janhq · ramonpzg · Aug 15, 2025 · Aug 15, 2025 · Aug 15, 2025 · Aug 15, 2025
diff --git a/docs/public/assets/images/changelog/mcp-linear.png b/docs/public/assets/images/changelog/mcp-linear.png
diff --git a/docs/public/assets/images/changelog/mcplinear2.gif b/docs/public/assets/images/changelog/mcplinear2.gif
diff --git a/docs/src/pages/_meta.json b/docs/src/pages/_meta.json
@@ -11,11 +11,6 @@
     "type": "page",
     "title": "Documentation"
   },
-  "cortex": {
-    "type": "page",
-    "title": "Cortex",
-    "display": "hidden"
-  },
   "platforms": {
     "type": "page",
     "title": "Platforms",

diff --git a/docs/src/pages/changelog/2025-08-14-general-improvs.mdx b/docs/src/pages/changelog/2025-08-14-general-improvs.mdx
@@ -0,0 +1,77 @@
+---
+title: "Jan v0.6.8: Engine fixes, new MCP tutorials, and cleaner docs"
+version: 0.6.8
+description: "Llama.cpp stability upgrades, Linear/Todoist MCP tutorials, new model pages (Lucy, Jan‑v1), and docs reorganization"
+date: 2025-08-14
+ogImage: "/assets/images/changelog/mcplinear2.gif"
+---
+
+import ChangelogHeader from "@/components/Changelog/ChangelogHeader"
+import { Callout } from 'nextra/components'
+
+<ChangelogHeader title="Jan v0.6.8: Engine fixes, new MCP tutorials, and cleaner docs" date="2025-08-14" ogImage="/assets/images/changelog/mcplinear2.gif" />
+
+## Highlights 🎉
+
+v0.6.8 focuses on stability and real workflows: major llama.cpp hardening, two new MCP productivity tutorials, new model pages, and a cleaner docs structure.
+
+
+### 🚀 New tutorials & docs
+
+- Linear MCP tutorial: create/update issues, projects, comments, cycles — directly from chat
+- Todoist MCP tutorial: add, list, update, complete, and delete tasks via natural language
+- New model pages:
+  - Lucy (1.7B) — optimized for web_search tool calling
+  - Jan‑v1 (4B) — strong SimpleQA (91.1%), solid tool use
+- Docs updates:
+  - Reorganized landing and Products sections; streamlined QuickStart
+  - Ongoing Docs v2 (Astro) migration with handbook, blog, and changelog sections added and then removed
+
+### 🧱 Llama.cpp engine: stability & correctness
+
+- Structured error handling for llama.cpp extension
+- Better argument handling, improved model path resolution, clearer error messages
+- Device parsing tests; conditional Vulkan support; support for missing CUDA backends
+- AVX2 instruction support check (Mac Intel) for MCP
+- Server hang on model load — fixed
+- Session management & port allocation moved to backend for robustness
+- Recommended labels in settings; per‑model Jinja template customization
+- Tensor buffer type override support
+- “Continuous batching” description corrected
+
+### ✨ UX polish
+
+- Thread sorting fixed; assistant dropdown click reliability improved
+- Responsive left panel text color; provider logo blur cleanup
+- Show toast on download errors; context size error dialog restored
+- Prevent accidental message submit for IME users
+- Onboarding loop fixed; GPU detection brought back
+- Connected MCP servers status stays in sync after JSON edits
+
+### 🔍 Hub & providers
+
+- Hugging Face token respected for repo search and private README visualization
+- Deep links and model details fixed
+- Factory reset unblocked; special chars in `modelId` handled
+- Feature toggle for auto‑updater respected
+
+### 🧪 CI & housekeeping
+
+- Nightly/PR workflow tweaks; clearer API server logs
+- Cleaned unused hardware APIs
+- Release workflows updated; docs release paths consolidated
+
+### 🤖 Reasoning model fixes
+
+- gpt‑oss “thinking block” rendering fixed
+- Reasoning text no longer included in chat completion requests
+
+## Thanks to new contributors
+
+· @cmppoon · @shmutalov · @B0sh
+
+---
+
+Update your Jan or [download the latest](https://jan.ai/).
+
+For the complete list of changes, see the [GitHub release notes](https://github.com/menloresearch/jan/releases/tag/v0.6.8).
diff --git a/docs/src/pages/docs/_assets/chat_jan_v1.png b/docs/src/pages/docs/_assets/chat_jan_v1.png
diff --git a/docs/src/pages/docs/_assets/creative_bench_jan_v1.png b/docs/src/pages/docs/_assets/creative_bench_jan_v1.png
diff --git a/docs/src/pages/docs/_assets/download_janv1.png b/docs/src/pages/docs/_assets/download_janv1.png
diff --git a/docs/src/pages/docs/_assets/enable_mcp.png b/docs/src/pages/docs/_assets/enable_mcp.png
diff --git a/docs/src/pages/docs/_assets/jan_v1_demo.gif b/docs/src/pages/docs/_assets/jan_v1_demo.gif
diff --git a/docs/src/pages/docs/_assets/jan_v1_serper.png b/docs/src/pages/docs/_assets/jan_v1_serper.png
diff --git a/docs/src/pages/docs/_assets/jan_v1_serper1.png b/docs/src/pages/docs/_assets/jan_v1_serper1.png
diff --git a/docs/src/pages/docs/_assets/linear1.png b/docs/src/pages/docs/_assets/linear1.png
diff --git a/docs/src/pages/docs/_assets/linear2.png b/docs/src/pages/docs/_assets/linear2.png
diff --git a/docs/src/pages/docs/_assets/linear3.png b/docs/src/pages/docs/_assets/linear3.png
diff --git a/docs/src/pages/docs/_assets/linear4.png b/docs/src/pages/docs/_assets/linear4.png
diff --git a/docs/src/pages/docs/_assets/linear5.png b/docs/src/pages/docs/_assets/linear5.png
diff --git a/docs/src/pages/docs/_assets/linear6.png b/docs/src/pages/docs/_assets/linear6.png
diff --git a/docs/src/pages/docs/_assets/linear7.png b/docs/src/pages/docs/_assets/linear7.png
diff --git a/docs/src/pages/docs/_assets/linear8.png b/docs/src/pages/docs/_assets/linear8.png
diff --git a/docs/src/pages/docs/_assets/lucy_demo.gif b/docs/src/pages/docs/_assets/lucy_demo.gif
diff --git a/docs/src/pages/docs/_assets/mcplinear2.gif b/docs/src/pages/docs/_assets/mcplinear2.gif
diff --git a/docs/src/pages/docs/_assets/mcptodoist_extreme.gif b/docs/src/pages/docs/_assets/mcptodoist_extreme.gif
diff --git a/docs/src/pages/docs/_assets/serper_janparams.png b/docs/src/pages/docs/_assets/serper_janparams.png
diff --git a/docs/src/pages/docs/_assets/serper_page.png b/docs/src/pages/docs/_assets/serper_page.png
diff --git a/docs/src/pages/docs/_assets/serper_playground.png b/docs/src/pages/docs/_assets/serper_playground.png
diff --git a/docs/src/pages/docs/_assets/simpleqa_jan_v1.png b/docs/src/pages/docs/_assets/simpleqa_jan_v1.png
diff --git a/docs/src/pages/docs/_assets/simpleqa_lucy.png b/docs/src/pages/docs/_assets/simpleqa_lucy.png
diff --git a/docs/src/pages/docs/_assets/todoist1.png b/docs/src/pages/docs/_assets/todoist1.png
diff --git a/docs/src/pages/docs/_assets/todoist2.png b/docs/src/pages/docs/_assets/todoist2.png
diff --git a/docs/src/pages/docs/_assets/todoist3.png b/docs/src/pages/docs/_assets/todoist3.png
diff --git a/docs/src/pages/docs/_assets/todoist4.png b/docs/src/pages/docs/_assets/todoist4.png
diff --git a/docs/src/pages/docs/_assets/todoist5.png b/docs/src/pages/docs/_assets/todoist5.png
diff --git a/docs/src/pages/docs/_assets/toggle_tools.png b/docs/src/pages/docs/_assets/toggle_tools.png
diff --git a/docs/src/pages/docs/_assets/turn_on_mcp.png b/docs/src/pages/docs/_assets/turn_on_mcp.png
diff --git a/docs/src/pages/docs/_meta.json b/docs/src/pages/docs/_meta.json
@@ -4,20 +4,16 @@
     "title": "Switcher"
   },
   "index": "Overview",
-  "how-to-separator": {
-    "title": "HOW TO",
+  "getting-started-separator": {
+    "title": "GETTING STARTED",
     "type": "separator"
   },
+  "quickstart": "QuickStart",
   "desktop": "Install 👋 Jan",
-  "threads": "Start Chatting",
-  "jan-models": "Use Jan Models",
+  "jan-models": "Models",
   "assistants": "Create Assistants",
-
-  "tutorials-separators": {
-    "title": "TUTORIALS",
-    "type": "separator"
-  },
-  "remote-models": "Connect to Remote Models",
+  "remote-models": "Cloud Providers",
+  "mcp-examples": "Tutorials",
 
   "explanation-separator": {
     "title": "EXPLANATION",
@@ -38,7 +34,6 @@
   },
   "manage-models": "Manage Models",
   "mcp": "Model Context Protocol",
-  "mcp-examples": "MCP Examples",
 
   "localserver": {
     "title": "LOCAL SERVER",

diff --git a/docs/src/pages/docs/index.mdx b/docs/src/pages/docs/index.mdx
@@ -1,17 +1,19 @@
 ---
 title: Jan
-description: Jan is an open-source ChatGPT-alternative and self-hosted AI platform - build and run AI on your own desktop or server.
+description: Build, run, and own your AI. From laptop to superintelligence.
 keywords:
   [
     Jan,
     Jan AI,
-    ChatGPT alternative,
-    OpenAI platform alternative,
-    local API,
+    open superintelligence,
+    AI ecosystem,
     local AI,
     private AI,
-    conversational AI,
-    no-subscription fee,
+    self-hosted AI,
+    llama.cpp,
+    Model Context Protocol,
+    MCP,
+    GGUF models,
     large language model,
     LLM,
   ]
@@ -24,123 +26,152 @@ import FAQBox from '@/components/FaqBox'
 
 ![Jan's Cover Image](./_assets/jan-app-new.png)
 
+## Jan's Goal
 
-Jan is a ChatGPT alternative that runs 100% offline on your desktop and (*soon*) on mobile. Our goal is to
-make it easy for anyone, with or without coding skills, to download and use AI models with full control and
-[privacy](https://www.reuters.com/legal/legalindustry/privacy-paradox-with-ai-2023-10-31/).
+> Jan's goal is to build superintelligence that you can self-host and use locally.
 
-Jan is powered by [Llama.cpp](https://github.com/ggerganov/llama.cpp), a local AI engine that provides an OpenAI-compatible
-API that can run in the background by default at `https://localhost:1337` (or your custom port). This enables you to power all sorts of
-applications with AI capabilities from your laptop/PC. For example, you can connect local tools like [Continue](https://jan.ai/docs/server-examples/continue-dev)
-and [Cline](https://cline.bot/) to Jan and power them using your favorite models.
+## What is Jan?
 
-Jan doesn't limit you to locally hosted models, meaning, you can create an API key from your favorite model provider,
-add it to Jan via the configuration's page and start talking to your favorite models.
+Jan is an open-source AI ecosystem that runs on your hardware. We're building towards open superintelligence - a complete AI platform you actually own.
 
-### Features
+### The Ecosystem
 
-- Download popular open-source LLMs (Llama3, Gemma3, Qwen3, and more) from the HuggingFace [Model Hub](./docs/manage-models.mdx)
-or import any GGUF files (the model format used by llama.cpp) available locally
-- Connect to [cloud services](/docs/remote-models/openai) (OpenAI, Anthropic, Mistral, Groq, etc.)
-- [Chat](./docs/threads.mdx) with AI models & [customize their parameters](/docs/model-parameters.mdx) via our
-intuitive interface
-- Use our [local API server](https://jan.ai/api-reference) with an OpenAI-equivalent API to power other apps.
+**Models**: We build specialized models for real tasks, not general-purpose assistants:
+- **Jan-Nano (32k/128k)**: 4B parameters designed for deep research with MCP. The 128k version processes entire papers, codebases, or legal documents in one go
+- **Lucy**: 1.7B model that runs agentic web search on your phone. Small enough for CPU, smart enough for complex searches
+- **Jan-v1**: 4B model for agentic reasoning and tool use, achieving 91.1% on SimpleQA
 
-### Philosophy
+We also integrate the best open-source models - from OpenAI's gpt-oss to community GGUF models on Hugging Face. The goal: make powerful AI accessible to everyone, not just those with server farms.
 
-Jan is built to be [user-owned](about#-user-owned), this means that Jan is:
-- Truly open source via the [Apache 2.0 license](https://github.com/menloresearch/jan/blob/dev/LICENSE)
-- [Data is stored locally, following one of the many local-first principles](https://www.inkandswitch.com/local-first)
-- Internet is optional, Jan can run 100% offline
-- Free choice of AI models, both local and cloud-based
-- We do not collect or sell user data. See our [Privacy Policy](./privacy).
+**Applications**: Jan Desktop runs on your computer today. Web, mobile, and server versions coming in late 2025. Everything syncs, everything works together.
+
+**Tools**: Connect to the real world through [Model Context Protocol (MCP)](./mcp). Design with Canva, analyze data in Jupyter notebooks, control browsers, execute code in E2B sandboxes. Your AI can actually do things, not just talk about them.
 
 <Callout>
-  You can read more about our [philosophy](/about#philosophy) here.
+API keys are optional. No account needed. Just download and run. Bring your own API keys to connect your favorite cloud models.
 </Callout>
 
-### Inspirations
+### Core Features
 
-Jan is inspired by the concepts of [Calm Computing](https://en.wikipedia.org/wiki/Calm_technology), and the Disappearing Computer.
+- **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
 
-## Acknowledgements
+### Growing MCP Integrations
+
+Jan connects to real tools through MCP:
+- **Creative Work**: Generate designs with Canva
+- **Data Analysis**: Execute Python in Jupyter notebooks
+- **Web Automation**: Control browsers with Browserbase and Browser Use
+- **Code Execution**: Run code safely in E2B sandboxes
+- **Search & Research**: Access current information via Exa, Perplexity, and Octagon
+- **More coming**: The MCP ecosystem is expanding rapidly
 
-Jan is built on the shoulders of many open-source projects like:
+## Philosophy
+
+Jan is built to be user-owned:
+- **Open Source**: Apache 2.0 license - truly free
+- **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 type="info">
+We're building AI that respects your choices. Not another wrapper around someone else's API.
+</Callout>
 
-- [Llama.cpp](https://github.com/ggerganov/llama.cpp/blob/master/LICENSE)
-- [Scalar](https://github.com/scalar/scalar)
+## Quick Start
+
+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)
+
+## Acknowledgements
+
+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
 
 <FAQBox title="What is Jan?">
-  Jan is a customizable AI assistant that can run offline on your computer - a privacy-focused alternative to tools like
-  ChatGPT, Anthropic's Claude, and Google Gemini, with optional cloud AI support.
+  Jan is an open-source AI ecosystem building towards superintelligence you can self-host. Today it's a desktop app that runs AI models locally. Tomorrow it's a complete platform across all your devices.
 </FAQBox>
 
-<FAQBox title="How do I get started with Jan?">
-  Download Jan on your computer, download a model or add API key for a cloud-based one, and start chatting. For
-  detailed setup instructions, see our [Quick Start](/docs/quickstart) guide.
+<FAQBox title="How is this different from other AI platforms?">
+  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.
 </FAQBox>
 
-<FAQBox title="Is Jan compatible with my system?">
-  Jan supports all major operating systems,
-  - [Mac](/docs/desktop/mac#compatibility)
-  - [Windows](/docs/desktop/windows#compatibility)
-  - [Linux](/docs/desktop/linux)
-
-  Hardware compatibility includes:
-  - NVIDIA GPUs (CUDA)
-  - AMD GPUs (Vulkan)
-  - Intel Arc GPUs (Vulkan)
-  - Any GPU with Vulkan support
+<FAQBox title="What models can I use?">
+  **Jan Models:**
+  - Jan-Nano (32k/128k) - Deep research with MCP integration
+  - Lucy - Mobile-optimized agentic search (1.7B)
+  - Jan-v1 - Agentic 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>
 
-<FAQBox title="How does Jan protect my privacy?">
-  Jan prioritizes privacy by:
-  - Running 100% offline with locally-stored data
-  - Using open-source models that keep your conversations private
-  - Storing all files and chat history on your device in the [Jan Data Folder](/docs/data-folder)
-  - Never collecting or selling your data
-
-  <Callout type="warning">
-    When using third-party cloud AI services through Jan, their data policies apply. Check their privacy terms.
-  </Callout>
-
-  You can optionally share anonymous usage statistics to help improve Jan, but your conversations are never
-  shared. See our complete [Privacy Policy](./docs/privacy).
+<FAQBox title="What are MCP tools?">
+  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.
 </FAQBox>
 
-<FAQBox title="What models can I use with Jan?">
-  - Download optimized models from the [Jan Hub](/docs/manage-models)
-  - Import GGUF models from Hugging Face or your local files
-  - Connect to cloud providers like OpenAI, Anthropic, Mistral and Groq (requires your own API keys)
+<FAQBox title="Is Jan compatible with my system?">
+  **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), 50GB storage
+  - Works with: NVIDIA (CUDA), AMD (Vulkan), Intel Arc, Apple Silicon
 </FAQBox>
 
-<FAQBox title="Is Jan really free? What's the catch?">
-  Jan is completely free and open-source with no subscription fees for local models and features. When using cloud-based
-  models (like GPT-4o or Claude Sonnet 3.7), you'll only pay the standard rates to those providers—we add no markup.
+<FAQBox title="Is Jan really free?">
+  **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>
 
-<FAQBox title="Can I use Jan offline?">
-  Yes! Once you've downloaded a local model, Jan works completely offline with no internet connection needed.
-</FAQBox>
+<FAQBox title="How does Jan protect privacy?">
+  - 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
 
-<FAQBox title="How can I contribute or get community help?">
-  - Join our [Discord community](https://discord.gg/qSwXFx6Krr) to connect with other users
-  - Contribute through [GitHub](https://github.com/menloresearch/jan) (no permission needed!)
-  - Get troubleshooting help in our [Discord](https://discord.com/invite/FTk2MvZwJH) channel [#🆘|jan-help](https://discord.com/channels/1107178041848909847/1192090449725358130)
-  - Check our [Troubleshooting](./docs/troubleshooting) guide for common issues
+  <Callout type="warning">
+    When using cloud providers through Jan, their privacy policies apply.
+  </Callout>
 </FAQBox>
 
 <FAQBox title="Can I self-host Jan?">
-  Yes! We fully support the self-hosted movement. Either download Jan directly or fork it on
-  [GitHub repository](https://github.com/menloresearch/jan) and build it from source.
+  Yes. Download directly or build from [source](https://github.com/menloresearch/jan). Jan Server for production deployments coming late 2025.
 </FAQBox>
 
-<FAQBox title="What does Jan stand for?">
-  Jan stands for "Just a Name". We are, admittedly, bad at marketing 😂.
+<FAQBox title="When will mobile/web versions launch?">
+  - **Jan Web**: Beta late 2025
+  - **Jan Mobile**: Late 2025
+  - **Jan Server**: Late 2025
+
+  All versions will sync seamlessly.
 </FAQBox>
 
-<FAQBox title="Are you hiring?">
-  Yes! We love hiring from our community. Check out our open positions at [Careers](https://menlo.bamboohr.com/careers).
+<FAQBox title="How can I contribute?">
+  - 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
 </FAQBox>
+
+<FAQBox title="Are you hiring?">
+  Yes! We love hiring from our community. Check [Careers](https://menlo.bamboohr.com/careers).
+</FAQBox>