+
+## Purpose
+
+Without Context Center, an AI assistant connected via MCP can only answer questions using what's in your data catalog: table schemas, column descriptions, lineage, and so on. But a lot of what teams actually need to know lives outside the catalog: a written data governance policy, a runbook for handling a recurring incident, an internal definition of a business metric, or a preference one person has for how they like answers formatted.
+
+Context Center gives that knowledge a home. After OpenMetadata extracts an uploaded file into shared knowledge pills, the [`search_company_context`](/v2.0.x-SNAPSHOT/how-to-guides/mcp/reference#search_company_context) and [`get_company_context`](/v2.0.x-SNAPSHOT/how-to-guides/mcp/reference#get_company_context) MCP tools can use those pills alongside catalog metadata. Articles and Memories support people and application workflows, but those tools do not currently return them.
+
+## How to Use
+
+Context Center holds three kinds of content, each suited to a different kind of knowledge:
+
+- **[Articles](/v2.0.x-SNAPSHOT/how-to-guides/context-center/articles)**: Long-form pages your team writes and maintains, such as policies, playbooks, and internal documentation.
+- **[Memories](/v2.0.x-SNAPSHOT/how-to-guides/context-center/memories)**: Short, atomic facts, such as preferences, runbook steps, and FAQs, created either by an AI assistant during a conversation or manually by a user.
+- **[Documents](/v2.0.x-SNAPSHOT/how-to-guides/context-center/documents)**: Files organized into folders. MCP search can retrieve shared knowledge pills OpenMetadata extracts from uploaded files.
+
+## When to Use
+
+- Writing or maintaining a policy, standard, or how-to guide that people should be able to find and reference: use an **Article**.
+- Capturing a quick fact, preference, or answer to a recurring question that doesn't need a full page: create a **Memory**.
+- Making an existing file, such as a PDF report, a spreadsheet, or a compliance audit, available to MCP search when OpenMetadata extracts shared knowledge pills from it: upload it as a **Document**.
+
+## Dashboard
+
+Opening **Context Center** takes you to its **Dashboard**, an at-a-glance summary of everything in your knowledge base.
+
+
+
+The Dashboard itself is a grid of six cards:
+
+- **Articles**, **Documents**, and **Memories**: One card per content type, each showing a short description of what it holds, a total count (for example, `3 Published` or `3 Files · 2 Folders`), and its three most recent items with author and last-edited time. Click **View All** on any card to open that section's full list.
+- **Recently Viewed**: The items you opened most recently across all content types, newest first.
+- **Folders**: The folders you've created to organize Documents, each showing how many files it contains.
+- **Most Cited**: Your Memories ranked by citation count, shown as `Cited N times`.
+
+Use **Upload File** or **Create** in the top-right corner to add a Document or start a new Article or Memory from anywhere on the Dashboard.
+
+
+
+## Access Control (RBAC)
+
+Documents and Memories are governed resources in OpenMetadata's role-based access control system: Documents are covered by the **File** resource (in the **Files and documents** category), and Memories by the **Context Memory** resource (in the **Misc** category). Selecting either resource in a policy rule controls who can view, create, edit, or delete that content type platform-wide, separately from any per-item sharing, such as a Memory's own Visibility setting.
+
+See [Roles and Policies](/v2.0.x-SNAPSHOT/how-to-guides/admin-guide/roles-policies) to create rules and attach policies to roles, and [Resource Scope and Operations Reference](/v2.0.x-SNAPSHOT/how-to-guides/admin-guide/roles-policies/resource-scope) for the full list of operations available on each resource.
diff --git a/v2.0.x-SNAPSHOT/how-to-guides/context-center/articles.mdx b/v2.0.x-SNAPSHOT/how-to-guides/context-center/articles.mdx
new file mode 100644
index 00000000..b2f0e81c
--- /dev/null
+++ b/v2.0.x-SNAPSHOT/how-to-guides/context-center/articles.mdx
@@ -0,0 +1,62 @@
+---
+title: Articles
+description: Long-form pages your team writes and maintains.
+sidebarTitle: Articles
+---
+
+# Articles
+
+Articles are Context Center's internal knowledge base: long-form pages your team writes, organizes, and maintains for people. Use them for durable, structured knowledge that's worth maintaining as a page, such as data governance policies, classification standards, incident playbooks, or internal API documentation.
+
+## Create an Article
+
+1. From the left sidebar, navigate to **Context Center** > **Articles**.
+
+ 
+
+2. Click **Create** and choose:
+ - **Article**: Opens a blank page in the rich text editor. Give it a title and start writing. Slash commands, text formatting, and nested lists are all supported.
+ - **Quick Link**: Bookmarks an external URL as an article instead of writing new content. Add a title, description, the target URL, and tags.
+
+ 
+
+Articles autosave as you type. There's no separate publish step.
+
+## View and Manage Articles
+
+The **Articles** list page helps you find and browse existing articles:
+
+- A search bar to look up articles by title.
+- A left-hand hierarchy panel that organizes articles into folders, so related articles, for example everything under a "Compliance" or "Engineering" folder, stay grouped together.
+- A card for each article, showing its title, a short description (or "No description" if none is set), when it was last edited, its owner, its domain, and any tags applied to it.
+- A right-hand panel with two sections:
+ - **Bookmarks**: Shows the articles you've bookmarked.
+ - **Recently Viewed**: The articles you opened most recently, newest first.
+
+
+
+Opening an article takes you to its detail page, which includes:
+
+- **Header information**: The article's domain and owner, each shown as a chip you can edit inline by clicking the pencil icon next to it. When editors are assigned, an **Editor** list appears alongside them.
+- **Save status and version**: A **Saved** indicator confirms your latest edit was captured automatically, and a version number, for example `0.2`, increases each time the article is updated, so you can track how much it's changed over time.
+- **Status badge**: If the article has an open review request, a badge such as **In Review** appears next to its title.
+- **Toolbar actions**, next to the Saved indicator:
+ - **Feedback**: Thumbs up or thumbs down on the article.
+ - **Conversation**: Open a comment thread on the article.
+ - **Favorite**: Bookmark the article so it's easy to find again later.
+ - **Copy link**: Use the copy icon to copy the article URL.
+ - **Delete**: Open the **⋮** menu and select **Delete** to remove the article.
+
+ 
+- **Content** and **Activity Feeds & Tasks** tabs:
+ - **Content** is the article body itself, where you write and edit using the rich text editor.
+ - **Activity Feeds & Tasks** tracks everything that's happened on the article, split into two views:
+ - **All**: A chronological feed of every change, who created or updated the article and when, with a short description of what changed. React to an entry with an emoji, or reply to start a thread on it.
+ - **Tasks**: Request-driven items on the article, such as an open review request, tracked separately from the general activity feed.
+
+ 
+
+ - Selecting an entry opens its details on the right, along with a **Comments** panel where you can add a comment and use `@mention` to tag a teammate.
+- **Properties panel**: Attach **Data Products**, **Reviewers**, **Tags**, a **Glossary Term**, related **Data Assets**, or **Attachments** to the article, each with its own `+` button.
+
+Quick Links, unlike written articles, show **Edit** and **Delete** icons directly on their card in the list, since there's no separate detail page to open.
diff --git a/v2.0.x-SNAPSHOT/how-to-guides/context-center/documents.mdx b/v2.0.x-SNAPSHOT/how-to-guides/context-center/documents.mdx
new file mode 100644
index 00000000..0201c603
--- /dev/null
+++ b/v2.0.x-SNAPSHOT/how-to-guides/context-center/documents.mdx
@@ -0,0 +1,53 @@
+---
+title: Documents and Archive
+description: Upload and organize files. MCP search can retrieve shared knowledge pills extracted from uploaded files.
+sidebarTitle: Documents and Archive
+---
+
+# Documents and Archive
+
+Documents let you upload files, such as reports, spreadsheets, and compliance audits, without rewriting them as an Article. When OpenMetadata extracts a file into shared knowledge pills, MCP search can retrieve the extracted content. The assistant searches the extracted pills, not the Document record itself. Organize files into folders to keep related documents together.
+
+## Upload a Document
+
+1. From the left navigation bar, navigate to **Context Center** > **Documents**.
+
+ 
+
+2. Click **Upload File**.
+
+ 
+
+3. Browse to the files on your computer and upload them.
+4. Optionally, organize the file into a folder:
+ - Click the **+** icon next to **Folder** to create a new folder.
+ - Files you don't move into a folder stay listed at the top level.
+
+## View and Manage Documents
+
+The **Documents** page shows:
+
+- **Search bar**: Search documents by file name.
+- **Folder panel**: Lists your folders on the left, each showing how many files it contains.
+ - To create a new folder, click the 
icon next to **Folder**.
+ - Click a folder to see only the files inside it.
+- **File list**: Shows the total number of files, sorted by **Recently uploaded** by default.
+- **Files Actions**:
+ - **Download**: Save a copy of the file to your local system.
+ - **Copy link**: Copy the document URL.
+ - **Three-dot (**⋮**) menu**:
+ - **Move to Folder**: Move the file into a different folder.
+ - **Delete**: Remove the file from Documents. This doesn't erase it immediately. See [Archive](#archive).
+
+ 
+
+## Archive
+
+Deleting a document moves it to **Context Center** > **Archive** instead of erasing it right away. From Archive, you can:
+
+- To restore the document, click the **Restore** icon next to the document.
+- To remove the document permanently, click the **Delete** icon next to the document.
+
+ 
+
+Archive currently holds only deleted Documents. Deleted Articles and Memories aren't tracked here.
diff --git a/v2.0.x-SNAPSHOT/how-to-guides/context-center/memories.mdx b/v2.0.x-SNAPSHOT/how-to-guides/context-center/memories.mdx
new file mode 100644
index 00000000..dbbd0246
--- /dev/null
+++ b/v2.0.x-SNAPSHOT/how-to-guides/context-center/memories.mdx
@@ -0,0 +1,83 @@
+---
+title: Memories
+description: Facts, definitions, and preferences your team can capture in Context Center.
+sidebarTitle: Memories
+---
+
+# Memories
+
+Memories are short, atomic facts, such as definitions, preferences, and answers to recurring questions, captured by your team while working with an AI assistant, or added manually. Unlike Articles, Memories aren't meant to be full pages. They're quick, reusable pieces of context. The [`create_context_memory`](/v2.0.x-SNAPSHOT/how-to-guides/mcp/reference#create_context_memory) MCP tool can create a memory when you ask an assistant to remember something. MCP company-context search currently retrieves only shared knowledge pills extracted from uploaded files; it does not retrieve manually created or remembered Memories.
+
+## Create a Memory
+
+To create a memory, follow these steps:
+
+1. From the left navigation bar, navigate to **Context Center** > **Memories**.
+
+ 
+
+2. Select **Add Memory**.
+
+ 
+
+3. In the **Add Memory** dialog, fill in the following details:
+ - **Title**: An optional label for the memory.
+ - **Memory**: Required. Describe what the assistant should remember, written in plain markdown. Click **Preview** to see how the formatted content will look. **Create Memory** stays disabled until this field has content.
+ - **Type**: Optional. Choose the kind of memory:
+ - **FAQ**: A recurring question and its answer.
+ - **Note**: A general fact worth remembering.
+ - **Preference**: A personal preference for how the assistant should behave for you.
+ - **Runbook**: A step-by-step procedure.
+ - **Use Case**: A specific scenario and how to handle it.
+ - **Linked Data Assets**: Optionally link the memory to one or more data assets using **Link an Asset**.
+ - **Metadata**:
+ - **Visibility**: Choose who can see the memory. Defaults to **Shared**.
+ - **Shared**: Visible to people or teams in the memory's shared-with list. The **Add Memory** dialog currently doesn't let you add people or teams to that list.
+ - **Entity**: Visible organization-wide to people with access to the **Context Memory** resource. It isn't limited to people viewing a linked data asset.
+ - **Private**: Visible only to you.
+ - **Tags**: Optionally tag the memory using **Add Tag**.
+
+ 
+
+4. Click **Create Memory** to save it.
+
+An AI assistant can also create memories on its own during a conversation, for example when you ask it to remember a preference.
+
+## View and Manage Memories
+
+The **Memories** page shows:
+
+- **Search bar**: Search memories by their content.
+- **Summary cards**: **Total Memories** and **Created by me**, each showing a count.
+- **Filters**: Switch between **All** and **Created by me**, or narrow the list by **All Assets** or **All Author**.
+- **Sort**: Order the list, for example by **Updated by**.
+- **Memory list**: Each row shows the author's name and avatar, when it was last updated, the memory's title, its content, and how many times it's been **Cited**, that is, how often it's actually been used to answer a question.
+- **Row actions**:
+ - **Copy link**: Copy the memory URL.
+ - **Edit**: Open the memory to change its title, content, type, visibility, tags, or linked assets.
+ - **Delete**: Open the **⋮** menu and select **Delete** to remove the memory.
+
+ 
+
+## Control Access to Memories with Roles and Policies
+
+Memories are a governed resource in OpenMetadata's role-based access control system, listed as **Context Memory** under the **Misc** resource category. Admins control who can view, create, edit, or delete memories platform-wide by adding a rule to a policy that targets the **Context Memory** resource.
+
+1. Click the **Profile** icon and navigate to **Settings** > **Access Control** > **Policies**.
+2. Open an existing policy and click **Add Rule**.
+3. Fill in the following details:
+ - **Name**: Enter a unique rule name.
+ - **Description** (optional): Add a note explaining what this rule does and why, so other admins reviewing the policy later understand its intent.
+ - **Resources**: Select `Context Memory`.
+ - **Operations**: Set the actions to allow or deny, for example `All` to cover every operation, or a specific set such as `Create` and `EditAll`.
+ - **Effect**: Select from `Allow` or `Deny`.
+ - **Condition** (optional): A CEL expression to scope the rule further, such as restricting it to a domain.
+4. Click **Save**, then attach it to the roles that should have this access.
+
+ 
+
+You can also add this rule while creating a new policy, instead of adding it to an existing one.
+
+This RBAC layer is separate from a memory's own **Visibility** setting (see [Create a Memory](#create-a-memory)): RBAC controls whether a role can interact with memories as a resource type at all, while Visibility and sharing control who can see one specific memory once it exists. Seeing a memory requires both: RBAC permission on Context Memory, and visibility into that memory, either as its owner, through its shared-with list, or because it uses **Entity** visibility.
+
+See [Roles and Policies](/v2.0.x-SNAPSHOT/how-to-guides/admin-guide/roles-policies) for how rules, policies, and roles fit together, and [Resource Scope and Operations Reference](/v2.0.x-SNAPSHOT/how-to-guides/admin-guide/roles-policies/resource-scope) for the full list of operations available on Context Memory and other resources.
diff --git a/v2.0.x-SNAPSHOT/index.mdx b/v2.0.x-SNAPSHOT/index.mdx
index 68956879..ae8d541c 100644
--- a/v2.0.x-SNAPSHOT/index.mdx
+++ b/v2.0.x-SNAPSHOT/index.mdx
@@ -250,6 +250,26 @@ Best for: Existing users
+ 
+ 
+
+
+
+
+ Context Center
+ Give your team a shared home for company knowledge. MCP assistants can search shared knowledge pills extracted from Documents alongside your metadata.
+ + Read More +
+
+
+ 
+
+
+
+
+ New Connectors
+ Ingest metadata from two new sources: Prefect for pipeline orchestration, and Omni for dashboards and analytics.
+ + Read More +
+
+
AI SDK
@@ -280,15 +300,6 @@ Best for: Existing users
-
Data Quality as Code
- Manage data quality checks using version-controlled configurations.
- - Read More -
-
-