Appreciate the feedback and support so far!

Wanted to add, in terms of extensibility, we've really tried to make the key parts of the UX hookable. Most of what you see on this page like tool / reasoning calls, voice, loaders, approvals, etc are completely replaceable in a few lines of plain JS: https://www.persona-chat.dev/advanced.html

It means you can do interesting things like go straight to OpenAI or Elevenlabs voice for read-aloud while streaming the main chat from your framework.

I'd like to improve the shareability of what's created in the ecosystem, but we're not quite there yet.

If you have ideas for more hooks or extensions you'd like to see, we're very much in listening mode.

IMO there's a lot more we can do around hooking into the DOM directly, with more efficient data formats over the wire, before we absolutely need WASM

We'd like to experiment more with this but haven't got their yet. Just some internal prototyping

Thanks! Definitely interested in the game overlay use case.

My gut says you'll need want to hook into custom render functions and theme config to map to your game styles, since it's going to look very different than the standard OOTB options.

The best file to use as a starting reference is here: https://github.com/runtypelabs/persona/blob/main/packages/wi...

If you run into anything, GH issues are welcome!

Appreciate it. And thank you for the work on WebMCP!

For everyone passing by, Alex created https://docs.mcp-b.ai/ and we use two of his libraries to enable WebMCP more cleanly. We found MCP-B after we built our own

It's interesting how experimental web tech vs. frameworks are. Kind of flipped once React and Next.js took off. Now we get to see what the browser can do again. Find the balance that works for each case

Note we actually use React / Vite and Next with Persona across a few of our products. It's nice in our case because the agent specific state (including event debug stream if you turn that on) doesn't need to interact with the main app at all. Keeps updates to agent UX from blowing up other parts of the app

Appreciate the quick take! Sounds like a keeper to me. I think the Opus and Fable design (that I saw for a short while) have gotten stale

> I think the Opus and Fable design (that I saw for a short while) have gotten stale

Can you expand on what you mean by stale? I don't get how an artefact-producer can get "stale" besides literally out-of-data information which I dont think you mean because you mention fable.

I think they mean the style these tend to put out is becoming noticeable in too many places and therefore the resulting frontends feel stale, ie not "fresh" or unique

I find I there is anxiety either direction but have more engaging days when I am chasing something deeply.

First thought was "only 30 tasks" however the findings map to what I've seen personally: code review consumes majority of tokens

Code review could also be run as an unattended/batched task though, possibly with at least some use of on-prem inference (which excels at this). That would be a major saving compared to the usual cloud inference scenario.

with which models, though?

Yeah wasn’t there a report recently on how local models after energy costs didn’t weren’t actually more efficient to complete the same task?

Feels like the active discovery going on is trying to understand what is computer vs what is AI, for every product.

Agents help a ton with the discovery, but the act of building a product needs a deeper level of thought and validation to make it actually better than what came before. So IMO what you see is people still learning what needs to be understood and crafted first hand to make a product better (including economics)

We’ll get there if more of us try

Hopefully we can blend those two options together so it’s not a choice.

Personally I find being able lean on our heavily documented standards in /review gives me back time to dive into what I want to craft next.

Same with scheduling repetitive tasks an agent can do for me well once instructed well. I am freed up to do something else I want to focus actively on because I like it and want it to be great.

Now stress about OKRs and OKRS in general… that’s a different issue

At this point you have to use more than one to get a complete picture, which I’m doing now. Mainly because: 1) some are not always up to date (started on helicone but felt a lag on price updates) 2) they don’t return every model / provider I want (https://ai-gateway.vercel.sh/v1/models has rich data but is a subset, so I combine with helicone)

I always hope for the best when someone has a new list because of this. I want a de facto source!