Sider Omni Sidebar - Give every Mac app an Agent Sidebar
An AI agent beside any Mac app. Sider Omni sidebar sees what's on your screen and acts on it directly, right where you're working. Watch the result, ask for the next change. Nothing to copy, nothing to upload.
Built on GPT-6 Astra, and it can run on your existing ChatGPT or Codex credits.
Replies
Not having to export the data before asking for the chart is such a minor but actual save of time.
@donovan10 Exactly. Exporting, finding the file, then uploading it sounds minor—until you do it over and over. Being able to look at your data in Numbers and simply say “make me a chart” feels so much smoother.
The screen awareness is the part I’m most curious about. How does Omni handle apps with sensitive information or screen?
@ben_d3 For any app or screen, Sider Omni only reads the relevant window when you explicitly start a task that requires screen context. It never reads information proactively.
Sider Omni Sidebar
@ben_d3 Simple, just don't run Omni on that window.
Does it add context across them or mainly control the visible interface?
@linpeng Both. Sider Omni uses the window it’s attached to as the main context, and it can also access relevant information and complete tasks across apps when needed.
Does using Omni consume credits based on every interaction or only when the agent needs the model?
@jasonwu Usage is based on the actual model processing involved in a task—it’s not a separate credit charge for every action the agent takes. You can also connect your ChatGPT/Codex account in Sider Omni and use the allowance from your existing ChatGPT/Codex plan.
Can the user tell Omni which window should be treated as the active context?
@simonclark55 Yes. Switch to the window you want to use, then click the Sider Omni companion beside it or use the keyboard shortcut to open the sidebar. The task will be linked to that window and use it as its context.
Does it automatically choose between ChatGPT and Codex depending on the task?
@noahanderson Sider Omni offers two model service sources: Sider and your connected ChatGPT/Codex account. You choose which one to use, and Sider Omni won’t automatically switch to the other based on the task.
Swytchcode
Really nice. Is it safe to use :)
Also, do i need a local LLM to run this?
@chilarai Safety is a big priority for us. Sider Omni only reads the screen context needed for a task you start, and the default Ask for approval mode asks for confirmation before important actions. You don’t need a local LLM—you can use Sider’s model service or connect your own ChatGPT/Codex account.
Love that it acts right on your screen without any copy paste, keeping you in flow instead of pulling you into yet another chat window.
@ilko_kacharov Thank you! We want AI to come to where you work, instead of making you move your work into another chat box. Sider Omni stays beside the current app and helps you get things done right there.
Congrats on the launch , It operates offline or in low band -width conditions?
@easeops Thank you! AI processing currently requires an internet connection. Text and interface-based tasks are generally lighter on bandwidth, while tasks involving screenshots and visual understanding depend more on the quality of the connection.
Earth.fm
@1mirul Glad that stood out to you! Constant copying and pasting breaks the flow, so Sider Omni stays beside the current app, understands the relevant context, and helps carry the task forward.