WASM Agents: AI agents running in the browser

The frustrating thing about this is the limitation of using a browser. Agents should be long-running processes that exist external to a browser. The idea of using wasm is clever, but it feels like the entire browser environment needs to evolve because we're no longer dealing with just web pages. I think we are looking at a true evolution of the web now if this is the way it's going to go

> Agents should be long-running processes that exist external to a browser

Sure, but there are a ton of ways for doing that today. What this specific thing is addressing, is removing the requirement of "the dependency on extra tools and frameworks that need to be installed before the agents can be run".

That's what the Component Model[0] is all about.

WASIp3[1] is gonna be awesome. Hopefully releasing later this year.

[0]: https://component-model.bytecodealliance.org/

[1]: https://wasi.dev/roadmap

When you say agents should be long running, which definition of "agent" are you talking about?

mcp.run is entirely based on wasm. Tools can run on our cloud or locally