imsh4yy

This is very cool! Will have a look.

Yep, came here expecting to read an interesting take on why SSE sucks or a better alternative, but this just reads like "skill issue." A term I very much dislike but seems appropriate here.

I've had early access to StepKit and this kind of sane, explicit API with pluggable backends feels like the right direction. Kudos to the team here!

Thank you :)

Haha, thank you! I just like to build stuff.

Anyway I can learn more about this?

Yes they are tools.

You're right that this isn't the "autonomous agent" fantasy that keeps getting hyped.

The agentic part here is more modest but real. The primary agent does make runtime decisions about task decomposition based on the data and calls the subagents (tools) to do the actual work.

So yeah, it's closer to "intelligent workflow orchestration." That's probably a more honest description.

I mean that depends on how you define the "input" for the tool. Some can be very deterministic like an enum, boolean, number, etc.

Yes, temp is close to 0 for most models. For top k and top p, I've been using the default values set in OpenRouter.

I assume you're talking about Claude Code, right? If so, I very much agree with this. A lot of this was actually inspired by how easy it was to do in Claude Code.

I first experimented with allowing the main agent have a "conversation" with sub-agents. For example, I created a database of messages between the main agent and the sub-agents, and allowed both append to it. This kinda worked for a few messages but kept getting stuck on mid-tier models, such as GPT-5 mini.

But from my understanding, their implementation is also similar to the stateless functions I described. (happy to be proven wrong). Sub agents don't communicate back much aside from the final result, and they don't have a conversation history.

The live updates you see are mostly the application layer updating the UI which initially confused me.

So far I've been hardcoding these into the API calls.

Not sure if I understand the question, but I'll do my best to answer.

I guess Agents/Agentic are too broad of a term. All of this is really an LLM that has a set of tools that may or may not be other LLMs. You don't really need a framework as long as you can make HTTP calls to openrouter or some other provider and handle tool calling.

I'm using the AI sdk as it plays very nicely with TypeScript and gives you a lot of interesting features like handling server-side/client-side tool calling and synchronization.

My current setup has a mix of tools, some of which are pure functions (i.e. database queries), some of which handle server-side mutations (i.e. scheduling a changelog), and some of which are supposed to run locally on the client (i.e. updating TipTap editor).

Again, hopefully this somewhat answers the question, but happy to provide more details if needed.

I think I need to make this a bit more clear. I was mostly referring to caching the tools (sub-agents) if they are a pure function. But that may be a bit too speicific for the sake of this post.

i.e. you have a query that reads data that doesn't change often, so you can cache the result.