Persona is a lightweight, open-source AI chat UI library that embeds into any website, from modern apps to static HTML. Unlike React-based chat frameworks, Persona is framework-free, backend-agnostic, and WebMCP-native, so your assistant can discover and execute tools exposed by the parent page. Add streaming chat, voice, theming, and interactive copilot experiences without rebuilding your frontend or writing bespoke APIs.
Hey Product Hunt 👋 I'm Nathan, cofounder at Runtype and one of the people who built Persona.
Persona is the world's first AI chat library to natively support WebMCP. It's a framework-agnostic chat UI you can drop into any existing website or app to easily add AI to your product.
Why we built it
Most AI chat libraries assume you're starting from scratch on React. Persona is built for the rest of the internet: existing sites, mixed frontend stacks, proprietary CMSes, and teams that want a modern AI experience without rebuilding in React. Drop it in with no build step, theme the whole experience through config and the built-in editor, then ship it as a chat widget, a full-screen ChatGPT/Claude-style surface with artifacts, or something in between.
It’s built in Vanilla JS so it can work anywhere - WordPress, Shopify Liquid, Static HTML sites, and more.
The part we're most excited about: WebMCP 🧩
Persona is the first Agent UI framework to natively support WebMCP, which just shipped in Chrome and has polyfills available for all other browsers. With WebMCP, you can register agent-facing tools directly in your frontend, which allows Persona-based agents to directly use your frontend app with much more dexterity & token efficiency than other approaches (headless browsers, DIY frontend tools, etc).
If you already have a sophisticated web app, this can be a much faster path to enabling AI capabilities in your app vs building an entirely new backend. And since WebMCP tools can be hooked directly into frontend code, the experience feels much more like a “copilot” and less like a bolt-on, all the usual side-effects and UX are preserved while your app gets more capable.
WebMCP is maturing to the point where it makes sense to start building against it, and Persona makes that easy with a built-in polyfill.
Open source, no lock-in
Persona is MIT-licensed and open source. It's made by an AI platform company, but it's deliberately not coupled to Runtype. You deploy it on any framework and wire it to any SSE-based AI endpoint with a little glue code. Examples for popular frameworks like Flue, Eve, OpenAI Agents SDK, and more are in the repo along with docs your existing coding tools can use to implement it quickly.
If you’re like to deploy a chat agent as quickly as possible, the CLI command:
npx @runtypelabs/cli@latest persona init
…will set you up with a WebMCP-capable chat agent on the Runtype platform in minutes.
Who it's for
Builders adding an AI experience to something that already exists, without a rewrite and who want to benefit from us obsessing over the details of frontier AI experiences so they can just deploy them.
We'd love your feedback! If you've tried adding AI into an existing app, I'm curious what was hardest: picking the right framework, standing up a new backend, wiring up the tools, building out the right evals, or trusting what the AI actually does. Happy to go deep on WebMCP in the comments.
About Persona.js on Product Hunt
“Add WebMCP-native AI chat to any Frontend”
Persona.js launched on Product Hunt on June 28th, 2026 and earned 290 upvotes and 44 comments, earning #3 Product of the Day. Persona is a lightweight, open-source AI chat UI library that embeds into any website, from modern apps to static HTML. Unlike React-based chat frameworks, Persona is framework-free, backend-agnostic, and WebMCP-native, so your assistant can discover and execute tools exposed by the parent page. Add streaming chat, voice, theming, and interactive copilot experiences without rebuilding your frontend or writing bespoke APIs.
On the analytics side, Persona.js competes within Open Source, Developer Tools and Artificial Intelligence — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Persona.js performed against the three products that launched closest to it on the same day.
Who hunted Persona.js?
Persona.js was hunted by Ben Lang. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Persona.js including community comment highlights and product details, visit the product overview.
Ben Lang
Hey Product Hunt 👋 I'm Nathan, cofounder at Runtype and one of the people who built Persona.
Persona is the world's first AI chat library to natively support WebMCP. It's a framework-agnostic chat UI you can drop into any existing website or app to easily add AI to your product.
Why we built it
Most AI chat libraries assume you're starting from scratch on React. Persona is built for the rest of the internet: existing sites, mixed frontend stacks, proprietary CMSes, and teams that want a modern AI experience without rebuilding in React. Drop it in with no build step, theme the whole experience through config and the built-in editor, then ship it as a chat widget, a full-screen ChatGPT/Claude-style surface with artifacts, or something in between.
It looks polished out of the box & you can make it pretty far down the path of customization with no code, but still gives developers hooks and plugins when they want to go deeper.
It’s built in Vanilla JS so it can work anywhere - WordPress, Shopify Liquid, Static HTML sites, and more.
The part we're most excited about: WebMCP 🧩
Persona is the first Agent UI framework to natively support WebMCP, which just shipped in Chrome and has polyfills available for all other browsers. With WebMCP, you can register agent-facing tools directly in your frontend, which allows Persona-based agents to directly use your frontend app with much more dexterity & token efficiency than other approaches (headless browsers, DIY frontend tools, etc).
If you already have a sophisticated web app, this can be a much faster path to enabling AI capabilities in your app vs building an entirely new backend. And since WebMCP tools can be hooked directly into frontend code, the experience feels much more like a “copilot” and less like a bolt-on, all the usual side-effects and UX are preserved while your app gets more capable.
Some cool demos:
Fullscreen Assistant → persona-chat.dev/fullscreen-assistant-demo.html
Slides → persona-chat.dev/webmcp-slides.html
Calendar → persona-chat.dev/webmcp-calendar.html
MSPaint → persona-chat.dev/webmcp-paint.html
WebMCP is maturing to the point where it makes sense to start building against it, and Persona makes that easy with a built-in polyfill.
Open source, no lock-in
Persona is MIT-licensed and open source. It's made by an AI platform company, but it's deliberately not coupled to Runtype. You deploy it on any framework and wire it to any SSE-based AI endpoint with a little glue code. Examples for popular frameworks like Flue, Eve, OpenAI Agents SDK, and more are in the repo along with docs your existing coding tools can use to implement it quickly.
If you’re like to deploy a chat agent as quickly as possible, the CLI command:
…will set you up with a WebMCP-capable chat agent on the Runtype platform in minutes.
Who it's for
Builders adding an AI experience to something that already exists, without a rewrite and who want to benefit from us obsessing over the details of frontier AI experiences so they can just deploy them.
Repo, docs, and examples: github.com/runtypelabs/persona
We'd love your feedback! If you've tried adding AI into an existing app, I'm curious what was hardest: picking the right framework, standing up a new backend, wiring up the tools, building out the right evals, or trusting what the AI actually does. Happy to go deep on WebMCP in the comments.