-
-## Types of Visualizations
-
-Basic Memory can create several types of visual maps:
-
-- **Document Maps** — Visualize connections between your notes and documents
-- **Concept Maps** — Create visual representations of ideas and their relationships
-- **Process Diagrams** — Map workflows, sequences, and procedures
-- **Thematic Analysis** — Organize ideas around central themes
-
-### Relationship Networks
-
-Show how different entities relate to each other in your knowledge base.
-
-## Visualization Sources
-
-Claude can create visualizations based on:
-
-### Documents in Your Knowledge Base
-
-```example
-You: "Create a canvas showing the connections between my project planning documents"
-```
-
-### Conversation Content
-
-```example
-You: "Make a canvas visualization of the main points we just discussed"
-```
-
-### Search Results
-
-```example
-You: "Find all my notes about psychology and create a visual map of the concepts"
-```
-
-### Themes and Relationships
-
-```example
-You: "Create a visual map showing how different philosophical schools relate to each other"
-```
-
-## Visualization Workflow
-
-::steps
-### Request a visualization
-Describe what you want to see by asking Claude to create a canvas
-
-### Claude creates the canvas file
-The canvas file is automatically created in your Basic Memory directory
-
-### Open the file in Obsidian
-View the visualization in Obsidian's Canvas feature
-
-### Refine the visualization
-Ask Claude for adjustments:
-- "Could you reorganize the canvas to group related components together?"
-- "Please add more detail about the connection between these two concepts."
-
-::
-
-## Technical Details
-
-Behind the scenes, the AI:
-
-::note
-1. Creates a `.canvas` file in JSON format
-2. Adds nodes for each concept or document
-3. Creates edges to represent relationships
-4. Sets positions for visual clarity
-5. Includes any relevant metadata
-::
-
-The resulting file is fully compatible with Obsidian's Canvas feature and can be edited directly in Obsidian.
-
-## Tips for Effective Visualizations
-
-- **Be Specific** — Clearly describe what you want to visualize
-- **Specify Detail Level** — Mention how much detail you need
-- **Mention Type** — Specify the visualization type (concept map, process flow, etc.)
-- **Start Simple** — Begin with basic visualizations and ask for refinements
-
-::note
-**Provide context** about what documents or concepts to include for the best results.
-::
diff --git a/content/6.concepts/6.schema-system.md b/content/6.concepts/6.schema-system.md
index 0de665b..7e5491f 100644
--- a/content/6.concepts/6.schema-system.md
+++ b/content/6.concepts/6.schema-system.md
@@ -1,5 +1,5 @@
---
-title: Schema System
+title: Schemas
description: Define, validate, and evolve note structure in Basic Memory with schemas.
---
diff --git a/content/7.integrations/0.index.md b/content/7.integrations/0.index.md
new file mode 100644
index 0000000..d1c8eb5
--- /dev/null
+++ b/content/7.integrations/0.index.md
@@ -0,0 +1,149 @@
+---
+title: Connect AI tools
+description: Choose an AI client or extension and connect it to Basic Memory.
+---
+
+Basic Memory is most useful when the AI tools you already use can read and write the same shared knowledge base. Start with the tool you use most, then connect others to the same workspace as needed.
+
+::tip
+For Basic Memory Cloud, use the hosted MCP endpoint:
+
+```text
+https://cloud.basicmemory.com/mcp
+```
+
+For local/open-source Basic Memory, use the local MCP server from your computer. See [Local MCP tools](/local/mcp-tools-local).
+::
+
+---
+
+## Recommended Cloud Connections
+
+These are the best starting points for most Basic Memory Cloud users.
+
+:::card-group
+::card
+---
+title: Claude
+icon: i-simple-icons-anthropic
+to: /integrations/claude-desktop
+---
+Connect Claude on the web, Claude Desktop, and Claude mobile apps through a custom remote MCP connector.
+::
+
+::card
+---
+title: Claude Code
+icon: i-simple-icons-anthropic
+to: /integrations/claude-code
+---
+Give Claude Code access to shared project knowledge while you work in a repository.
+::
+
+::card
+---
+title: Codex
+icon: i-lucide-code
+to: /integrations/codex
+---
+Use Basic Memory from the Codex app, CLI, and IDE extension.
+::
+
+::card
+---
+title: ChatGPT
+icon: i-simple-icons-openai
+to: /integrations/chatgpt
+---
+Connect ChatGPT as a custom MCP app, with notes about the extra per-chat step.
+::
+:::
+
+---
+
+## Coding And Local Editors
+
+Use these when you work from a code editor, terminal agent, or synced Markdown folder.
+
+:::card-group
+::card
+---
+title: Gemini CLI
+icon: i-simple-icons-googlegemini
+to: /integrations/gemini
+---
+Connect Google's command-line AI agent through MCP.
+::
+
+::card
+---
+title: Cursor
+icon: i-lucide-mouse-pointer-2
+to: /integrations/cursor
+---
+Use Basic Memory knowledge while coding in Cursor.
+::
+
+::card
+---
+title: VS Code
+icon: i-lucide-code-2
+to: /integrations/vscode
+---
+Work with Basic Memory from VS Code and local Markdown files.
+::
+
+::card
+---
+title: Obsidian
+icon: i-lucide-notebook
+to: /integrations/obsidian
+---
+Use Obsidian as a local editor for Basic Memory Markdown projects.
+::
+:::
+
+---
+
+## Extensions And Agent Workflows
+
+These integrations add richer workflows on top of the core MCP connection.
+
+:::card-group
+::card
+---
+title: Agent Skills
+icon: i-lucide-sparkles
+to: /integrations/skills
+---
+Optional instruction packs that teach agents when and how to use Basic Memory well.
+::
+
+::card
+---
+title: OpenClaw
+icon: i-lucide-bot
+to: /integrations/openclaw
+---
+Use the OpenClaw plugin for bundled Basic Memory tools and skills.
+::
+
+::card
+---
+title: Hermes
+icon: i-lucide-send
+to: /integrations/hermes
+---
+Use Hermes for Basic Memory-aware agent workflows.
+::
+:::
+
+---
+
+## Choosing Cloud Or Local
+
+- **Use Cloud** when you want the web app, remote MCP, collaboration, and the same knowledge available from multiple tools or devices.
+- **Run locally** when you want files and indexing to stay on your machine, or when your AI client expects a local stdio MCP server.
+- **Use both** when you want Cloud for shared projects and local files for editor-first workflows.
+
+Not sure? Start with [Quickstart: Cloud](/start-here/quickstart-cloud).
diff --git a/content/7.integrations/1.claude-desktop.md b/content/7.integrations/1.claude-desktop.md
index 70e4e15..a3aae45 100644
--- a/content/7.integrations/1.claude-desktop.md
+++ b/content/7.integrations/1.claude-desktop.md
@@ -1,146 +1,76 @@
---
-title: Claude Desktop
-description: Give Claude a persistent memory that grows with every conversation.
+title: Claude
+description: Connect Claude to Basic Memory Cloud with a custom MCP connector.
---
-Claude Desktop is the flagship way to use Basic Memory. Connect once, and Claude gains full access to your knowledge base — reading, writing, searching, and building on past conversations automatically.
+Claude can use Basic Memory Cloud from Claude on the web, Claude Desktop, Cowork, and the Claude mobile apps. The connection is managed through your Claude account, so you only need to add it once.
-Basic Memory describes its tools to Claude through the Model Context Protocol, so Claude already knows how to use them. You just ask in plain language.
+::note
+**The setup is the same across Claude clients.** Add and authorize Basic Memory from claude.ai or Claude Desktop, and the connector becomes available anywhere you use the same Claude account. Mobile apps can use an existing connector, but cannot add a new custom connector.
+::
-## Cloud Setup
+## Connect Basic Memory
::steps
-### Sign Up
-Create your account at [app.basicmemory.com](https://app.basicmemory.com)
-
-### Add Remote MCP Connector
-In Claude Desktop, go to **Settings > Claude > Connectors**
+### Open connectors
-Click "Add connector" and enter:
-- **Name**: Basic Memory
-- **Remote MCP server URL**: `https://cloud.basicmemory.com/mcp`
+In Claude on the web or Claude Desktop, open **Customize -> Connectors**.
-
+On Team and Enterprise plans, an owner may need to add Basic Memory first from **Organization settings -> Connectors**.
-### Authenticate
-Click "Connect" and follow the OAuth flow to grant permissions
+### Add a custom connector
-
+Choose **Add custom connector** and enter:
-### Verify Setup
-In Claude, click the tools icon to see Basic Memory tools
+- **Name:** Basic Memory
+- **Remote MCP server URL:** `https://cloud.basicmemory.com/mcp`
-
+### Authorize access
-Try prompting: `List my projects`
+Add the connector, choose **Connect**, and complete the Basic Memory sign-in and authorization flow.
-::
+### Enable it in a conversation
-::tip
-See the [Cloud Guide](/cloud/cloud-guide) for web editor usage and troubleshooting.
+Open the **+** menu beside the message box, choose **Connectors**, and enable Basic Memory for the conversation.
::
----
-
-## Local Setup
-
-For local installation, follow the [Quickstart: Local](/start-here/quickstart-local) guide. It walks you through installing Basic Memory and configuring Claude Desktop in a few minutes.
-
----
-
-## Try It
+## Verify the connection
-Once connected, try these prompts to see Basic Memory in action:
+Ask Claude:
-**Save something from a conversation:**
-```
-Create a note summarizing what we just discussed about API rate limiting.
+```text
+List my Basic Memory projects.
```
-Claude will write a structured note with observations, tags, and relations to other topics in your knowledge base.
+Claude should use a Basic Memory tool and return the projects in your workspace.
-**Search with meaning, not just keywords:**
-```
-Find my notes about login security.
-```
+## Try it
-Even if your notes use terms like "authentication hardening" or "credential rotation," semantic search surfaces them based on meaning. See [Semantic Search](/concepts/semantic-search) for details.
-
-**Pick up where you left off:**
-```
-What have we been working on this week?
+```text
+Create a note summarizing what we just discussed, including decisions,
+open questions, and next steps.
```
-Claude checks recent activity and offers to continue any thread. Changes sync in real time — edits you make in any text editor appear instantly in your next conversation.
-
-You can also reference specific notes with `memory://` URLs. Learn more in [Memory URLs](/concepts/memory-urls).
-
----
+```text
+Find my notes about authentication and summarize the latest decisions.
+```
## Troubleshooting
-### Tools not appearing
-- **Cloud**: Re-open Claude Desktop after adding the connector. Check that the connector URL is exactly `https://cloud.basicmemory.com/mcp`.
-- **Local**: Verify `uv` is installed (`which uvx`), check config JSON syntax, and restart Claude Desktop.
-- **Advanced research is on**: Research mode runs in a separate environment that can't reach any MCP connectors. See [Claude Research Mode](/integrations/claude-research-mode).
+**Basic Memory is not listed:** Confirm the connector was added to the correct Claude account or organization.
-### Tools appear but return errors
-- Check Basic Memory is installed: `basic-memory --version`
-- Verify sync status: `basic-memory status`
-- Check file permissions in your `~/basic-memory` directory
+**Claude does not use it:** Enable Basic Memory from the conversation's Connectors menu.
-### Changes not showing up
-- Real-time sync is on by default. Run `basic-memory status` to confirm.
-- Make sure the file is in the correct project directory.
-- If needed, run the watcher manually: `basic-memory watch`
+**Authorization failed:** Remove the connector, add it again, and repeat the Basic Memory sign-in flow.
-### Project selection
-Projects are selected at the start of each conversation. For single-project setups, set a default in `~/.basic-memory/config.json`:
+**A workspace member cannot add it:** On managed Claude plans, an owner may need to add and approve the connector for the organization.
-```json
-{
- "default_project": "main"
-}
-```
-
----
-
-## Next Steps
-
-:::card-group
-::card
----
-title: User Guide
-icon: i-lucide-book-open
-to: /local/user-guide
----
-Daily workflows and usage patterns for getting the most out of Basic Memory.
+::note
+Claude's labels and settings layout may change. The durable setup is always the same: add Basic Memory as a custom remote connector, use `https://cloud.basicmemory.com/mcp`, then authorize with Basic Memory.
::
-::card
----
-title: Knowledge Format
-icon: i-lucide-file-text
-to: /concepts/knowledge-format
----
-How observations, relations, and tags create a semantic knowledge graph.
-::
-
-::card
----
-title: AI Assistant Guide
-icon: i-lucide-bot
-to: /reference/ai-assistant-guide
----
-How Claude uses Basic Memory tools under the hood.
-::
+## Next steps
-::card
----
-title: Agent Skills
-icon: i-lucide-sparkles
-to: /integrations/skills
----
-Pre-built skills that teach Claude best practices for Basic Memory.
-::
-:::
+- [MCP tools reference](/reference/mcp-tools-reference)
+- [Knowledge format](/concepts/knowledge-format)
+- [Claude Code](/integrations/claude-code)
diff --git a/content/7.integrations/11.hermes.md b/content/7.integrations/11.hermes.md
index 73325f0..047f13d 100644
--- a/content/7.integrations/11.hermes.md
+++ b/content/7.integrations/11.hermes.md
@@ -7,7 +7,7 @@ The [hermes-basic-memory](https://github.com/basicmachines-co/hermes-basic-memor
The plugin is open source — browse the source on [GitHub](https://github.com/basicmachines-co/hermes-basic-memory).
::warning
-**Slash commands need a Hermes Agent-side patch on current releases.** The plugin's agent tools (`bm_*`) and auto-capture work as documented once installed. The native `/bm-*` **slash commands**, however, do not appear in gateway sessions on Hermes Agent releases through `v0.14.0` / `v2026.5.16` (verified 2026-05-16). This is a Hermes Agent plugin-loading gap — exclusive memory-provider plugins aren't loaded during gateway slash-command discovery — not a plugin bug. The plugin ships a best-effort workaround, but it isn't sufficient for gateway startup discovery in affected builds. Until the upstream Hermes fix lands, apply the Hermes Agent-side patch documented in [MONKEYPATCH.md](https://github.com/basicmachines-co/hermes-basic-memory/blob/main/MONKEYPATCH.md). This affects only the slash-command surface; nothing else in this page depends on it.
+**Some Hermes Agent releases require an Agent-side patch for slash commands.** The plugin's `bm_*` tools and automatic capture work independently. If `/bm-*` commands do not appear in a gateway session, follow the current compatibility instructions in [MONKEYPATCH.md](https://github.com/basicmachines-co/hermes-basic-memory/blob/main/MONKEYPATCH.md).
::
::tip
@@ -135,7 +135,7 @@ Every read/write tool also accepts `project` / `project_id` for per-call routing
## Slash Commands
::note
-On Hermes Agent releases through `v0.14.0` / `v2026.5.16`, these commands require the Hermes Agent-side patch in [MONKEYPATCH.md](https://github.com/basicmachines-co/hermes-basic-memory/blob/main/MONKEYPATCH.md) — see the warning at the top of this page. The agent tools above are unaffected.
+If these commands do not appear, follow the Hermes Agent compatibility instructions in [MONKEYPATCH.md](https://github.com/basicmachines-co/hermes-basic-memory/blob/main/MONKEYPATCH.md). The agent tools above are unaffected.
::
For direct, in-session use without going through the agent:
diff --git a/content/7.integrations/12.claude-research-mode.md b/content/7.integrations/12.claude-research-mode.md
deleted file mode 100644
index 3186898..0000000
--- a/content/7.integrations/12.claude-research-mode.md
+++ /dev/null
@@ -1,82 +0,0 @@
----
-title: Claude Research Mode
-description: Why your MCP connectors (including Basic Memory) aren't available during a Claude advanced-research run — and the recommended flow for combining research with your knowledge base.
----
-
-When you turn on **advanced research**, Claude hands your request to a dedicated research agent that works across the web and Google Drive. That agent runs in its own environment and **does not have access to your connected MCP servers** — including Basic Memory, Gmail, Google Calendar, and any other connectors. This is a limitation of research mode itself, not of any individual connector: every MCP connector is unavailable during a research run, in the same way.
-
-What this means in practice:
-
-- **During a research run,** Claude can't read from or write to Basic Memory (or call any other connector's tools). It will research using web and Drive sources only.
-- **After a research run finishes,** control returns to the normal conversation — which _does_ have your connectors. At that point Claude can save the results to Basic Memory, draft an email, add a calendar event, and so on.
-
-So research and your connectors aren't combined in a single step, but they chain cleanly: **research first, then act on the results with your connectors second.**
-
----
-
-## Recommended flow: research → save to Basic Memory
-
-::steps
-### Turn advanced research on
-
-Toggle **advanced research** in the message composer, then run your query — for example, _"survey how other agent-memory tools expose graph APIs."_
-
-### Wait for the report
-
-Let the research run complete. The report comes back inline in the conversation.
-
-### Turn advanced research off
-
-Use the same toggle to drop back into normal conversation. This is the important step — leaving research on keeps connectors out of reach.
-
-### Ask Claude to save it
-
-Now you're back in the normal tool path. Ask Claude to write up the results — _"Save that as a note in my `research` project"_ — and it can call Basic Memory's [`write_note`](/reference/mcp-tools-reference#write_note) directly.
-::
-
-The same pattern works in reverse for context you already have: if you need Claude to _use_ your Basic Memory notes as input, keep research off and ask normally — Claude can read your notes and reason over them directly. Use research only when you specifically want fresh web/Drive sources.
-
-::tip
-**Which mode do I need?** If the question is "go find out what's out there on the web," use research. If it's "do something with my notes/data," keep research off.
-::
-
----
-
-## Why this happens
-
-Research mode runs a separate agent with its own toolset (web search, Google Drive). MCP connectors live on the main Claude conversation, not inside the research agent's environment. The research agent doesn't know your connectors exist, so it can't call them — and there's no way to "pass through" a connector during a research run.
-
-This is the same for **every** MCP connector, not specific to Basic Memory. If you have a workflow that wants both web research _and_ your private knowledge base in a single step, today the answer is to run them sequentially: research first, then a follow-up turn that uses your connectors on the results.
-
----
-
-## Related
-
-:::card-group
-::card
----
-title: Claude Desktop
-icon: i-lucide-monitor
-to: /integrations/claude-desktop
----
-Connect Basic Memory to Claude Desktop or Claude on the web.
-::
-
-::card
----
-title: MCP Tools Reference
-icon: i-lucide-wrench
-to: /reference/mcp-tools-reference
----
-Every tool Claude can call when research mode is off.
-::
-
-::card
----
-title: Web App
-icon: i-lucide-layout-dashboard
-to: /cloud/web-app
----
-Save and organize research results in the cloud app.
-::
-:::
diff --git a/content/7.integrations/2.claude-code.md b/content/7.integrations/2.claude-code.md
index 954cb31..e4b850f 100644
--- a/content/7.integrations/2.claude-code.md
+++ b/content/7.integrations/2.claude-code.md
@@ -1,145 +1,73 @@
---
-title: "Claude Code"
-description: "Give Claude Code persistent memory with Basic Memory. Decisions, architecture, and project context carry over across every coding session."
+title: Claude Code
+description: Connect Claude Code to Basic Memory Cloud through remote MCP.
---
-Claude Code is powerful, but every session starts from zero. Basic Memory gives it a persistent knowledge base -- so your AI remembers project decisions, code patterns, and context across every session.
+Connect Claude Code to Basic Memory Cloud to use shared project knowledge, decisions, research, and workflows while you code.
-## Cloud Setup
+## Connect Basic Memory
-::steps
-### Sign Up
-Create your account at [app.basicmemory.com](https://app.basicmemory.com).
-
-### Add Remote MCP Server
-In your terminal, add the remote MCP server:
+Run:
```bash
-claude mcp add -s user -t http basic-memory-cloud https://cloud.basicmemory.com/mcp
+claude mcp add --transport http --scope user basic-memory https://cloud.basicmemory.com/mcp
```
-### Authenticate
-Follow the OAuth flow in Claude Code to grant permissions.
+The `user` scope makes the connection available across your projects.
-### Verify
-Run `/mcp` in Claude Code and confirm Basic Memory tools are listed.
-::
+Then open Claude Code and run:
-::tip
-See the [Cloud Guide](/cloud/cloud-guide) for detailed instructions and troubleshooting.
-::
+```text
+/mcp
+```
----
+Select Basic Memory and complete the browser authorization flow.
-## Local Setup
+## Verify the connection
-Install Basic Memory locally ([Quickstart: Local](/start-here/quickstart-local)), then add it to Claude Code:
+Run `/mcp` again and confirm that Basic Memory is connected. Then ask:
-```bash
-claude mcp add basic-memory basic-memory mcp
+```text
+List my Basic Memory projects.
```
-Run `/mcp` in Claude Code to confirm the tools are available.
-
----
-
-## Try It
-
-Once connected, try these prompts in Claude Code:
+## Try it
```text
-"Create a note about our authentication strategy -- we're using JWT with
-refresh tokens, and here's why..."
+Create a note documenting the architecture decisions in this repository.
```
```text
-"Search my notes for anything related to database migration patterns"
+Search my notes for previous decisions about database migrations.
```
```text
-"What do my notes say about the API rate limiting decision we made last week?"
+Update the project note with the changes we made today.
```
-Basic Memory supports [semantic search](/concepts/semantic-search), so your queries don't need to match exact keywords -- it finds notes by meaning.
+## Claude Code instructions and Basic Memory
-For the full list of tools Claude Code can use, see the [MCP Tools Reference](/reference/mcp-tools-reference).
-
----
-
-## CLAUDE.md and Basic Memory
-
-Claude Code uses `CLAUDE.md` files for project-level instructions. Basic Memory complements this nicely: `CLAUDE.md` tells Claude Code *how* to work in a project, while Basic Memory stores the *knowledge* -- decisions, architecture notes, research, context -- that doesn't belong in a static instruction file.
-
----
-
-## Agent Skills
-
-Install [agent skills](/integrations/skills) to teach Claude Code best practices for writing well-structured notes. Skills give your AI reusable patterns so notes are consistent and useful from the start.
-
----
+Use `CLAUDE.md` for durable instructions about how Claude should work in a repository. Use Basic Memory for knowledge that grows and changes: decisions, research, meeting notes, project history, and reusable workflows.
## Troubleshooting
-**Tools not showing up in `/mcp`?**
-- For local: verify Basic Memory is installed (`basic-memory --version`) and re-add the server: `claude mcp remove basic-memory && claude mcp add basic-memory basic-memory mcp`
-- For cloud: re-run the `claude mcp add` command and complete the OAuth flow again
+**The server is missing from `/mcp`:**
-**Notes not syncing?**
-- Check sync status: `basic-memory status`
-- Look for errors in `~/.basic-memory/logs/`
-
----
-
-## FAQ
-
-### Claude Code already has CLAUDE.md and auto memory. Why add Basic Memory?
-Claude Code's built-in memory is great for project instructions and short learnings. Basic Memory adds a full knowledge base on top — searchable notes with semantic connections, observations, and relations that span across projects and AI tools. Think of CLAUDE.md as "how to work here" and Basic Memory as "everything we know." See [Using Basic Memory with Built-in AI Memory](/concepts/vs-built-in-memory) for a deeper comparison.
-
-### How does Basic Memory work alongside CLAUDE.md?
-They complement each other. `CLAUDE.md` holds project instructions and coding standards. Basic Memory holds evolving knowledge — decisions, architecture notes, research, meeting notes, and context that grows over time. Claude Code's auto memory captures small preferences; Basic Memory captures structured knowledge you can search, link, and reuse across any AI tool.
-
----
-
-::note
-**Basic Memory also works with:** [Cursor](/integrations/cursor) · [OpenAI Codex](/integrations/codex) · [Claude Desktop](/integrations/claude-desktop) · [VS Code](/integrations/vscode) · [Obsidian](/integrations/obsidian)
-::
+```bash
+claude mcp list
+```
-## Next Steps
+If necessary, remove it and add it again:
-:::card-group
-::card
----
-title: Project Documentation
-icon: i-lucide-folder-kanban
-to: /how-to/project-documentation
----
-Learn how to document your development projects.
-::
+```bash
+claude mcp remove basic-memory
+claude mcp add --transport http --scope user basic-memory https://cloud.basicmemory.com/mcp
+```
-::card
----
-title: MCP Tools Reference
-icon: i-lucide-wrench
-to: /reference/mcp-tools-reference
----
-Full reference for all 17 Basic Memory tools.
-::
+**Authorization needs to be repeated:** Open `/mcp`, select Basic Memory, and use the authentication controls to clear or restart authorization.
-::card
----
-title: Agent Skills
-icon: i-lucide-sparkles
-to: /integrations/skills
----
-Pre-built skills that teach Claude Code best practices for Basic Memory.
-::
+## Next steps
-::card
----
-title: Knowledge Format
-icon: i-lucide-file-text
-to: /concepts/knowledge-format
----
-Structure effective development documentation.
-::
-:::
+- [Project documentation](/how-to/project-documentation)
+- [MCP tools reference](/reference/mcp-tools-reference)
+- [Agent skills](/integrations/skills)
diff --git a/content/7.integrations/3.chatgpt.md b/content/7.integrations/3.chatgpt.md
index 126d829..a737550 100644
--- a/content/7.integrations/3.chatgpt.md
+++ b/content/7.integrations/3.chatgpt.md
@@ -1,100 +1,86 @@
---
title: ChatGPT
-description: Use ChatGPT with Basic Memory Cloud for MCP-powered knowledge access
+description: Connect ChatGPT to Basic Memory Cloud as a custom MCP app.
---
-ChatGPT supports remote MCP servers, giving it access to your Basic Memory knowledge base. Since ChatGPT only connects to remote servers, **Basic Memory Cloud is required**.
+ChatGPT connects to Basic Memory as a custom app backed by its remote MCP server.
-## Cloud Setup
+::tip
+**For the smoothest experience with a ChatGPT account, we recommend [Codex](/integrations/codex).** Codex treats MCP servers as part of its persistent tool configuration, making Basic Memory readily available across new threads. Standard ChatGPT requires you to add Basic Memory to each chat where you want to use it.
+::
+
+::note
+**Configure Basic Memory on the web.** Developer mode and custom app creation are managed at [chatgpt.com](https://chatgpt.com). Once connected, Basic Memory can be used in ChatGPT on the web and in the ChatGPT desktop app. Custom MCP apps are not currently available on mobile.
+::
+
+::note
+OpenAI is still rolling out full MCP support. Full read and write access is currently intended for ChatGPT Business, Enterprise, and Edu workspaces. Pro users can use custom apps with more limited read and fetch access. Workspace administrators control availability on managed plans.
+::
+
+## Connect Basic Memory
::steps
-### Sign Up
+### Open ChatGPT on the web
-Create your account at [app.basicmemory.com](https://app.basicmemory.com).
+Go to [chatgpt.com](https://chatgpt.com). Custom MCP apps are created and managed from the web interface, even if you plan to use Basic Memory in the desktop app.
-### Get Your MCP Endpoint
+### Enable developer mode
-Your remote MCP URL: `https://cloud.basicmemory.com/mcp`
+In ChatGPT on the web, open **Settings -> Apps -> Advanced settings** and enable developer mode.
-### Configure ChatGPT
+On managed workspaces, an administrator may first need to allow custom MCP apps under workspace permissions.
-In ChatGPT, go to **Settings > Developer > Custom MCP Servers** and add:
+### Create the app
-- **Name**: Basic Memory
-- **Server URL**: `https://cloud.basicmemory.com/mcp`
+Open **Settings -> Apps -> Create** and enter:
-### Authenticate
+- **Name:** Basic Memory
+- **MCP server URL:** `https://cloud.basicmemory.com/mcp`
+- **Authentication:** OAuth
-Follow the OAuth flow to grant ChatGPT access to your Basic Memory account.
+### Authorize access
-### Enable in Conversations
+Complete the Basic Memory sign-in flow and allow ChatGPT to discover the available tools.
-When chatting, enable Basic Memory from the MCP server selector to start using your knowledge base.
-::
+### Add Basic Memory to a chat
-::tip
-See the [Cloud Setup Guide](/cloud/cloud-guide) for detailed instructions.
+Start a chat, open the **+** menu, choose **More**, and select Basic Memory. ChatGPT only gives the current chat access to apps you add to it.
::
-## Try It
+
-Once connected, ask ChatGPT to work with your knowledge base:
+You need to add Basic Memory again when you start another chat. This extra per-chat step is the main reason we recommend Codex for people who want Basic Memory available throughout an ongoing AI-assisted workflow.
-- **Search**: "Find my notes about authentication design"
-- **Retrieve**: "Show me the full contents of my API documentation"
-- **Semantic search**: "Find notes conceptually related to microservice architecture" (requires full MCP access)
+## Verify the connection
-ChatGPT will call the appropriate tools behind the scenes, searching and fetching documents as needed.
+Ask:
-## Important Notes
+```text
+List my Basic Memory projects.
+```
-::warning
-**ChatGPT Plus or Pro subscription required.** MCP integration is not available on ChatGPT's free tier.
-::
+When the connection is working, ChatGPT shows that it called a tool and answers using your Basic Memory knowledge.
-::note
-**Default vs full MCP access**
+
-By default, ChatGPT exposes two tools: `search` for finding content and `fetch` for retrieving documents. To unlock all 17+ MCP tools — including `write_note`, `edit_note`, semantic search with text/vector/hybrid modes, and project management — explicitly enable the Basic Memory MCP server in ChatGPT's developer settings.
+For a workspace with full MCP access, also test:
-See the [MCP Tools Reference](/reference/mcp-tools-reference) for full tool documentation and the [Semantic Search](/concepts/semantic-search) guide for search mode details.
-::
+```text
+Create a note titled "ChatGPT connection test."
+```
## Troubleshooting
-**"MCP server not available"** — Confirm you have a ChatGPT Plus or Pro subscription. MCP is not available on the free tier.
-
-**Authentication errors** — Re-add the MCP server in ChatGPT settings and complete the OAuth flow again.
+**Developer mode is unavailable:** Your ChatGPT plan, workspace role, or administrator policy may not permit custom apps.
-**No results returned** — Make sure your Basic Memory Cloud account has synced content. Check your project at [app.basicmemory.com](https://app.basicmemory.com).
+**Basic Memory can search but cannot write:** Your current ChatGPT plan or workspace configuration may expose only read and fetch actions.
-## Next Steps
+**The tool list is outdated:** Managed ChatGPT workspaces may use an approved snapshot of an app's tools. An administrator may need to refresh and republish the app.
-:::card-group
-::card
----
-title: Cloud Setup Guide
-icon: i-lucide-cloud
-to: /cloud/cloud-guide
----
-Detailed cloud configuration and sync options.
-::
+**Authorization failed:** Remove the app, create it again, and repeat the Basic Memory OAuth flow.
-::card
----
-title: MCP Tools Reference
-icon: i-lucide-wrench
-to: /reference/mcp-tools-reference
----
-Complete documentation for all 17+ MCP tools.
-::
+## Next steps
-::card
----
-title: Claude Desktop
-icon: i-lucide-message-square
-to: /integrations/claude-desktop
----
-Full local and remote MCP integration.
-::
-:::
+- [MCP tools reference](/reference/mcp-tools-reference)
+- [Knowledge format](/concepts/knowledge-format)
+- [Cloud Overview](/cloud/cloud-guide)
diff --git a/content/7.integrations/4.gemini.md b/content/7.integrations/4.gemini.md
index e1e5f5a..f90a817 100644
--- a/content/7.integrations/4.gemini.md
+++ b/content/7.integrations/4.gemini.md
@@ -1,165 +1,57 @@
---
-title: Google Gemini
-description: Connect Basic Memory to Google Gemini CLI for persistent knowledge across AI sessions
+title: Gemini CLI
+description: Connect Gemini CLI to Basic Memory Cloud through remote MCP.
---
-Google Gemini has native MCP support, so connecting it to Basic Memory takes a single command.
+Gemini CLI supports remote HTTP MCP servers, so it can connect directly to Basic Memory Cloud.
-## Cloud Setup
+## Connect Basic Memory
-No local install needed -- Basic Memory Cloud gives you hosted MCP access.
-
-::steps
-### Sign Up
-Create your account at [app.basicmemory.com](https://app.basicmemory.com).
-
-### Add the Remote MCP Server
+Run:
```bash
-gemini mcp add -t http basic-memory-cloud https://cloud.basicmemory.com/mcp
+gemini mcp add basic-memory https://cloud.basicmemory.com/mcp --transport http --scope user
```
-### Authenticate
-Follow the OAuth flow to grant Gemini access to your Basic Memory account.
+Complete the authorization flow when Gemini prompts you to sign in.
-### Verify
+## Verify the connection
```bash
gemini mcp list
```
-You should see `basic-memory-cloud` with Connected status.
-::
-
-::tip
-See the [Cloud Setup Guide](/cloud/cloud-guide) for detailed instructions and troubleshooting.
-::
-
----
-
-## Local Setup
-
-### Video Tutorial
+Basic Memory should appear as a connected HTTP server. Then start Gemini and ask:
-Watch this quick guide to get started with Basic Memory and Google Gemini:
-
-
-
-### Configure Gemini
-
-::steps
-### Install
-
-```bash
-gemini mcp add basic-memory bash -c "uvx basic-memory mcp"
+```text
+List my Basic Memory projects.
```
-### Verify
+## Try it
-```bash
-gemini mcp list
-```
-
-You should see `basic-memory` listed with Connected status.
-::
-
-::tip
-To target a specific project:
-```bash
-gemini mcp add basic-memory bash -c "uvx basic-memory mcp --project your-project-name"
+```text
+Create a note explaining the decisions we made in this session.
```
-To install globally for your user profile, add the `-s user` flag:
-```bash
-gemini mcp add -s user basic-memory bash -c "uvx basic-memory mcp"
+```text
+Search my notes for research related to this project.
```
-::
-
----
-
-## Try It
-
-Once Gemini is connected, give these a spin:
-
-**Save a decision**
-```
-"Create a note about our decision to use JWT-based auth for the API,
-including the trade-offs we discussed."
-```
-
-**Pick up where you left off**
-```
-"What have I been working on this week? Check recent activity."
-```
-
-**Semantic search**
-```
-"Search my notes for anything related to database migration strategies."
-```
-
-For the full list of available tools, see the [MCP Tools Reference](/reference/mcp-tools-reference).
-
----
## Troubleshooting
-**Gemini can't find Basic Memory** -- Verify it's installed (`basic-memory --version`), then check `gemini mcp list`. If the entry looks wrong, remove and re-add it:
+**Basic Memory is not connected:**
+
```bash
gemini mcp remove basic-memory
-gemini mcp add basic-memory bash -c "uvx basic-memory mcp"
+gemini mcp add basic-memory https://cloud.basicmemory.com/mcp --transport http --scope user
```
-**memory:// URLs not resolving** -- Make sure the note exists in your current project and that sync is running (`basic-memory status`).
-
-**Notes not updating** -- Check file permissions in your knowledge base directory and look for errors in `~/.basic-memory/logs`.
+**The connection changed but Gemini still shows the old state:** Restart Gemini or use `/mcp reload` in an active session.
----
-
-## Next Steps
-
-:::card-group
-::card
----
-title: Project Documentation
-icon: i-lucide-folder-kanban
-to: /how-to/project-documentation
----
-Learn how to document your projects.
-::
-
-::card
----
-title: Research & Learning
-icon: i-lucide-graduation-cap
-to: /how-to/research-learning
----
-Build knowledge from your sessions.
-::
+**Authorization failed:** Remove the server, add it again, and repeat the browser sign-in flow.
-::card
----
-title: MCP Tools Reference
-icon: i-lucide-wrench
-to: /reference/mcp-tools-reference
----
-See every tool Basic Memory exposes.
-::
+## Next steps
-::card
----
-title: Knowledge Format
-icon: i-lucide-file-text
-to: /concepts/knowledge-format
----
-Structure effective documentation.
-::
-:::
+- [MCP tools reference](/reference/mcp-tools-reference)
+- [Research and learning](/how-to/research-learning)
+- [Knowledge format](/concepts/knowledge-format)
diff --git a/content/7.integrations/5.codex.md b/content/7.integrations/5.codex.md
index 0feb535..6065fa2 100644
--- a/content/7.integrations/5.codex.md
+++ b/content/7.integrations/5.codex.md
@@ -1,249 +1,120 @@
---
-title: "OpenAI Codex"
-description: "Give OpenAI Codex persistent memory with Basic Memory and MCP. Architecture decisions, API designs, and project context follow you across every session — in the Codex app and the Codex CLI."
+title: Codex
+description: Connect the Codex app and CLI to Basic Memory Cloud through MCP.
---
-OpenAI Codex is a powerful coding agent, but it starts fresh every time. Basic Memory gives it persistent context through MCP — architecture decisions, API designs, and project knowledge carry over between sessions. Notes created in Codex are immediately available in Claude Code, Cursor, Claude Desktop, or any other MCP client.
+Codex can use Basic Memory while planning, coding, reviewing, and working across applications. The Codex desktop app, CLI, and IDE extension share MCP configuration on your computer.
-Codex comes in two forms, and both connect to Basic Memory:
-
-- **Codex app** — the agent inside ChatGPT (or the Codex desktop app)
-- **Codex CLI** — the terminal-based coding agent
-
-Each one can connect to either a **local** Basic Memory (running on your machine) or **Basic Memory Cloud** (remote MCP). Pick the combination that fits your workflow.
-
-::tip
-**Cloud is the easiest path for the Codex app.** App clients only speak HTTP/SSE, so connecting to Basic Memory Cloud takes one URL and a sign-in — no local servers to keep running.
-::
-
----
-
-## Codex app
-
-The Codex app talks to MCP servers over HTTP, so you give it a URL.
-
-### Connect to Basic Memory Cloud (remote MCP)
+## Codex desktop
::steps
-### Get your MCP endpoint
+### Open MCP settings
-Your Basic Memory Cloud URL is:
+In the Codex app, open **Settings -> Integrations & MCP**.
-```
-https://cloud.basicmemory.com/mcp
-```
+### Add Basic Memory
-### Add it in Codex
+Choose the option to add a custom MCP server and enter:
-In the Codex app, open **Settings → Connectors → Custom MCP** (the exact label may be "MCP Servers" or "Developer → MCP" depending on your version) and add:
+- **Name:** Basic Memory
+- **URL:** `https://cloud.basicmemory.com/mcp`
-- **Name**: Basic Memory
-- **Server URL**: `https://cloud.basicmemory.com/mcp`
+### Authorize access
-### Authenticate
+Save the server. Codex opens the Basic Memory authorization flow when the connection requires OAuth.
-Sign in to authorize Codex. Basic Memory Cloud uses OAuth — when prompted, complete the sign-in flow in your browser.
+### Start a new thread
-### Enable in conversations
+Open a new Codex thread after the connection is authorized, then ask:
-Turn on the Basic Memory connector for the conversation, and Codex can read, write, and search your notes.
-::
-
-### Connect to a local Basic Memory (local MCP)
-
-To point the app at a Basic Memory running on your own machine, start a local HTTP MCP server, then add its URL to Codex:
-
-::steps
-### Start a local server
-
-```bash
-basic-memory mcp --transport streamable-http --port 8000
+```text
+List my Basic Memory projects.
```
-
-This exposes Basic Memory at `http://localhost:8000/mcp`.
-
-### Add it in Codex
-
-In Codex's MCP/connector settings, add:
-
-- **Name**: Basic Memory (local)
-- **Server URL**: `http://localhost:8000/mcp`
::
-::note
-Local MCP for an app means keeping that `basic-memory mcp` process running while you use Codex. For most app users, the Cloud setup is simpler.
-::
-
----
+The app stores this connection in `~/.codex/config.toml`, so it is also available to the Codex CLI and IDE extension.
## Codex CLI
-The [Codex CLI](https://github.com/openai/codex) can spawn local MCP servers as subprocesses **or** connect to a remote MCP endpoint via its config file.
-
-### Local MCP
-
-::steps
-### Add Basic Memory as a local MCP server
+You can configure the same connection from a terminal:
```bash
-codex mcp add basic-memory bash -c "uvx basic-memory mcp"
+codex mcp add basic-memory --url https://cloud.basicmemory.com/mcp
```
-::tip
-To lock it to a specific project, add the `--project` flag:
+Authorize the connection:
```bash
-codex mcp add basic-memory bash -c "uvx basic-memory mcp --project your-project-name"
+codex mcp login basic-memory
```
-::
-### Verify
+Complete the Basic Memory sign-in flow in your browser.
+
+Verify the connection:
```bash
codex mcp list
```
-You should see `basic-memory` listed with the command `bash -c uvx basic-memory mcp`.
-::
-
-#### Video walkthrough
-
-
-
-### Remote MCP (Basic Memory Cloud)
-
-::steps
-### Get an API key
-
-Create one in the [web app](https://app.basicmemory.com) under **Settings → API Keys**. See the [API Keys guide](/cloud/api-keys) for details.
-
-### Export it
+Then open a new Codex session and ask:
-Add the key to your shell profile (`~/.zshrc` or `~/.bashrc`):
-
-```bash
-export BASIC_MEMORY_API_KEY=