<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Sagar Ingalagi on Medium]]></title>
        <description><![CDATA[Stories by Sagar Ingalagi on Medium]]></description>
        <link>https://medium.com/@sagar.ingalagi?source=rss-462c4389bdb8------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*hwv7ER9Rpj6c-G5r.jpg</url>
            <title>Stories by Sagar Ingalagi on Medium</title>
            <link>https://medium.com/@sagar.ingalagi?source=rss-462c4389bdb8------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 22 Nov 2026 11:30:29 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@sagar.ingalagi/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Run a Local LLM in VS Code with Continue.dev: Your Private AI Coding Assistant and Auto Complete]]></title>
            <link>https://medium.com/@sagar.ingalagi/run-a-local-llm-in-vs-code-with-continue-dev-your-private-ai-coding-assistant-and-auto-complete-42595b9f2b61?source=rss-462c4389bdb8------2</link>
            <guid isPermaLink="false">https://medium.com/p/42595b9f2b61</guid>
            <category><![CDATA[autocomplete]]></category>
            <category><![CDATA[local-llm]]></category>
            <category><![CDATA[vscode]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[llm]]></category>
            <dc:creator><![CDATA[Sagar Ingalagi]]></dc:creator>
            <pubDate>Wed, 02 Jul 2025 11:23:09 GMT</pubDate>
            <atom:updated>2025-07-02T11:53:04.513Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ueDhk40ZB9dMil4cu6KaiA.png" /></figure><p>AI coding assistants are transforming how we write software. <br>Tools like GitHub Copilot and ChatGPT have brought powerful AI right into our development environments — but they rely on sending your code to remote servers.</p><p>But what if you want to keep your code <strong>private</strong>, work <strong>offline</strong>, or avoid <strong>usage limits</strong>?</p><p><strong>Continue.dev</strong> — a powerful VS Code extension that lets you integrate AI into your coding workflow using <strong>local models</strong> like Mistral, LLaMA, or Phi-2.</p><p>Prerequisites</p><p>Before we begin, make sure you have the following:</p><ul><li>✅ <a href="https://code.visualstudio.com/">Visual Studio Code</a> installed</li></ul><p><strong>Step 1: Set Up a Local Model with Ollama<br>1. </strong>Install Ollama</p><pre>curl -fsSL https://ollama.com/install.sh | sh</pre><p>2. Pull a model</p><pre>ollama run qwen2.5-coder:3b<br>ollama run qwen2.5-coder:1.5b</pre><p><strong>Step 2: Install Continue.dev<br></strong>Open VS Code and search for <strong>“Continue”</strong> in the Extensions.<br>Click <strong>Install</strong>, then open the side panel using the “Continue” icon.</p><p>.continue/config.yml</p><pre>name: Local Assistant<br>version: 1.0.0<br>schema: v1<br><br>models:<br>  - name: Qwen2.5-Coder 3B<br>    provider: ollama<br>    model: qwen2.5-coder:3b<br>    roles:<br>      - chat<br>      - edit<br>      - apply<br><br>  - name: Qwen2.5-Coder 1.5B (Autocomplete)<br>    provider: ollama<br>    model: qwen2.5-coder:1.5b<br>    roles:<br>      - autocomplete<br><br>  - name: Autodetect<br>    provider: ollama<br>    model: AUTODETECT<br><br>context:<br>  - provider: code<br>  - provider: docs<br>  - provider: diff<br>  - provider: terminal<br>  - provider: problems<br>  - provider: folder<br>  - provider: codebase</pre><figure><img alt="" src="https://cdn-images-1.medium.com/max/388/1*GYf-Ey0NCX2OXFBBUDiyRQ.png" /></figure><p>Step 3: Use Your New Coding Copilot</p><p>You can:<br>- Ask questions about your code<br>- Generate boilerplate<br>- Refactor large chunks<br>- Explain complex logic</p><p>All of this happens <strong>locally</strong>, with <strong>no data leaving your machine</strong>. This means:</p><p>🔐 No privacy concerns<br>🌐 Fully offline capability<br>🚀 No API rate limits or tokens to manage<br>🧩 Total control over which models you use</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=42595b9f2b61" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>