main pages revamped and new docs updated

docs/src/pages/docs/index.mdx

@@ -28,22 +28,24 @@ import FAQBox from '@/components/FaqBox'
 
 ## Jan's Goal
 
-> We're working towards open superintelligence - a viable open-source alternative to platforms like ChatGPT and Claude that anyone can own and run.
+> We're working towards open superintelligence to make a viable open-source alternative to platforms like ChatGPT
+and Claude that anyone can own and run.
 
 ## What is Jan Today
 
-Jan is an open-source AI platform that runs on your hardware. We believe AI should be in the hands of many, not controlled by a few tech giants.
+Jan is an open-source AI platform that runs on your hardware. We believe AI should be in the hands of many, not
+controlled by a few tech giants.
 
 Today, Jan is:
 - **A desktop app** that runs AI models locally or connects to cloud providers
 - **A model hub** making the latest open-source models accessible
-- **A connector system** that lets AI interact with real-world tools
-- **A testing framework** that evaluates model quality transparently
+- **A connector system** that lets AI interact with real-world tools via MCP
 
 Tomorrow, Jan aims to be a complete ecosystem where open models rival or exceed closed alternatives.
 
 <Callout type="info">
-We're building this with the open-source AI community, using the best available tools, and sharing everything we learn along the way.
+We're building this with the open-source AI community, using the best available tools, and sharing everything
+we learn along the way.
 </Callout>
 
 ## The Jan Ecosystem
@@ -56,19 +58,19 @@ We're building this with the open-source AI community, using the best available
 - **Mobile**: Jan on your phone
 - **Web**: Browser-based access at jan.ai
 - **Server**: Self-hosted for teams
-- **Extensions**: Excel, Word, and browser integrations
+- **Extensions**: Browser extension for Chrome-based browsers
 
 ### Jan Model Hub
 Making open-source AI accessible to everyone:
 - **Easy Downloads**: One-click model installation
 - **Jan Models**: Our own models optimized for local use
-  - **Jan-Nano (32k/128k)**: 4B model for research with MCP tools
-  - **Lucy**: 1.7B mobile-optimized search model
-  - **Jan-v1**: 4B reasoning and tool-use model
-- **Community Models**: Any GGUF from Hugging Face
-- **Cloud Models**: Connect your API keys for OpenAI, Anthropic, etc.
+  - **Jan-v1**: 4B reasoning model specialized in web search
+  - **Research Models**
+    - **Jan-Nano (32k/128k)**: 4B model for web search with MCP tools
+    - **Lucy**: 1.7B mobile-optimized for web search
+- **Community Models**: Any GGUF from Hugging Face works in Jan
+- **Cloud Models**: Connect your API keys for OpenAI, Anthropic, Gemini, and more
 
-Each model comes with transparent evaluations through Jan Exam.
 
 ### Jan Connectors Hub
 Connect AI to the tools you use daily via [Model Context Protocol](./mcp):
@@ -89,40 +91,27 @@ Connect AI to the tools you use daily via [Model Context Protocol](./mcp):
 - **Linear**: Project management
 - **Todoist**: Task management
 
-More connectors are added regularly by the community.
-
-### Jan Exam
-Transparent model evaluation:
-- Real-world benchmarks
-- Community-driven testing
-- Public results for all models
-- No cherry-picked metrics
-
-### Jan Family of Models
-We're training specialized models optimized for local devices:
-- **Speech Models**: Like Ichigo for voice interactions
-- **Reasoning Models**: Like Jan-v1 for tool use and complex tasks
-- **Task-Specific Models**: Optimized for search, writing, analysis
-
-These take the best of open source and tailor them for real-world use on consumer hardware.
-
 ## Core Features
 
-- **Run Models Locally**: Download any GGUF model from Hugging Face, use OpenAI's gpt-oss models, or connect to cloud providers
-- **OpenAI-Compatible API**: Local server at `localhost:1337` works with tools like [Continue](./server-examples/continue-dev) and [Cline](https://cline.bot/)
-- **Extend with MCP Tools**: Browser automation, web search, data analysis, design tools - all through natural language
-- **Your Choice of Infrastructure**: Run on your laptop, self-host on your servers (soon), or use cloud when you need it
+- **Run Models Locally**: Download any GGUF model from Hugging Face, use OpenAI's gpt-oss models,
+or connect to cloud providers
+- **OpenAI-Compatible API**: Local server at `localhost:1337` works with tools like
+[Continue](./server-examples/continue-dev) and [Cline](https://cline.bot/)
+- **Extend with MCP Tools**: Browser automation, web search, data analysis, and design tools, all
+through natural language
+- **Your Choice of Infrastructure**: Run on your laptop, self-host on your servers (soon), or use
+cloud when you need it
 
 ## Philosophy
 
 Jan is built to be user-owned:
-- **Open Source**: Apache 2.0 license - truly free
+- **Open Source**: Apache 2.0 license
 - **Local First**: Your data stays on your device. Internet is optional
 - **Privacy Focused**: We don't collect or sell user data. See our [Privacy Policy](./privacy)
 - **No Lock-in**: Export your data anytime. Use any model. Switch between local and cloud
 
 <Callout>
-The best AI is the one you control. Not the one that controls you.
+The best AI is the one you control. Not the one that other control for you.
 </Callout>
 
 ## The Path Forward
@@ -137,7 +126,7 @@ The best AI is the one you control. Not the one that controls you.
 - More specialized models that excel at specific tasks
 - Expanded app ecosystem (mobile, web, extensions)
 - Richer connector ecosystem
-- Models that approach or exceed GPT-4 class performance
+- An evaluation framework to build better models
 
 ### The Long-Term Vision
 We're working towards open superintelligence where:
@@ -147,7 +136,8 @@ We're working towards open superintelligence where:
 - AI capabilities are owned by users, not rented
 
 <Callout type="warning">
-This is an ambitious goal without a guaranteed path. We're betting on the open-source community, improved hardware, and better techniques - but we're honest that this is a journey, not a destination we've reached.
+This is an ambitious goal without a guaranteed path. We're betting on the open-source community, improved
+hardware, and better techniques, but we're honest that this is a journey, not a destination we've reached.
 </Callout>
 
 ## Quick Start
@@ -155,7 +145,7 @@ This is an ambitious goal without a guaranteed path. We're betting on the open-s
 1. [Download Jan](./quickstart) for your operating system
 2. Choose a model - download locally or add cloud API keys
 3. Start chatting or connect tools via MCP
-4. Build with our [API](https://jan.ai/api-reference)
+4. Build with our [local API](./api-server)
 
 ## Acknowledgements
 
@@ -179,11 +169,11 @@ Jan is built on the shoulders of giants:
   - Jan-Nano (32k/128k) - Research and analysis with MCP integration
   - Lucy - Mobile-optimized search (1.7B)
   - Jan-v1 - Reasoning and tool use (4B)
-  
+
   **Open Source:**
   - OpenAI's gpt-oss models (120b and 20b)
   - Any GGUF model from Hugging Face
-  
+
   **Cloud (with your API keys):**
   - OpenAI, Anthropic, Mistral, Groq, and more
 </FAQBox>
@@ -220,7 +210,7 @@ Jan is built on the shoulders of giants:
   **Local use**: Always free, no catches
   **Cloud models**: You pay providers directly (we add no markup)
   **Jan cloud**: Optional paid services coming 2025
-  
+
   The core platform will always be free and open source.
 </FAQBox>
 
@@ -243,7 +233,7 @@ Jan is built on the shoulders of giants:
   - **Jan Web**: Beta late 2025
   - **Jan Mobile**: Late 2025
   - **Jan Server**: Late 2025
-  
+
   All versions will sync seamlessly.
 </FAQBox>
 
@@ -256,4 +246,4 @@ Jan is built on the shoulders of giants:
 
 <FAQBox title="Are you hiring?">
   Yes! We love hiring from our community. Check [Careers](https://menlo.bamboohr.com/careers).
-</FAQBox>
+</FAQBox>

docs/src/pages/docs/quickstart.mdx

@@ -47,30 +47,13 @@ We recommend starting with **Jan v1**, our 4B parameter model optimized for reas
 Jan v1 achieves 91.1% accuracy on SimpleQA and excels at tool calling, making it perfect for web search and reasoning tasks.
 </Callout>
 
-**HuggingFace models:** Some require an access token. Add yours in **Settings > Model Providers > Llama.cpp > Hugging Face Access Token**.
-
-![Add HF Token](./_assets/hf_token.png)
-
-### Step 3: Enable GPU Acceleration (Optional)
-
-For Windows/Linux with compatible graphics cards:
-
-1. Go to **(<Settings width={16} height={16} style={{display:"inline"}}/>) Settings** > **Hardware**
-2. Toggle **GPUs** to ON
-
-![Turn on GPU acceleration](./_assets/gpu_accl.png)
-
-<Callout type="info">
-Install required drivers before enabling GPU acceleration. See setup guides for [Windows](/docs/desktop/windows#gpu-acceleration) & [Linux](/docs/desktop/linux#gpu-acceleration).
-</Callout>
-
-### Step 4: Start Chatting
+### Step 3: Start Chatting
 
 1. Click **New Chat** (<SquarePen width={16} height={16} style={{display:"inline"}}/>) icon
 2. Select your model in the input field dropdown
 3. Type your message and start chatting
 
-![Create New Thread](./_assets/threads-new-chat-updated.png)
+![Create New Thread](./_assets/jan_loaded.png)
 
 Try asking Jan v1 questions like:
 - "Explain quantum computing in simple terms"
@@ -118,7 +101,7 @@ Thread deletion is permanent. No undo available.
 
 **All threads:**
 1. Hover over `Recents` category
-2. Click **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon  
+2. Click **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon
 3. Select <Trash2 width={16} height={16} style={{display:"inline"}}/> **Delete All**
 
 ## Advanced Features

docs/src/pages/platforms/_meta.json

@@ -0,0 +1,9 @@
+{
+  "-- Switcher": {
+    "type": "separator",
+    "title": "Switcher"
+  },
+  "index": {
+    "display": "hidden"
+  }
+}

docs/src/pages/platforms/index.mdx

@@ -0,0 +1,87 @@
+---
+title: Coming Soon
+description: Exciting new features and platforms are on the way. Stay tuned for Jan Web, Jan Mobile, and our API Platform.
+keywords:
+  [
+    Jan,
+    Customizable Intelligence, LLM,
+    local AI,
+    privacy focus,
+    free and open source,
+    private and offline,
+    conversational AI,
+    no-subscription fee,
+    large language models,
+    coming soon,
+    Jan Web,
+    Jan Mobile,
+    API Platform,
+  ]
+---
+
+import { Callout } from 'nextra/components'
+
+<div className="text-center py-12">
+  <div className="mb-8">
+    <h1 className="text-4xl font-bold bg-gradient-to-r from-blue-600 to-purple-600 bg-clip-text text-transparent mb-4 py-2">
+      🚀 Coming Soon
+    </h1>
+    <p className="text-xl text-gray-600 dark:text-gray-300 max-w-2xl mx-auto">
+      We're working on the next stage of Jan - making our local assistant more powerful and available in more platforms.
+    </p>
+  </div>
+
+  <div className="grid grid-cols-1 md:grid-cols-3 gap-6 max-w-4xl mx-auto mb-12">
+    <div className="p-6 border border-gray-200 dark:border-gray-700 rounded-lg bg-gradient-to-br from-blue-50 to-indigo-50 dark:from-blue-900/20 dark:to-indigo-900/20">
+      <div className="text-3xl mb-3">🌐</div>
+      <h3 className="text-lg font-semibold mb-2">Jan Web</h3>
+      <p className="text-sm text-gray-600 dark:text-gray-400">
+        Access Jan directly from your browser with our powerful web interface
+      </p>
+    </div>
+
+    <div className="p-6 border border-gray-200 dark:border-gray-700 rounded-lg bg-gradient-to-br from-green-50 to-emerald-50 dark:from-green-900/20 dark:to-emerald-900/20">
+      <div className="text-3xl mb-3">📱</div>
+      <h3 className="text-lg font-semibold mb-2">Jan Mobile</h3>
+      <p className="text-sm text-gray-600 dark:text-gray-400">
+        Take Jan on the go with our native mobile applications
+      </p>
+    </div>
+
+    <div className="p-6 border border-gray-200 dark:border-gray-700 rounded-lg bg-gradient-to-br from-purple-50 to-pink-50 dark:from-purple-900/20 dark:to-pink-900/20">
+      <div className="text-3xl mb-3">⚡</div>
+      <h3 className="text-lg font-semibold mb-2">API Platform</h3>
+      <p className="text-sm text-gray-600 dark:text-gray-400">
+        Integrate Jan's capabilities into your applications with our API
+      </p>
+    </div>
+  </div>
+
+  <Callout type="info">
+    **Stay Updated**: Follow our [GitHub repository](https://github.com/menloresearch/jan) and join our [Discord community](https://discord.com/invite/FTk2MvZwJH) for the latest updates on these exciting releases!
+  </Callout>
+
+  <div className="mt-12">
+    <h2 className="text-2xl font-semibold mb-6">What to Expect</h2>
+    <div className="text-left max-w-2xl mx-auto space-y-4">
+      <div className="flex items-start gap-3">
+        <span className="text-green-500 text-xl">✓</span>
+        <div>
+          <strong>Seamless Experience:</strong> Unified interface across all platforms
+        </div>
+      </div>
+      <div className="flex items-start gap-3">
+        <span className="text-green-500 text-xl">✓</span>
+        <div>
+          <strong>Privacy First:</strong> Same privacy-focused approach you trust
+        </div>
+      </div>
+      <div className="flex items-start gap-3">
+        <span className="text-green-500 text-xl">✓</span>
+        <div>
+          <strong>Developer Friendly:</strong> Robust APIs and comprehensive documentation
+        </div>
+      </div>
+    </div>
+  </div>
+</div>

website/astro.config.mjs

@@ -76,17 +76,12 @@ export default defineConfig({
                       { label: 'Groq', slug: 'jan/remote-models/groq' },
                     ],
                   },
-                ],
-              },
-              {
-                label: 'TUTORIALS',
-                items: [
                   {
-                    label: 'MCP Examples',
+                    label: 'Tutorials',
                     collapsed: true,
                     items: [
                       {
-                        label: 'Browser Control (Browserbase)',
+                        label: 'Browser Control',
                         slug: 'jan/mcp-examples/browser/browserbase',
                       },
                       {
@@ -94,11 +89,15 @@ export default defineConfig({
                         slug: 'jan/mcp-examples/data-analysis/e2b',
                       },
                       {
-                        label: 'Design Creation (Canva)',
+                        label: 'Jupyter Notebooks',
+                        slug: 'jan/mcp-examples/data-analysis/jupyter',
+                      },
+                      {
+                        label: 'Design with Canva',
                         slug: 'jan/mcp-examples/design/canva',
                       },
                       {
-                        label: 'Deep Research (Octagon)',
+                        label: 'Deep Financial Research',
                         slug: 'jan/mcp-examples/deepresearch/octagon',
                       },
                       {
@@ -106,9 +105,17 @@ export default defineConfig({
                         slug: 'jan/mcp-examples/search/serper',
                       },
                       {
-                        label: 'Web Search (Exa)',
+                        label: 'Exa Search',
                         slug: 'jan/mcp-examples/search/exa',
                       },
+                      {
+                        label: 'Linear',
+                        slug: 'jan/mcp-examples/productivity/linear',
+                      },
+                      {
+                        label: 'Todoist',
+                        slug: 'jan/mcp-examples/productivity/todoist',
+                      },
                     ],
                   },
                 ],

website/src/content/docs/index.mdx

@@ -4,42 +4,47 @@ description: Working towards open superintelligence through community-driven AI
 keywords:
   [
     Jan,
+    Jan AI,
     open superintelligence,
     AI ecosystem,
-    self-hosted AI,
     local AI,
+    private AI,
+    self-hosted AI,
     llama.cpp,
+    Model Context Protocol,
+    MCP,
     GGUF models,
-    MCP tools,
-    Model Context Protocol
+    large language model,
+    LLM,
   ]
 ---
 
 import { Aside } from '@astrojs/starlight/components';
 
-![Jan Desktop](../../assets/jan-app-new.png)
+# Jan
+
+![Jan's Cover Image](../../assets/jan_loaded.png)
 
 ## Jan's Goal
 
-> We're working towards open superintelligence that will be a viable open-source alternative to
-platforms like ChatGPT and Claude that anyone can own and run.
+> We're working towards open superintelligence to make a viable open-source alternative to platforms like ChatGPT
+and Claude that anyone can own and run.
 
 ## What is Jan Today
 
-Jan is an open-source AI platform that runs on your hardware. We believe AI should be in the
-hands of many, not controlled by a few tech giants.
+Jan is an open-source AI platform that runs on your hardware. We believe AI should be in the hands of many, not
+controlled by a few tech giants.
 
 Today, Jan is:
 - **A desktop app** that runs AI models locally or connects to cloud providers
 - **A model hub** making the latest open-source models accessible
-- **A connector system** that lets AI interact with real-world tools via MCPs
-- **A testing framework** that evaluates model quality transparently
+- **A connector system** that lets AI interact with real-world tools via MCP
 
 Tomorrow, Jan aims to be a complete ecosystem where open models rival or exceed closed alternatives.
 
 <Aside type="note">
-We're building this with the open-source AI community, using the best available tools, and
-sharing everything we learn along the way.
+We're building this with the open-source AI community, using the best available tools, and sharing everything
+we learn along the way.
 </Aside>
 
 ## The Jan Ecosystem
@@ -51,23 +56,23 @@ sharing everything we learn along the way.
 **Coming Late 2025:**
 - **Mobile**: Jan on your phone
 - **Web**: Browser-based access at jan.ai
-- **Extensions**: Excel, Word, and browser integrations
+- **Server**: Self-hosted for teams
+- **Extensions**: Browser extension for Chrome-based browsers
 
 ### Jan Model Hub
 Making open-source AI accessible to everyone:
 - **Easy Downloads**: One-click model installation
 - **Jan Models**: Our own models optimized for local use
-- **Jan-v1**: 4B reasoning model for web search
-  **Research Models**:
+  - **Jan-v1**: 4B reasoning model specialized in web search
+  - **Research Models**
     - **Jan-Nano (32k/128k)**: 4B model for web search with MCP tools
     - **Lucy**: 1.7B mobile-optimized for web search
-- **Community Models**: Any GGUF from Hugging Face
-- **Cloud Models**: Connect your API keys for OpenAI, Anthropic, etc.
+- **Community Models**: Any GGUF from Hugging Face works in Jan
+- **Cloud Models**: Connect your API keys for OpenAI, Anthropic, Gemini, and more
 
-Each model comes with transparent evaluations through Jan Exam.
 
 ### Jan Connectors Hub
-Connect AI to the tools you use daily via [Model Context Protocol](https://modelcontextprotocol.io):
+Connect AI to the tools you use daily via [Model Context Protocol](./mcp):
 
 **Creative & Design:**
 - **Canva**: Generate and edit designs
@@ -77,41 +82,36 @@ Connect AI to the tools you use daily via [Model Context Protocol](https://model
 - **E2B**: Execute code in sandboxes
 
 **Web & Search:**
-- **Browserbase**: Browser automation
-- **Exa & Serper**: Advanced web search
+- **Browserbase & Browser Use**: Browser automation
+- **Exa, Serper, Perplexity**: Advanced web search
 - **Octagon**: Deep research capabilities
 
 **Productivity:**
 - **Linear**: Project management
 - **Todoist**: Task management
 
-More connectors are added regularly by the community.
+## Core Features
 
-### Jan Exam
-Transparent model evaluation:
-- Real-world benchmarks
-- Community-driven testing
-- Public results for all models
-- No cherry-picked metrics
+- **Run Models Locally**: Download any GGUF model from Hugging Face, use OpenAI's gpt-oss models,
+or connect to cloud providers
+- **OpenAI-Compatible API**: Local server at `localhost:1337` works with tools like
+[Continue](./server-examples/continue-dev) and [Cline](https://cline.bot/)
+- **Extend with MCP Tools**: Browser automation, web search, data analysis, and design tools, all
+through natural language
+- **Your Choice of Infrastructure**: Run on your laptop, self-host on your servers (soon), or use
+cloud when you need it
 
-### Jan Family of Models
-We're training specialized models optimized for local devices:
-- **Speech Models**: Like Ichigo for voice interactions
-- **Web Search Models**: Like Jan-v1 with tool use and reasoning
-- **Other Task-Specific Models**: Optimized for search, writing, analysis
+## Philosophy
 
-These take the best of open source and tailor them for real-world use on consumer hardware.
+Jan is built to be user-owned:
+- **Open Source**: Apache 2.0 license
+- **Local First**: Your data stays on your device. Internet is optional
+- **Privacy Focused**: We don't collect or sell user data. See our [Privacy Policy](./privacy)
+- **No Lock-in**: Export your data anytime. Use any model. Switch between local and cloud
 
-## Why Jan?
-
-| Feature | Big Tech AI | Jan |
-|:--------|:------------|:----|
-| **Control** | They control access | You own everything |
-| **Data** | Stored on their servers | Stays on your device |
-| **Models** | One-size-fits-all | Choose from many options |
-| **Cost** | Monthly subscription | Free locally, optional cloud |
-| **Tools** | Limited integrations | Growing MCP ecosystem |
-| **Transparency** | Black box | Open source, open evals |
+<Aside>
+The best AI is the one you control. Not the one that other control for you.
+</Aside>
 
 ## The Path Forward
 
@@ -125,7 +125,7 @@ These take the best of open source and tailor them for real-world use on consume
 - More specialized models that excel at specific tasks
 - Expanded app ecosystem (mobile, web, extensions)
 - Richer connector ecosystem
-- Models that approach or exceed GPT-4 class performance
+- An evaluation framework to build better models
 
 ### The Long-Term Vision
 We're working towards open superintelligence where:
@@ -135,35 +135,77 @@ We're working towards open superintelligence where:
 - AI capabilities are owned by users, not rented
 
 <Aside type="caution">
-This is an ambitious goal without a guaranteed path. We're betting on the open-source community,
-improved hardware, and better techniques - but we're honest that this is a journey, not a
-destination we've reached.
+This is an ambitious goal without a guaranteed path. We're betting on the open-source community, improved
+hardware, and better techniques, but we're honest that this is a journey, not a destination we've reached.
 </Aside>
 
-## System Requirements
-To use Jan Desktop today, you'll need:
-**Minimum**: 8GB RAM, 10GB storage
-**Recommended**: 16GB RAM, GPU (NVIDIA/AMD/Intel/Apple), 50GB storage
-**Supported**: Windows 10+, macOS 12+, Linux (Ubuntu 20.04+)
+## Quick Start
 
-## Get Started
+1. [Download Jan](./quickstart) for your operating system
+2. Choose a model - download locally or add cloud API keys
+3. Start chatting or connect tools via MCP
+4. Build with our [local API](./api-server)
 
-1. [Install Jan Desktop](./jan/installation) - Start using AI locally
-2. [Explore Models](./jan/models) - Download models from our hub
-3. [Connect Tools](./jan/mcp) - Extend AI with real-world capabilities
-4. [Join the Community](https://discord.gg/FTk2MvZwJH) - Help build open superintelligence
+## Acknowledgements
 
-## FAQ
+Jan is built on the shoulders of giants:
+- [Llama.cpp](https://github.com/ggerganov/llama.cpp) for inference
+- [Model Context Protocol](https://modelcontextprotocol.io) for tool integration
+- The open-source community that makes this possible
+
+## FAQs
 
 <details>
-<summary><strong>How is this different from just using ChatGPT?</strong></summary>
+<summary><strong>What is Jan?</strong></summary>
 
-With Jan:
-- Your conversations stay on your device
-- No monthly subscription for local use
-- Choose from many models, not just one
-- Connect to tools ChatGPT doesn't support
-- Own your AI infrastructure forever
+Jan is an open-source AI platform working towards a viable alternative to Big Tech AI. Today it's a desktop app that runs models locally or connects to cloud providers. Tomorrow it aims to be a complete ecosystem rivaling platforms like ChatGPT and Claude.
+</details>
+
+<details>
+<summary><strong>How is this different from other AI platforms?</strong></summary>
+
+Other platforms are models behind APIs you rent. Jan is a complete AI ecosystem you own. Run any model, use real tools through MCP, keep your data private, and never pay subscriptions for local use.
+</details>
+
+<details>
+<summary><strong>What models can I use?</strong></summary>
+
+**Jan Models:**
+- Jan-Nano (32k/128k) - Research and analysis with MCP integration
+- Lucy - Mobile-optimized search (1.7B)
+- Jan-v1 - Reasoning and tool use (4B)
+
+**Open Source:**
+- OpenAI's gpt-oss models (120b and 20b)
+- Any GGUF model from Hugging Face
+
+**Cloud (with your API keys):**
+- OpenAI, Anthropic, Mistral, Groq, and more
+</details>
+
+<details>
+<summary><strong>What are MCP tools?</strong></summary>
+
+MCP (Model Context Protocol) lets AI interact with real applications. Instead of just generating text, your AI can create designs in Canva, analyze data in Jupyter, browse the web, and execute code - all through conversation.
+</details>
+
+<details>
+<summary><strong>Is Jan compatible with my system?</strong></summary>
+
+**Supported OS**:
+- [Windows 10+](/docs/desktop/windows#compatibility)
+- [macOS 12+](/docs/desktop/mac#compatibility)
+- [Linux (Ubuntu 20.04+)](/docs/desktop/linux)
+
+**Hardware**:
+- Minimum: 8GB RAM, 10GB storage
+- Recommended: 16GB RAM, GPU (NVIDIA/AMD/Intel/Apple), 50GB storage
+</details>
+
+<details>
+<summary><strong>How realistic is 'open superintelligence'?</strong></summary>
+
+Honestly? It's ambitious and uncertain. We believe the combination of rapidly improving open models, better consumer hardware, community innovation, and specialized models working together can eventually rival closed platforms. But this is a multi-year journey with no guarantees. What we can guarantee is that we'll keep building in the open, with the community, towards this goal.
 </details>
 
 <details>
@@ -178,39 +220,55 @@ Right now, Jan can:
 </details>
 
 <details>
-<summary><strong>How realistic is "open superintelligence"?</strong></summary>
+<summary><strong>Is Jan really free?</strong></summary>
 
-Honestly? It's ambitious and uncertain. We believe the combination of:
-- Rapidly improving open models
-- Better consumer hardware
-- Community innovation
-- Specialized models working together
+**Local use**: Always free, no catches
+**Cloud models**: You pay providers directly (we add no markup)
+**Jan cloud**: Optional paid services coming 2025
 
-...can eventually rival closed platforms. But this is a multi-year journey with no guarantees. What we can guarantee is that we'll keep building in the open, with the community, towards this goal.
+The core platform will always be free and open source.
 </details>
 
 <details>
-<summary><strong>How does Jan make money?</strong></summary>
+<summary><strong>How does Jan protect privacy?</strong></summary>
 
-- **Local use**: Always free
-- **Cloud services**: Optional paid features (coming late 2025)
-- **Enterprise**: Support and deployment services
+- Runs 100% offline once models are downloaded
+- All data stored locally in [Jan Data Folder](/docs/data-folder)
+- No telemetry without explicit consent
+- Open source code you can audit
 
-We build sustainable software, not surveillance capitalism.
+<Aside type="caution">
+When using cloud providers through Jan, their privacy policies apply.
+</Aside>
 </details>
 
 <details>
-<summary><strong>Can I contribute?</strong></summary>
+<summary><strong>Can I self-host Jan?</strong></summary>
 
-Absolutely. This only works with community involvement:
-- [GitHub](https://github.com/janhq/jan) - Code contributions
-- [Discord](https://discord.gg/FTk2MvZwJH) - Join discussions
-- [Model Training](https://train.jan.ai) - Watch our training runs
-- [Model Testing](https://eval.jan.ai) - Help evaluate models
+Yes. Download directly or build from [source](https://github.com/menloresearch/jan). Jan Server for production deployments coming late 2025.
 </details>
 
----
+<details>
+<summary><strong>When will mobile/web versions launch?</strong></summary>
 
-**Ready to own your AI?** [Download Jan](./jan/installation) and join us in building towards open superintelligence.
+- **Jan Web**: Beta late 2025
+- **Jan Mobile**: Late 2025
+- **Jan Server**: Late 2025
 
-**Have questions?** Join our [Discord](https://discord.gg/FTk2MvZwJH) or explore our [GitHub](https://github.com/janhq/jan).
+All versions will sync seamlessly.
+</details>
+
+<details>
+<summary><strong>How can I contribute?</strong></summary>
+
+- Code: [GitHub](https://github.com/menloresearch/jan)
+- Community: [Discord](https://discord.gg/FTk2MvZwJH)
+- Testing: Help evaluate models and report bugs
+- Documentation: Improve guides and tutorials
+</details>
+
+<details>
+<summary><strong>Are you hiring?</strong></summary>
+
+Yes! We love hiring from our community. Check [Careers](https://menlo.bamboohr.com/careers).
+</details>

website/src/content/docs/jan/jan-models/jan-v1.mdx

@@ -1,6 +1,11 @@
 ---
 title: Jan-v1
 description: 4B parameter model with strong performance on reasoning benchmarks
+sidebar:
+  order: 0
+  badge:
+    text: New
+    variant: tip
 ---
 
 import { Aside } from '@astrojs/starlight/components';

website/src/content/docs/jan/mcp-examples/data-analysis/jupyter.mdx

@@ -18,17 +18,15 @@ keywords:
   ]
 ---
 
-import { Callout } from 'nextra/components'
-
-# Jupyter MCP
+import { Aside } from '@astrojs/starlight/components';
 
 [Jupyter MCP Server](https://jupyter-mcp-server.datalayer.tech/) enables real-time interaction with Jupyter notebooks, allowing AI models to edit, execute, and document code for data analysis and visualization. Instead of just generating code suggestions, AI can actually run Python code and see the results.
 
 This integration gives Jan the ability to execute analysis, create visualizations, and iterate based on actual results - turning your AI assistant into a capable data science partner.
 
-<Callout type="info">
+<Aside type="note">
 **Breaking Change**: Version 0.11.0+ renamed `room` to `document`. Check the [release notes](https://jupyter-mcp-server.datalayer.tech/releases) for details.
-</Callout>
+</Aside>
 
 ## Available Tools
 
@@ -52,9 +50,9 @@ The Jupyter MCP Server provides [12 comprehensive tools](https://jupyter-mcp-ser
 - `read_cell`: Examine specific cell content
 - `read_all_cells`: Get complete notebook state
 
-<Callout type="warning">
+<Aside type="caution">
 The MCP connects to **one notebook at a time**, not multiple notebooks. Specify your target notebook in the configuration.
-</Callout>
+</Aside>
 
 ## Prerequisites
 
@@ -161,9 +159,9 @@ Since GPT-5 is new, you'll need to manually add it to Jan:
 
 ![Manually adding GPT-5 model name](../../../../../assets/gpt5-add.png)
 
-<Callout type="info">
+<Aside type="note">
 **About GPT-5**: OpenAI's smartest, fastest, most useful model yet. It features built-in thinking capabilities, state-of-the-art performance across coding, math, and writing, and exceptional tool use abilities. GPT-5 automatically decides when to respond quickly versus when to think longer for expert-level responses.
-</Callout>
+</Aside>
 
 ### Enable Tool Calling
 
@@ -237,9 +235,9 @@ Generate two datasets representing A/B test results for an e-commerce site. Perf
 
 ## Performance Considerations
 
-<Callout type="warning">
+<Aside type="caution">
 Multiple tools can quickly consume context windows, especially for local models. GPT-5's unified system with smart routing helps manage this, but local models may struggle with speed and context limitations.
-</Callout>
+</Aside>
 
 ### Context Management
 - Each tool call adds to conversation history
@@ -254,9 +252,9 @@ Multiple tools can quickly consume context windows, especially for local models.
 
 ## Security Considerations
 
-<Callout type="warning">
+<Aside type="caution">
 MCP provides powerful capabilities but requires careful security practices.
-</Callout>
+</Aside>
 
 ### Authentication Tokens
 - **Always use strong tokens** - avoid simple passwords
@@ -334,4 +332,4 @@ The Jupyter MCP integration combined with GPT-5's advanced capabilities creates
 
 Whether you're exploring data, building models, or creating visualizations, this integration provides the computational power of Jupyter with the intelligence of GPT-5 - all within Jan's privacy-conscious interface.
 
-Remember: with great computational power comes the responsibility to use it securely. Always validate generated code, use strong authentication, and be mindful of data privacy when using cloud-based models.
+Remember: with great computational power comes the responsibility to use it securely. Always validate generated code, use strong authentication, and be mindful of data privacy when using cloud-based models.

website/src/content/docs/jan/mcp-examples/productivity/linear.mdx

@@ -13,11 +13,13 @@ keywords:
     software development,
     tool calling,
   ]
+sidebar:
+  badge:
+    text: New
+    variant: tip
 ---
 
-import { Callout, Steps } from 'nextra/components'
-
-# Linear MCP
+import { Aside } from '@astrojs/starlight/components';
 
 [Linear MCP](https://linear.app) provides comprehensive project management capabilities through natural conversation. Transform your software development workflow by managing issues, projects, and team collaboration directly through AI.
 
@@ -59,9 +61,9 @@ Linear MCP offers extensive project management capabilities:
 - Model with strong tool calling support
 - Active internet connection
 
-<Callout type="info">
+<Aside type="note">
 Linear offers a generous free tier perfect for small teams and personal projects. Unlimited users, 250 active issues, and full API access included.
-</Callout>
+</Aside>
 
 ## Setup
 
@@ -78,9 +80,9 @@ Once logged in, you'll see your workspace:
 
 ### Enable MCP in Jan
 
-<Callout type="warning">
+<Aside type="caution">
 Enable **Experimental Features** in **Settings > General** if you don't see the MCP Servers option.
-</Callout>
+</Aside>
 
 1. Go to **Settings > MCP Servers**
 2. Toggle **Allow All MCP Tool Permission** ON
@@ -128,7 +130,7 @@ You should see all Linear tools in the chat interface:
 
 Watch AI transform mundane tasks into epic narratives:
 
-![Linear MCP creating Shakespearean war epic tasks](../../../../../assets/mcplinear2.gif)
+![Linear MCP creating Shakespearean war epic tasks](/gifs/mcplinear2.gif)
 
 ## Creative Examples
 
@@ -240,9 +242,9 @@ Generate a retrospective report for our last completed cycle. List what was comp
 - Cache frequently accessed data
 - Use specific filters to reduce data
 
-<Callout type="tip">
+<Aside type="tip">
 Linear's keyboard shortcuts work great alongside MCP! Use CMD+K for quick navigation while AI handles the heavy lifting.
-</Callout>
+</Aside>
 
 ## Integration Ideas
 
@@ -265,4 +267,4 @@ Linear MCP uses OAuth for authentication, meaning:
 
 Linear MCP transforms project management from clicking through interfaces into natural conversation. Whether you're planning sprints, triaging bugs, or crafting epic development sagas, AI becomes your project management companion.
 
-Start with simple issue creation, then explore complex workflows like automated sprint planning and workload balancing. The combination of Linear's powerful platform with AI's creative capabilities makes project management both efficient and entertaining!
+Start with simple issue creation, then explore complex workflows like automated sprint planning and workload balancing. The combination of Linear's powerful platform with AI's creative capabilities makes project management both efficient and entertaining!

website/src/content/docs/jan/mcp-examples/productivity/todoist.mdx

@@ -12,11 +12,13 @@ keywords:
     todo list,
     tool calling,
   ]
+sidebar:
+  badge:
+    text: New
+    variant: tip
 ---
 
-import { Callout, Steps } from 'nextra/components'
-
-# Todoist MCP
+import { Aside } from '@astrojs/starlight/components';
 
 [Todoist MCP Server](https://github.com/abhiz123/todoist-mcp-server) enables AI models to manage your Todoist tasks through natural conversation. Instead of switching between apps, you can create, update, and complete tasks by simply chatting with your AI assistant.
 
@@ -35,9 +37,9 @@ import { Callout, Steps } from 'nextra/components'
 - Model with strong tool calling support
 - Node.js installed
 
-<Callout type="info">
+<Aside type="note">
 Todoist offers a generous free tier perfect for personal task management. Premium features add labels, reminders, and more projects.
-</Callout>
+</Aside>
 
 ## Setup
 
@@ -63,9 +65,9 @@ Once logged in, you'll see your main dashboard:
 
 ### Enable MCP in Jan
 
-<Callout type="warning">
+<Aside type="caution">
 If you don't see the MCP Servers option, enable **Experimental Features** in **Settings > General** first.
-</Callout>
+</Aside>
 
 1. Go to **Settings > MCP Servers**
 2. Toggle **Allow All MCP Tool Permission** ON
@@ -78,7 +80,7 @@ Click the `+` button to add a new MCP server:
 - **Server Name**: `todoist`
 - **Command**: `npx`
 - **Arguments**: `-y @abhiz123/todoist-mcp-server`
-- **Environment Variables**: 
+- **Environment Variables**:
   - Key: `TODOIST_API_TOKEN`, Value: `your_api_token_here`
 
 ![Todoist MCP configuration in Jan](../../../../../assets/todoist4.png)
@@ -101,7 +103,7 @@ You should see the Todoist tools in the tools panel:
 
 Now you can manage your todo list through natural conversation:
 
-![Todoist MCP in action](../../../../../assets/mcptodoist_extreme.gif)
+![Todoist MCP in action](/gifs/mcptodoist_extreme.gif)
 
 ## Example Prompts
 
@@ -241,9 +243,9 @@ I'm moving to a new apartment next month. Generate a comprehensive moving checkl
 - Space out bulk operations
 - Wait a moment between large task batches
 
-<Callout type="tip">
+<Aside type="tip">
 Todoist syncs across all devices. Tasks created through Jan instantly appear on your phone, tablet, and web app!
-</Callout>
+</Aside>
 
 ## Privacy Note
 
@@ -256,4 +258,4 @@ Combine Todoist MCP with other tools for powerful workflows:
 - Generate code with E2B, then add testing tasks to your todo list
 - Analyze data with Jupyter, then create follow-up tasks for insights
 
-Task management through natural language makes staying organized effortless. Let your AI assistant handle the overhead while you focus on getting things done!
+Task management through natural language makes staying organized effortless. Let your AI assistant handle the overhead while you focus on getting things done!

website/src/content/docs/jan/mcp-examples/search/serper.mdx

@@ -1,12 +1,14 @@
 ---
 title: Serper Search MCP
 description: Connect Jan to real-time web search with Google results through Serper API.
+sidebar:
+  badge:
+    text: New
+    variant: tip
 ---
 
 import { Aside } from '@astrojs/starlight/components';
 
-# Serper Search MCP
-
 [Serper](https://serper.dev) provides Google search results through a simple API, making it perfect for giving AI models access to current web information. The Serper MCP integration enables Jan models to search the web and retrieve real-time information.
 
 ## Available Tools

website/src/content/docs/jan/quickstart.mdx

@@ -50,7 +50,7 @@ Jan v1 achieves 91.1% accuracy on SimpleQA and excels at tool calling, making it
 2. Select your model in the input field dropdown
 3. Type your message and start chatting
 
-![Create New Thread](../../../assets/threads-new-chat-updated.png)
+![Create New Thread](../../../assets/jan_loaded.png)
 
 Try asking Jan v1 questions like:
 - "Explain quantum computing in simple terms"

website/src/content/docs/local-server/settings.mdx

@@ -16,7 +16,6 @@ keywords:
 
 import { Aside, Steps } from '@astrojs/starlight/components'
 
-# Settings
 
 Access Jan's settings by clicking the Settings icon in the bottom left corner.