AI Sidebar
Your writing just got four expert assistants. The AI Sidebar in Ritemark gives you instant access to the Ritemark Agent for quick text edits, Claude Code for deep document restructuring, OpenAI Codex for code-aware writing tasks, and as of v1.7.3 the new OpenCode bring-your-own-key runtime that lets you reuse any API key you already have. Switch between them with a dropdown — they all share the same unified interface.
Four Agents, One Sidebar
The AI Sidebar hosts four different AI assistants, each with its own strengths. You pick the right tool for the job, and they all work directly with your documents.
Ritemark Agent is the built-in assistant. It's perfect for quick text operations like rephrasing paragraphs, finding and replacing text, or inserting new content at specific positions. No setup required beyond an OpenAI API key.
Claude Code is Anthropic's autonomous coding agent, but it works just as well for writing. Use it when you need to restructure entire documents, research topics and expand sections, or make complex multi-file changes. It reads your files, understands context, and executes changes directly.
OpenAI Codex is OpenAI's coding agent. It's particularly strong for technical documentation, code-heavy content, and API docs. Requires a ChatGPT Plus, Pro, Team, or Business subscription. As of v1.7.0, Codex is a stable agent in Settings, no longer flagged as experimental. The compatibility probe now tries both argv shapes, so the spurious "Some agent features are unavailable" banner is gone.
OpenCode (v1.7.3, bring-your-own-key) is the third chat runtime, integrated via the Agent Client Protocol alongside Claude Code and Codex. Configure your own API key for OpenAI, Google AI, Anthropic, or OpenRouter in Settings → OpenCode, and the model picker gains an OpenCode group with every provider you have configured. See Setup OpenCode for the full key-setup walkthrough and the File Change Approval flow.
To switch agents, click the dropdown at the top of the AI sidebar and select the one you need.
As of v1.6.3, a single conversation can use multiple runtimes. Start a thread with Claude and send the next message through Codex, and both turns stay in the same thread. Every assistant response carries a small provenance line that tells you which runtime and model produced it.
As of v1.8.0, the old Codex-only Edit/Plan toggle is replaced by a single approval policy — Auto, Ask, or Plan — that means the same thing across all three runtimes. See One Approval Policy below.
You can also pin any agent from the Agent Library for the conversation by right-clicking it and choosing Launch Chat. The pinned agent shows up as an indigo chip in the composer.
Browser-Aware AI Chat
As of v1.7.0, the AI sidebar can see what's on screen in the integrated browser, but only after you say yes.
When a browser tab is open in Ritemark, the composer shows a "Share with Agent?" prompt. Accept it and the next AI turn receives the page URL, title, and ARIA outline of the page. A small globe icon chip appears in the composer to show you exactly what the agent is seeing. Nothing reaches the AI until you allow it, and you can revoke sharing for any turn.
There's also a camera icon in the browser toolbar. Click it and Ritemark attaches a viewport screenshot to your next AI message, so you can ask the agent about something visual on the page. This is annotation mode, and it's a one-shot per turn.
This works the same with Claude and Codex. The browser context follows the conversation, not the runtime.
Live screenshot chip in the composer (v1.7.3)
When annotation mode is on, the composer used to show a plain URL chip — which was misleading, because what actually gets attached to your prompt is a screenshot of the page, not the URL. As of v1.7.3 the composer shows a live 56×56 screenshot thumbnail chip in place of the URL chip whenever annotation mode is active. The thumbnail refreshes about every five seconds as you scroll or interact with the page, so it always previews what the AI will receive on the next turn. Dismiss the chip with × to drop the browser context for that prompt.
browser_snapshot — agents can re-observe pages (v1.7.3)
Agents working with the integrated browser used to have only one way to "look at" a page after a click or a form-fill: navigate to it again, losing page state. v1.7.3 adds a browser_snapshot tool that returns the current ARIA outline of the active tab — URL, title, and full accessibility tree — without navigating.
The tool surfaces as mcp__ritemark_browser__browser_snapshot for Claude Code and as ritemark_browser_snapshot for Codex. It is read-only and consent-aware: an unshared tab returns an error, and no URL, title, or page content leaks. Snapshots stay subject to the same per-tab read consent as everything else in browser-aware chat. Full setup details in the In-App Browser article.
Browser control (v1.7.1, macOS, opt-in)
In v1.7.1, the AI sidebar can also act on the browser tab — not just read it. There are five new tools: navigate, click, fill, type, and scroll. The AI can open a URL, click a button, fill a form, type into a field, and scroll the page. The browser tab stays visible the whole time so you see every action as it happens.
This is gated behind a dedicated "Allow AI to control this browser tab?" dialog, separate from the v1.7.0 read-share prompt. Reading the page and typing into the page are two different decisions, and Ritemark treats them that way. Revoking read consent also revokes control consent — the AI cannot act on a page it cannot see.
The feature is off by default. To enable it, add "ritemark.features.browser-agent-control": true to settings.json. macOS only, marked experimental. Under the hood, Claude Code SDK sees the tools as mcp__ritemark_browser__* and Codex App Server sees them as ritemark_browser_*. Full setup details in the In-App Browser article.
Chat History
The History panel in the AI sidebar lists every saved conversation, so you can jump back to a previous thread without losing context. Click an entry to reopen it; the runtime and model that produced each turn are still visible from the provenance line.
In v1.7.1, the History panel reloads the conversation list whenever the workspace context loads. Earlier builds loaded the list only once on startup, so older conversations were saved correctly but never appeared in the panel until a restart. They are all visible now.
While we're here: code-block copy buttons, "Copy as Markdown" in the export menu, and Cmd+C/Cmd+V inside table cells also work properly in v1.7.1. The clipboard now routes through the extension host instead of the sandboxed webview, so the copy and paste actions that silently failed before now succeed.
Keep Typing While the Agent Runs (v1.7.3)
The composer no longer locks during an agent run. Type a follow-up while Claude Code, Codex, or OpenCode is still working and press Enter — instead of being dropped or blocked, the prompt parks in a "Queued" notch above the input, the same visual pattern you already know from "Working on selected text." The moment the current run finishes, the queued prompt auto-sends.
One queued prompt at a time. Changed your mind? Click the × on the Queued notch and the prompt is cleared before it ever sends. Richer queue controls — removing, editing, or promoting queued prompts, and queueing more than one — are on the roadmap.
One Approval Policy: Auto, Ask, Plan
As of v1.8.0, the composer has a single mode picker — Auto · Ask · Plan — that applies identically to all three runtimes (Claude Code, Codex, and OpenCode). You choose it per conversation, right where you type. This replaces the old Codex-only Edit/Plan toggle.
What each mode does:
- Auto (default) — the agent acts without asking. It edits files and runs commands directly, with no approval prompts. This is the behavior Claude Code already had.
- Ask — before the agent writes a file or runs a shell command, an approval card appears with Approve / Reject. You review every change before it happens.
- Plan — the agent proposes a plan first and waits for your approval before doing anything. Once you approve the plan, it executes.
Because all three runtimes now share one approval gate, an Ask prompt from Codex looks and works exactly like one from OpenCode or Claude Code. The approval card offers just Approve and Reject.
Note: OpenCode has no native plan mode, so choosing Plan for an OpenCode conversation behaves like Ask — you approve each action as it comes.
Plan Mode
Plan mode is the Plan approval policy described above. Sometimes you want to see what the AI intends to do before it does it.
You can also type "plan first" or "show me the plan" in your prompt, and the agent will outline its intended actions as numbered steps. You'll see exactly what changes it plans to make before any files are touched.
Once you review the plan, you have two options: Approve to let the agent proceed, or Reject to cancel and try a different approach. This gives you full control over complex operations.
As of v1.7.3, the plan-approval card is redesigned and reliable. The Approve/Reject buttons now render only while the agent is genuinely blocked waiting on your call — no more clicking buttons that silently did nothing after the approval window had closed. The card uses a flat single-level layout, the Approve button gets a clear indigo primary call-to-action, and the full plan text is shown (previous versions truncated to the last section). The plan content itself is taken straight from Claude Code's plan-approval request, so the card always shows the actual plan, not an empty body with two buttons.
Tip: Plan Mode is especially useful with Claude Code, Codex, and OpenCode when you're asking for significant document restructuring. Review the plan to make sure it matches your intent before approving.
Scheduled AI Agents (v1.8.0)
As of v1.8.0, an AI agent can run on a schedule while Ritemark is open. Set it up once and the agent runs headlessly at the time you choose — a daily briefing every morning, a weekly summary every Friday, a recurring report.
There are two ways to schedule an agent:
- The Schedule picker in the Agent editor. Open an agent and choose Interval mode (every N minutes or hours, from presets) or Days mode (weekday chips Mon–Sun, with Every day / Weekdays / Weekends presets, plus a time of day). A plain-English summary reads back what you picked — "Runs daily at 09:00" — so there's no guessing. Everything is in local time. If you actually want raw cron, there's an Advanced escape hatch, but you never need it.
- A
schedule:block in the agent's.mdfile. Add the block directly to the agent file. Edits take effect live, with no restart.
Safe by default. A scheduled run happens without you watching, so Ritemark is conservative: scheduled runs auto-approve file reads but block file writes and shell commands until you grant a one-time approval. If a run tries to write a file or run a command, it stops and adds an amber "needs review" row in the Agent Library's SCHEDULED section. Click Review & approve, confirm the exact blocked action, and the agent re-runs with that single action allowed — once. Future runs stay restricted.
Always visible. The status bar shows live scheduling state: "N scheduled" when idle, a spinner with the task label while a run is in progress, and amber "N needs review" when something is waiting on you. When a run finishes, a completion toast shows the first line of the agent's output with Open result and Show runs buttons.
Scheduled runs are isolated, fresh sessions — they never touch your interactive conversations. Their run history (the last 10 runs per task) lives in its own SCHEDULED section in the Agent Library and persists across restarts.
One limitation to know: scheduled tasks run only while Ritemark is open. There is no background OS daemon yet.
File Attachments for Every Runtime (v1.8.0)
You could already attach images, PDFs, and text files to Claude Code prompts. As of v1.8.0, the same attachment picker works for Codex and OpenCode too.
The picker UI doesn't change — it already worked. What changed is that the files now reach the agent. Claude Code passes them natively. Codex and OpenCode inline PDFs and text files into the prompt so the agent can read the content, and send images as attachments when the selected provider supports them. When OpenCode has to downgrade an attachment type, it shows a notice in the progress stream.
Interactive Questions
AI agents don't always have enough context to complete your request perfectly. Instead of guessing, they now ask clarifying questions mid-task.
When an agent needs more information, it pauses and presents you with selectable options. Pick the one that fits, or choose "Other" to type a custom response. This back-and-forth dialogue helps the agent understand exactly what you want.
For example, if you ask Claude Code to "improve this document," it might ask: "What aspect should I focus on?" with options like "Make it more concise," "Add more technical detail," or "Improve the structure."
File Context Menu
Getting files into your AI conversation is now as easy as right-clicking.
In the Explorer sidebar, right-click any file or folder and select "Send to AI Chat". The file appears as a context chip in your conversation, and the agent can read and reference it directly.
The active file chip automatically shows whichever document you're currently editing. This means the AI always knows what file you're working on without you having to specify it.
RiteMark uses smart deduplication to prevent the same file from being added multiple times. If you accidentally send the same file twice, it recognizes the duplicate and keeps your context window clean.
You can also drag and drop file paths directly into the chat input. All three agents support this workflow.
Context Window Protection
Every AI has a limited context window - the amount of text it can "remember" at once. RiteMark now helps you stay within those limits.
The usage bar at the top of the sidebar shows your estimated context usage. It turns yellow at 60% and red at 80%, giving you visual feedback as your conversation grows.
When you hit 70%, a warning banner appears suggesting you use /compact to summarize the conversation or start a fresh one. This keeps your AI responsive and prevents the dreaded mid-conversation memory loss.
If you push past the limit, RiteMark shows an overflow explanation with a clear "Start Fresh" button. No confusion about what went wrong - just a clear path forward.
Ritemark Agent Tools
The built-in Ritemark Agent includes specialized text editing tools that work with your selected text.
Rephrase Text
Select text in your document and ask the agent to rewrite it. Try prompts like "make this shorter," "more formal," or "simplify for a general audience." The agent rewrites just the selected portion while preserving everything else.
Find and Replace
Replace every occurrence of a word or phrase across your document. Type something like "replace 'user' with 'customer'" and the agent handles all instances at once.
Insert Text
Add new content at specific positions. Ask to "add a summary at the start" or "insert a bullet list after the introduction." The agent figures out the right location and inserts your content.
Setting Up Each Agent
Ritemark Agent
The built-in assistant works with your OpenAI API key. If you haven't set one up yet, head to Set Up AI for instructions. Once configured, Ritemark Agent is ready to use immediately.
Claude Code
Claude Code requires a one-time installation:
- Open the terminal in RiteMark (View menu or the
>_icon) - Install the CLI:
npm install -g @anthropic-ai/claude-code - Run
claudeand follow the authentication prompts - Select "Claude Code" from the agent dropdown in the sidebar
Claude Code uses your Anthropic account. You can sign up at anthropic.com if you don't have one.
As of v1.5.0, there is a dedicated Claude Account section in Settings where you can see your authentication method, CLI version, and billing source at a glance. Settings and the AI sidebar sync in real time, so any status change appears immediately in both places. On Windows, binary detection issues that affected earlier versions have been fixed, including .cmd/.exe shim resolution.
OpenAI Codex
Codex requires both CLI installation and a paid ChatGPT subscription:
- Install the CLI:
npm install -g @openai/codex - Go to RiteMark Settings and sign in with your ChatGPT account (OAuth)
- Select "Codex" from the agent dropdown
Note: Codex requires ChatGPT Plus, Pro, Team, or Business. Free ChatGPT accounts won't work.
Starting with v1.5.0, a dedicated ChatGPT Account section in Settings shows your email, plan, and connection status. OAuth login handling has been improved for more reliable sign-in.
Agent Runtime
Some users prefer to run the Claude or Codex CLI they already have installed system-wide instead of the version bundled with Ritemark. As of v1.7.0, Settings -> Agent Runtime lets you choose between two modes:
- Bundled (default) -- Ritemark uses the CLI version it ships with. No setup needed.
- System -- Ritemark uses the Claude or Codex binary already on your PATH.
The current active binary path is shown live in Settings, so you always know which version is in use. Switch between modes any time without restarting.
Model Picker and Runtime Diagnostics (v1.7.2)
As of v1.7.2, the model picker is clearer about what each option does. Every row now shows two lines: the model name and version on top, and a short description of what it's good for underneath. When a runtime offers a long list of models, the picker keeps a constrained height with its own vertical scrollbar, so it never pushes the rest of the sidebar around.
Settings diagnostics also got more precise. The Claude Account section shows the CLI version and the SDK version together, so you can tell exactly which pieces are installed. The Codex section uses runtime detection to report the active version. If something looks off with an agent, these two lines tell you what Ritemark is actually running.
Quick Reference
| Agent | Best For | Setup Required |
|---|---|---|
| Ritemark Agent | Quick text edits, rephrasing | OpenAI API key |
| Claude Code | Document restructuring, research | CLI + Anthropic account |
| OpenAI Codex | Technical docs, code-heavy content | CLI + ChatGPT Plus/Pro |
| OpenCode (v1.7.3) | Any provider via your own API key | Bundled — paste keys in Settings → OpenCode |
| Feature | How to Use |
|---|---|
| Switch agents | Dropdown at top of sidebar |
| Approval policy (v1.8.0) | Auto / Ask / Plan picker in the composer — same across all runtimes |
| Plan Mode | Choose Plan in the composer, or type "plan first" / "show me the plan" |
| Schedule an agent (v1.8.0) | Schedule picker in the Agent editor, or a schedule: block in the agent .md |
| Attach files (v1.8.0) | Attachment picker now works for Codex and OpenCode too, not just Claude Code |
| Add file context | Right-click file, "Send to AI Chat" |
| Share browser page | "Share with Agent?" prompt in composer when a browser tab is open |
| Attach screenshot | Camera icon in browser toolbar (composer shows live 56×56 thumbnail in v1.7.3) |
| Agent re-reads the page mid-task (v1.7.3) | browser_snapshot tool, only on shared tabs |
| Queue a follow-up mid-run (v1.7.3) | Just type and press Enter — parks in the "Queued" notch above the input |
| Let AI control a browser tab (macOS, opt-in) | Set ritemark.features.browser-agent-control: true, approve consent dialog |
| Switch runtime | Settings -> Agent Runtime (Bundled or System) |
| Pick a model | Model picker rows show model/version + purpose (v1.7.2); OpenCode group refreshes on key save (v1.7.3) |
| Check installed versions | Settings -> Claude Account (CLI + SDK) or ChatGPT Account |
| Check context usage | Look at usage bar at top |
| Start fresh | Click "Start Fresh" or type /compact |
Privacy
Your text is sent to the respective AI provider for processing - OpenAI for the Ritemark Agent and Codex, Anthropic for Claude Code. Your API keys and OAuth tokens are stored securely on your machine. RiteMark has no servers, so no data passes through us.
Troubleshooting
If an agent isn't responding, check these common issues:
Ritemark Agent shows "AI Offline" - Verify your internet connection and that your OpenAI API key is configured in Settings.
Claude Code not appearing - Make sure you've installed the CLI (npm install -g @anthropic-ai/claude-code) and authenticated by running claude in the terminal.
Codex login spinner stuck - Try signing out in Settings and signing back in. If OAuth fails silently, check that you have an active ChatGPT Plus/Pro/Team/Business subscription. In v1.5.0, OAuth handling has been improved to reduce silent failures.
Claude Code not working on Windows - Earlier versions had binary detection issues where .cmd/.exe shims were not resolved correctly, causing "spawn EINVAL" errors. Upgrade to v1.5.0 to fix this. After updating, check Settings -> Claude Account to confirm that Claude Code shows as connected.
Codex not working on Windows - The same binary detection fix in v1.5.0 applies to Codex. Check Settings -> ChatGPT Account for connection status.
"Some agent features are unavailable" banner - This appeared in some versions before v1.7.0 because the Codex compatibility probe only tried one argv shape. The probe now tries both shapes. Update to v1.7.0 or later and the false warning is gone.
Context window warning - Your conversation is getting long. Use /compact to summarize or start a fresh conversation.
Tip: Settings now shows real-time agent status for all three agents. If something looks wrong, the Account sections in Settings are the first place to check.
For more help, see Common Issues.
A Smaller v1.7.3 Touch — Edit Link
Not strictly an AI sidebar feature, but it lives one keystroke away from where you write. The Edit Link dialog now has an optional Display text field that pre-populates from the current selection when you create a link, and pre-fills with an existing link's current text when you re-open one. Clicking Update replaces both the text and the target in one step, so renaming a link is finally a single predictable action. The field is hidden during @file search to keep the file-link picker flow unchanged.
Related
- Set Up AI - Configure your OpenAI API key
- Set Up OpenCode - Add the bring-your-own-key runtime
- Agent Library - Browse all agents in one place
- Agent Configurator - Configure an agent visually
- Terminal AI - Use AI agents in the terminal
- Setup Claude Code - Detailed Claude Code installation