Feedback and context, right where your product speaks.
From AI summaries to dashboards to reports — users react right where it happened. Voice notes, thumbs, support requests. Your team adds context that lives there permanently. One component. No forms.
Open source · MIT license · Self-hostable · No vendor lock-in
Users hover and leave feedback right where it happened — on an AI output, a chart, a report row, anything.
Attach video or written context to any section. It lives there permanently, not in a docs tab.
Lands in Slack, Discord, Teams, or your own webhook. No backend to write.
Try it now
Section titled “Try it now”This is an interactive demo. Nothing you submit here is sent anywhere, no data leaves your browser.
The interactive demo requires a desktop browser. Open this page on your computer to try it.
Hover over any card — then try voice feedback, thumbs, support, or video.
Revenue grew 17.4% quarter-over-quarter, driven primarily by expansion in the EU region. Customer churn dropped to 2.1%, the lowest in eight quarters. The model recommends focusing the next campaign on the mid-market segment, where engagement signals are strongest.
- Expected revenue€ 2.4M
- Confidence interval87 %
- Churn riskMedium
- Berlin Mitte94
- Kreuzberg92
- Prenzlauer Berg87
The AI generated a summary. A user disagreed. There's no way to say so without opening a ticket.
Disagreements with AI outputs and reports surface in Slack, far from the actual content.
Frustrated users open a ticket. You find out days later.
The user reacts right on the summary — voice note, thumbs, or a direct message. All tied to that section.
A voice note lands in your channel the moment it happens, attached to the exact output.
One click opens a dedicated channel with full context already attached.
How it works
Wrap any section
Drop <FeedbackTarget> around any output in your app. That's the only code change required on the frontend.
import { MusProvider, FeedbackTarget } from '@datachefhq/mus' <MusProvider config={{ projectName: 'My App', ... }}> <FeedbackTarget sectionId="revenue-chart" sectionName="Revenue Chart" > <RevenueChart /> </FeedbackTarget> </MusProvider>
Users hover and react
A toolbar appears on hover. Voice notes, thumbs, support requests — no form, no context switch. The feedback is tied to that exact section automatically.
Feedback routes to your team
Slack, Discord, Teams, or any webhook. Or run the mus-server Docker sidecar alongside your app — no Node.js server to maintain, no backend to write.
What you get
Section titled “What you get”Users leave a voice note, thumbs reaction, or support request right where it happened — on an AI output, a chart, a report row. No forms, no context switching.
Attach a video or written explanation directly to any section. It lives there permanently — available the moment a user asks "wait, why?"
One click opens a dedicated channel between the user and your team. No tickets, no bots — a real conversation with full context already attached.
Built for any product where output matters
Dashboards & analytics
Charts and data that users question, compare, and debate. MUS puts the conversation on the chart.
AI-powered products
AI generates. Users question. MUS captures that disagreement right on the output — voice note, thumbs, or a direct escalation to your team.
E-learning platforms
Lessons and content that learners react to. Attach explanations, collect reactions, without redirecting away.
Internal tools
Reports and outputs your team questions in meetings. Surface that feedback before the meeting.
Common questions
Section titled “Common questions”Does MUS only work with React?
The component library is React (18+ and 19). The mus-server is framework-agnostic and works behind any frontend, so your backend doesn’t need to be React or even JavaScript.
Can I self-host everything?
Yes. The package is open source under MIT, and mus-server ships as a pre-built Docker image you run alongside your app. No SaaS dependency.
Does it have to go to Slack?
No. Slack, Discord, Teams, and generic webhooks are built in. Custom adapters take a few lines of code and can route feedback to Linear, Jira, your data warehouse, or any HTTP endpoint.
Does it work with non-AI products?
Yes. MUS is built around the idea of in-context feedback on specific sections, which is useful anywhere users interpret output. AI products are where it shines, but dashboards, reports, and internal tools benefit just as much.
What about user identity?
MUS auto-fills name and email from your auth system via pluggable resolvers (Stytch, Clerk, Auth0, NextAuth, or your own). If you don’t have auth, users can type their info or stay anonymous.
Is voice feedback really 60 seconds?
Yes, that’s the default cap and it’s configurable. The recording is converted to MP3 server-side and uploaded to your chosen destination automatically.
Add MUS in minutes
Install the package, wrap a section, configure your destination. That's it.