The future of AI agents is WebAssembly (get started now)

The future of AI Agents is WebAssembly.
In this video. we look at how AI Agents can call WebAssembly functions dynamically using LlamaIndex, AssemblyScript and RAG.
WebAssembly is probably the future of AI function calling due to it's secure sandboxing.
In this video, Chris breaks down how to use function calling with AI Agents and LlamaIndex, how to build webassembly functions and how to call them from your AI Agents. Finally we look at how we can use RAG to dynamically load tools from a tools database.
github: github.com/chrishayuk/hello-a...

[@twilkpsu]

Bravo! 🎯

[@chrishayuk]

glad you enjoyed

[@kenchang3456]

Interesting, thanks.

[@chrishayuk]

glad you enjoyed

[@TatyanaEmelyanova-ov2qq]

How is this possible, looks too good to be true

[@chrishayuk]

it's pretty cool right

[@MavVRX]

Too much effort. Just use containers. How would you package a tool that has tonne of dependencies using web assembly?

[@chrishayuk]

you can't have a model install containers...

[@MavVRX]

@@chrishayuk I'm not saying the LLM to install containers (even though it can, since it's just a function call). I'm saying to use containers (docker, podman, containerd) instead of webaasembly. Try creating a more complex tool, such as a tool that uses a dataframe in webassembly...maybe using pyodide and micropip

[@chrishayuk]

@@MavVRX yeah, maybe i didn't explain this video so well.. function calling other agents, containers etc is a given. but this is more about integration of libraries and tools

[@fraternitas5117]

@@chrishayuk you can with gptscript