What is OpenCues?

OpenCues enables AI inside any text field. If you can type, you can access AI features instantly, with no additional UI required.

This is not a chatbox. In a conversation, people give cues via facial expressions and body language while a conversation is ongoing. OpenCues dispenses with the turn based paradigm and provides contextual feedback and prompt steering while you type, or answers users’ queries as they are being written.

What models are supported?

OpenCues is platform, model and provider agnostic, engineered from the ground up to enable native inline AI. It uses your own API key, your existing Claude/OpenAI subscription, or local models via Ollama.

Features

  • Inline Cues - cues are provided to the user as they type, helping shape their prompt or warn about implications, before pressing enter.
  • Inline Prompting - a prompt is typed followed by the underscore symbol. This triggers the LLM to action that prompt, returning answers or modifying text inline and within any textbox.

FAQs

What is OpenCues?

OpenCues brings AI wherever you type. Just type _ and AI will fill in the blank. Anywhere.

How do I set up OpenCues?

npm install -g opencues, then opencues install <host>. Full instructions on the OpenCues repo. Or ask AI to read it for you.

How do I use OpenCues?

Just type _ and AI will fill in the blank. If you don’t like what AI did, Ctrl+Alt+←/→ to select the changed text, then Ctrl+Alt+↑/↓ cycles through other things it could have said, or right back to exactly what you typed. Your original text is always one cycle away.

Is OpenCues open source?

Yes, OpenCues is fully open source. The source code is public on GitHub under the Apache-2.0 License, meaning anyone can use, modify, or contribute to its development. We are trying to grow a community that files issues, submits pull requests, and extends functionality.

What is the OpenCues mission?

To explore and advance the frontier of human to AI interfaces.

Can I use my existing AI subscriptions with OpenCues?

Yes. Bring an API key from Cerebras, Groq, OpenAI, Anthropic, Gemini or OpenRouter, connect through your existing Claude or OpenAI subscription, or run local models via Ollama.

Do I need extra AI subscriptions to use OpenCues?

No. OpenCues works with what you already have: an existing API key, or an AI subscription you already pay for.

Where can I use OpenCues?

You can use OpenCues almost anywhere in Chrome, Claude Code, OpenCode, Gemini CLI, and in your terminal via the standalone oc-shell app. Full guide: AI in any text field.

How much does OpenCues cost?

OpenCues itself is free and open source. It plugs into whatever AI service you choose, so the only cost is your model usage with that provider (several, like Cerebras, have free tiers).

What about data and privacy?

OpenCues has no servers and collects nothing. Your text goes directly from your machine to the model provider you configured, on your own key or subscription. Config lives in local files, and the optional identity feature keeps personal values on your machine by default.