[{"data":1,"prerenderedAt":121},["ShallowReactive",2],{"/2026/03/04-running-coding-ai-agent-locally":3},{"id":4,"title":5,"body":6,"date":112,"description":105,"extension":113,"meta":114,"navigation":115,"path":116,"robots":117,"seo":118,"stem":119,"__hash__":120},"posts/2026/03/04 running-coding-ai-agent-locally.md","04 Running Coding Ai Agent Locally",{"type":7,"value":8,"toc":109},"minimark",[9,18,22,38,41,93,106],[10,11,13],"post-title",{":date":12},"date",[14,15,17],"h1",{"id":16},"running-coding-ai-agent-locally","Running Coding AI Agent Locally",[19,20,21],"p",{},"I was wondering if there's a decent AI agent that helped with coding but can be run locally. After a quick test, I managed to get it to work with the following stack:",[23,24,25,29,32,35],"ul",{},[26,27,28],"li",{},"Ollama",[26,30,31],{},"DeepSeek Coder",[26,33,34],{},"Continue VS Code Extension",[26,36,37],{},"VS Code",[19,39,40],{},"To set it up, I follow the steps below:",[42,43,44,56,75,78,90],"ol",{},[26,45,46,47,55],{},"First, I install Ollama on my machine using winget: ",[48,49,54],"code",{"className":50},[51,52,53],"bg-gray-200","p-2","rounded","winget install Ollama.Ollama",".",[26,57,58,59,70,71,55],{},"Then, download DeepSeek Coder to run in Ollama. ",[60,61,64],"span",{"className":62},[63],"text-blue-600",[65,66,67],"a",{"href":67,"rel":68},"https://ollama.com/library/",[69],"nofollow",". In my case, I just use the smallest model which is 1.3b paramaters: ",[48,72,74],{"className":73},[51,52,53],"ollama run deepseek-coder:1.3b",[26,76,77],{},"Next, I search for and install \"Continue\" VS Code extension by continue.dev.",[26,79,80,81,85,86,55],{},"To configure the extension, make sure Ollama is running on ",[65,82,83],{"href":83,"rel":84},"http://localhost:11434",[69],". If it's not, run ",[48,87,89],{"className":88},[51,52,53],"ollama serve",[26,91,92],{},"In my case, the \"Continue\" extension was unable to detect Ollama. I had to setup the configuration to autodetect. To do that, I open the Configs menu of the extension. Click the setting/gear icon next to Local Config and paste the following config:",[94,95,96],"code-block",{},[97,98,103],"pre",{"className":99,"code":101,"language":102},[100],"language-text","name: Local Config\nversion: 1.0.0\nschema: v1\nmodels:\n  - name: Autodetect\n    provider: ollama\n    model: AUTODETECT\n    roles:\n      - chat\n      - edit\n      - apply\n      - rerank\n      - autocomplete\n","text",[48,104,101],{"__ignoreMap":105},"",[19,107,108],{},"Then, the LLM works locally, but it will use a lot of CPU and memory.",{"title":105,"searchDepth":110,"depth":110,"links":111},2,[],"2026-03-04T00:00:00.000Z","md",{},true,"/2026/03/04-running-coding-ai-agent-locally",null,{"title":5,"description":105},"2026/03/04 running-coding-ai-agent-locally","AyNbYdnU8mJvjN5rFJJNSQBQ_5JWkhPQxRE5hQdVkH8",1785167451490]