[kveykva]

In what I think of as engineering terms: an agent is a long running service that invokes LLMs during its execution. In contrast to an LLM driven application where the primary function is synchronous with the end user (like chatGPT). There's a blurry line there but that's how I think about it.

AutoGPT and BabyAGI are probably the two most well known examples so far.

A significant struggle when building these types of applications is understanding and debugging behavior many execution steps deep. This tries to assist with that by giving a framework for structuring the way your agent runs.

Maybe a similar concept is breaking out a web application into services, or individual route handlers, rather than implementing everything as one massive loop that responds to events.

[hgomersall]

So essentially a long running process that responds to events etc. So my understanding is now: when stuff happens, say a database gets updated, or a timer triggers, the agent wrangles the data and passes it to OpenAI for some LLM heavy lifting, then wrangles what is returned somehow. Is that correct?

[gerad]

Yeah, but the value they provide IMO (or promise to, it’s only promised in the readme, not shown) is the observability.

Creating one of these event driven systems is somewhat trivial. Node has event emitter built in for example.

Being able to monitor, debug, scale it and ensure it’s robust to failure is much harder.

In that respect it sounds kinda like tray.io. [1]

1: https://youtu.be/g_2HNv8HZcA

[kveykva]

That is correct