without coding or Docker skills, with privacy by default",[75],{"id":55},null,[],"open_source","launched","team",{"praise":82,"objections":112,"requests":134,"questions":167,"alternatives":193},[83,97,108],{"value":84,"source":66,"evidence":85},"Easy setup and polished desktop install",[86,90,94],{"id":87,"by":88,"text":89},"41459033","A4ET8a8uTh0","This definitely makes it super easy for less technical folks to access it ( got it up and running in less than 5 minutes ). Initial reaction is positive with just Ollama.…",{"id":91,"by":92,"text":93},"41457970","phren0logy","I have been really impressed with AnythingLLM as a no-fuss way to use LLMs locally and via APIs. For those of us who want to tinker, there's a solid range of choice for embedders…",{"id":95,"by":92,"text":96},"41459810","I had a much smoother experience with the desktop version of AnythingLLM. There's more in openwebui, but the things that are in AnythingLLM are more polished (IMO).",{"value":98,"source":66,"evidence":99},"Supports many embedders, vector stores and providers",[100,104,105],{"id":101,"by":102,"text":103},"41459153","md3911027514","this is super sweet for developers (or anyone else) who like to have granular control over their LLM set up - ability to edit system prompt - ability to change LLM temperature -…",{"id":91,"by":92,"text":93},{"id":106,"by":11,"text":107},"41459284","You can use LiteLLM _as the LLM provider_ which is just a relay to a ton of other models. For people who already have it set up connecting to x,y,z providers can keep that work…",{"value":109,"source":66,"evidence":110},"Responsive maker and useful for enterprise deployment",[111],{"id":61,"by":62,"text":63},[113,120,127],{"value":114,"source":66,"evidence":115},"Citations window shows garbled content",[116],{"id":117,"by":118,"text":119},"41458374","hannofcart","Downloaded and checked it out. Looks great so far. Tried using it to read a bunch of regulatory PDFs using GPT-4o. Some quick and early feedback: 1. The citations seem to be a…",{"value":121,"source":66,"evidence":122},"Docker image pull timed out for one user",[123],{"id":124,"by":125,"text":126},"41458731","ranger_danger","$ docker pull mintplexlabs\u002Fanythingllm Using default tag: latest Error response from daemon: Get \"https:\u002F\u002Fregistry-1.docker.io\u002Fv2\u002F\": net\u002Fhttp: request canceled while waiting for…",{"value":128,"source":66,"evidence":129},"Unclear how privacy by default holds when cloud models are offered",[130],{"id":131,"by":132,"text":133},"41457902","vednig","How do you ensure \"privacy by default\" if you are also providing cloud models?",[135,139,149,160],{"value":136,"source":66,"evidence":137},"Search within existing chat history",[138],{"id":117,"by":118,"text":119},{"value":140,"source":66,"evidence":141},"Keyboard shortcuts and desktop launcher",[142,146],{"id":143,"by":144,"text":145},"41458633","philipjoubert","This looks really great. Are you planning on adding shortcut keys anytime soon?",{"id":147,"by":11,"text":148},"41459346","We actually are planning to really lean into the \"Desktop assistant\" style of things, so yes absolutely. Like how on Mac you can cmd+space to launch spotlight, we can offer the…",{"value":150,"source":66,"evidence":151},"Custom CSS support",[152,156],{"id":153,"by":154,"text":155},"41464645","fl_rn_st","What a coincidence, I just setup AnythingLLM yesterday for trying it on an enterprise level. I'm super impressed with most of the stuff I used so far. I just wish there was an…",{"id":157,"by":158,"text":159},"41467774","db3d","+1 on custom CSS overwrites. A bigger feature that would add a lot of value might also be a prompt manager with a shareable prompt list.",{"value":161,"source":66,"evidence":162},"Home Assistant or Alexa integration",[163],{"id":164,"by":165,"text":166},"41461466","conception","Can this roll into home assistant and provide alexa at home in any capacity?",[168,178,182],{"value":169,"source":66,"evidence":170},"What hardware is needed to run it",[171,175],{"id":172,"by":173,"text":174},"41457974","anonymous344","what kind of pc does it need ? ram, etc?",{"id":176,"by":11,"text":177},"41459336","Depends on the model you want to run! That is the beauty of it. If you can muster that ability to run a Q4 Llama3.1 8B - great, if your specs are really low end you can always…",{"value":179,"source":66,"evidence":180},"How the hosted plan works and whether it has GPU access",[181],{"id":69,"by":70,"text":71},{"value":183,"source":66,"evidence":184},"How it differs from Open WebUI and Chatbox",[185,189],{"id":186,"by":187,"text":188},"41458151","candiddevmike","Have you tried openwebui? What are your thoughts on it vs this?",{"id":190,"by":191,"text":192},"41458506","santamex","How does this differ from chatboxai? https:\u002F\u002Fgithub.com\u002FBin-Huang\u002Fchatbox",[194,198,206],{"value":195,"source":66,"evidence":196},"Open WebUI",[197],{"id":186,"by":187,"text":188},{"value":199,"source":66,"evidence":200},"Chatbox",[201,202],{"id":190,"by":191,"text":192},{"id":203,"by":204,"text":205},"41458749","Ringz","Chatboxai is a client for multiple AIs like OpenAi, Cloude, etc. It does not work on your local files and documents.",{"value":207,"source":66,"evidence":208},"Ollama",[209],{"id":87,"by":88,"text":89},{"comments":211,"answered":212,"key":213},10,6,[214,217,220],{"id":215,"text":216},"41459257","It was a typo haha, someone just PR'd the fix for it. God knows how long it has been there - whoops",{"id":218,"text":219},"41459267","It was indeed a brainfart on my end that has then been in there since the dawn of time. Pretty funny honestly",{"id":221,"text":222},"41459971","That's the point! Shouldn't have to know and naturally over time you'll learn more and the controls are there when you feel comfortable tuning them",{"commenters":224,"max_depth":225,"maker_replies":211,"first_comment_mins":226,"lifespan_hours":227},55,7,17,98,[229,233,237,241,244,247,249,253,257,259,260,264,267,269,273,276,278,281,285,287,290,293,296,299,302,304,307,310,312,314,316,318,321,324,327,330,331,332,336,339,341,345,347,349,351,352,354,357,359,362,365,368,372,373,375,377,379,381,383,387,389,390,393,395,398,399,401,402,405,408,412,415,419,421,424,425,427],[230,38,43,231,232,38],"41459226","project\u002Fpositive\u002Fidea","DebtDeflation",[234,40,34,235,236,38],"41458463","project\u002Fneutral\u002Fdocs","furyofantares",[238,40,38,239,240,38],"41458494","commenter\u002Fneutral\u002Fnone","mattygee",[242,40,38,239,243,38],"41458662","rafram",[245,40,38,239,246,38],"41459208","cholantesh",[215,40,38,248,11,40],"maker\u002Fneutral\u002Fdocs",[250,40,38,251,252,38],"41459853","other\u002Fneutral\u002Fnone","qup",[254,40,43,255,256,38],"41461331","maker\u002Fpositive\u002Fnone","tomrod",[258,40,38,239,236,38],"41461864",[218,40,38,248,11,40],[261,40,34,262,263,38],"41471675","maker\u002Fneutral\u002Fnone","Tepix",[265,40,38,251,266,38],"41463803","placebo",[117,33,34,268,118,38],"project\u002Fmixed\u002Fexecution",[270,33,34,271,272,38],"41459651","project\u002Fneutral\u002Fidea","fallinditch",[274,33,34,271,275,38],"41461739","shanusmagnus",[277,33,34,271,272,38],"41462282",[279,33,34,271,280,38],"41466600","bottom999mottob",[282,34,43,283,284,38],"41459470","project\u002Fpositive\u002Fdesign","tencentshill",[221,34,38,286,11,40],"maker\u002Fneutral\u002Fdesign",[288,18,38,251,289,38],"41458386","101008",[291,18,38,251,292,38],"41458407","samdung",[294,18,38,251,295,38],"41458722","dartos",[297,18,38,251,298,38],"41458758","smokel",[300,18,38,251,301,38],"41458966","bboygravity",[303,18,38,251,289,38],"41459312",[305,18,38,239,306,38],"41467255","bubaumba",[308,18,38,251,309,38],"41462268","jrm4",[311,18,38,239,298,38],"41464253",[313,18,38,239,309,38],"41469331",[315,18,38,239,298,38],"41472985",[317,18,38,239,309,38],"41478295",[319,18,38,239,320,38],"41491411","nativeit",[322,18,38,251,323,38],"41462521","nl",[325,18,38,251,326,38],"41461969","darepublic",[328,18,38,251,329,38],"41468569","aldanor",[61,43,43,255,62,38],[87,212,43,283,88,38],[333,225,34,334,335,38],"41458212","project\u002Fneutral\u002Fexecution","nunobrito",[337,225,38,239,338,38],"41458464","yjftsjthsd-h",[340,225,38,239,335,38],"41458766",[342,225,40,343,344,38],"41461616","project\u002Fcritical\u002Fexecution","viraptor",[346,225,38,239,335,38],"41482370",[91,348,43,283,92,38],8,[186,348,34,350,187,38],"project\u002Fneutral\u002Fnone",[95,348,43,283,92,38],[353,348,38,262,11,40],"41459983",[69,355,34,356,70,38],9,"project\u002Fneutral\u002Fpricing",[358,355,34,356,70,38],"41467370",[360,211,34,356,361,38],"41460062","egamirorrim",[363,211,34,356,364,38],"41460690","monkmartinez",[366,211,34,356,367,38],"41460973","aznumeric",[369,370,34,271,371,38],"41458843",11,"CuriouslyC",[106,370,38,350,11,40],[124,374,40,343,125,38],12,[376,374,38,262,11,40],"41459321",[378,374,38,239,125,38],"41461029",[153,31,34,380,154,38],"project\u002Fmixed\u002Fdesign",[157,31,34,382,158,38],"project\u002Fneutral\u002Fdesign",[384,385,34,235,386,38],"41458791",14,"politelemon",[143,388,34,382,144,38],15,[147,388,38,283,11,40],[391,388,34,271,392,38],"41463871","prometheon1",[164,394,43,231,165,38],16,[396,394,43,231,397,38],"41463450","Kichererbsen",[101,226,43,283,102,38],[190,400,34,350,191,38],18,[203,400,34,271,204,38],[131,403,40,404,132,38],19,"project\u002Fcritical\u002Fprivacy",[406,403,43,255,407,38],"41457968","hluska",[409,403,38,410,411,38],"41458833","commenter\u002Fneutral\u002Fprivacy","Tostino",[413,403,38,414,11,40],"41459304","project\u002Fneutral\u002Fprivacy",[416,417,34,350,418,38],"41463469",20,"somesun",[420,417,38,350,11,40],"41470119",[172,422,34,423,173,38],21,"project\u002Fneutral\u002Fperformance",[176,422,38,423,11,40],[426,32,43,231,125,38],"41457824",[428,429,43,430,431,38],"41470020",23,"maker\u002Fpositive\u002Fdocs","m1keil",[],[434,439,443,448,452,457],{"id":435,"name":436,"points":437,"category":438},"41465735","Wealthfolio",924,"finance_crypto",{"id":440,"name":441,"points":442,"category":20},"41467704","Infinity",481,{"id":444,"name":445,"points":446,"category":447},"41473518","HN Books",285,"learning_science",{"id":449,"name":450,"points":446,"category":451},"41500938","YourNextStore","web_saas",{"id":453,"name":454,"points":455,"category":456},"41456411","Hacker League",192,"games",{"id":458,"name":459,"points":460,"category":20},"41512142","felafax",189,false,"v2",{"id":464,"name":5,"line":6,"ai":461,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":465,"top":18,"kw":466,"maker":11,"domain":10,"tier":19,"attempts":38,"strip":467,"url":9,"mix":468,"praise":84,"objection":114,"sub":21},41457633,0.25,[24,25,26,27],"5300533335000000005501553333133355330335",[31,32,33,34],1793991099656]