[{"data":1,"prerenderedAt":168},["ShallowReactive",2],{"project-39552826":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":15,"aspects":34,"strip":37,"post_text":39,"what":40,"said":74,"maker_in_thread":118,"shape":120,"grid":123,"attempts":131,"same_week":132,"maker_shows":160,"maker_hidden":161,"reader_version":162,"card":163},"39552826","Continue.dev","Continue.dev releases local, open-source tab-autocomplete","title","Show HN: Continue.dev releases local, open-source tab-autocomplete","https:\u002F\u002Fcontinue.dev\u002Fdocs\u002Fwalkthroughs\u002Ftab-autocomplete","continue.dev","sestinj",1709230095,2024,53,3,1257,3515,36,"notable","dev_tools","ai code completion","other",[24,25,26,27,28],"tab autocomplete","code completion","ollama","llama.cpp","copilot alternative","quiet",null,{"positive":32,"neutral":32,"mixed":33,"critical":32},1,0,{"performance":35,"idea":36},{"positive":33,"critical":32},{"positive":32,"critical":33},[32,38,15],5,"Hey HN! After working on this for the last couple of months, we (Continue.dev) are finally releasing tab-autocomplete in beta. It is private, local, and secure, using Ollama, llama.cpp, or any other LLM provider. I'm even more excited about it being completely open-source, because it means I can share how we built it!\n\nI've been sharing details on Twitter for the last month (summarized here: https:\u002F\u002Ftwitter.com\u002FNateSesti\u002Fstatus\u002F1763264142163808279), covering the following:\n\n- A specific type of debouncing, and strategy for re-using streamed requests\n\n- How we use the Language Server Protocol t",{"problem":41,"audience":30,"pricing":30,"motivation":47,"time_to_build":51,"stack":55,"openness":71,"stage":72,"team_size":73},{"value":42,"source":43,"evidence":44},"Code autocomplete that runs privately and locally instead of through a cloud service","maker",[45],{"id":46},"post",{"value":48,"source":43,"evidence":49},"Make an open-source alternative to Copilot and share how it was built",[50],{"id":46},{"value":52,"source":43,"evidence":53},"A couple of months",[54],{"id":46},[56,60,64,68],{"value":57,"source":43,"evidence":58},"Language Server Protocol",[59],{"id":46},{"value":61,"source":43,"evidence":62},"tree-sitter",[63],{"id":46},{"value":65,"source":43,"evidence":66},"Ollama",[67],{"id":46},{"value":27,"source":43,"evidence":69},[70],{"id":46},"open_source","beta","company",{"praise":75,"objections":84,"requests":96,"questions":104,"alternatives":105},[76],{"value":77,"source":78,"evidence":79},"Welcomed as an open-source alternative to Copilot","commenter",[80],{"id":81,"by":82,"text":83},"39564630","moritzwarhier","I was confused by the title at first. I was thinking of CLI tab-autocomplete, which thankfully is local by default :) Anyway, as much as I am lagging behind in adoption of LLMs…",[85,92],{"value":86,"source":78,"evidence":87},"Poor results with C# and Windows setup; local DeepSeek hard to get running",[88],{"id":89,"by":90,"text":91},"39582460","NoxiousPluK","I recently (yesterday) for the first time tried various variants to get code completion and refactoring after all the hype, and was quite disappointed in it. Now I mainly develop…",{"value":93,"source":78,"evidence":94},"Lazy, slow answers from GPT-4 chat and Copilot in the commenter's test",[95],{"id":89,"by":90,"text":91},[97],{"value":98,"source":78,"evidence":99},"Support for running alongside Tabby or using Groq for faster autocomplete",[100],{"id":101,"by":102,"text":103},"39561014","Havoc","Neat. Been trying to get rid of the dual LLMs (one for complete via Tabby and one for continue). Also want to try autocomplete via groq given its speed, though lack of a code…",[],[106,110,114],{"value":107,"source":78,"evidence":108},"GitHub Copilot",[109],{"id":89,"by":90,"text":91},{"value":111,"source":78,"evidence":112},"Codeium",[113],{"id":89,"by":90,"text":91},{"value":115,"source":78,"evidence":116},"Tabby",[117],{"id":101,"by":102,"text":103},{"comments":33,"answered":33,"key":119},[],{"commenters":15,"max_depth":32,"maker_replies":33,"first_comment_mins":121,"lifespan_hours":122},1084,71,[124,126,128],[89,33,32,125,90,33],"project\u002Fcritical\u002Fperformance",[81,32,38,127,82,33],"project\u002Fpositive\u002Fidea",[101,129,15,130,102,33],2,"project\u002Fneutral\u002Fidea",[],[133,137,141,146,151,155],{"id":134,"name":135,"points":136,"category":20},"39597030","Puter",1274,{"id":138,"name":139,"points":140,"category":20},"39620540","dockerc",374,{"id":142,"name":143,"points":144,"category":145},"39557188","Struct",298,"productivity",{"id":147,"name":148,"points":149,"category":150},"39591529","Astro App",291,"learning_science",{"id":152,"name":153,"points":154,"category":145},"39551064","Row Zero",274,{"id":156,"name":157,"points":158,"category":159},"39549194","Workout Tracker",263,"infrastructure",4,false,"v2",{"id":164,"name":5,"line":6,"ai":161,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":30,"top":18,"kw":165,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":166,"url":9,"mix":167,"praise":77,"objection":86,"sub":21},39552826,[24,25,26,27,28],"153",[32,32,33,32],1793991085713]