Humalike - Give your AI agents the social intelligence they're missing
by•
Today's models are capable enough. Smart enough. Fast enough. But we still feel they don’t fit in the room. Humalike is building the behavioral infrastructure for humanlike AI agents. The social skills & proactiveness your agents have been missing. APIs, models, benchmarks.
Replies
This is very cool and very needed! I tried testing the apis and ran into some issues (just sharing) but I will come back later and try again. Can't wait to implement into our agents.
Humalike
@bo_kommu Shit, looking into it rn!
@bo_kommu Fixed! Sorry for the long wait
@mateusz_jacniacki Amazing! Working now. Thanks so much!
The "groups, not 1:1" framing is what got me.
I run a 2k-person Discord and tried putting an agent in the busy channels. In a 1:1 DM it's fine — but the moment 5 people are going back and forth, it either spams every message or freezes and says nothing. There's no in-between.
So my question on Turn-Taking: in a fast group thread, is it scoring "should I speak right now" per incoming message? Or does it hold a running read of the whole conversation and wait for a real opening?
And can I bias it toward "lurk more" — for a channel where I only want it to chime in occasionally?
Humalike
@rudratosh We would love you to connect your agent again to your community but now using Humalike :)) tysm for the supp!
@rudratosh It's funny that you bring up Discord, as it was our first use when we began working on Humalike. We hit the same issues as you described and decided that there's no point agents for Discord until Turn-taking and social aspects are solved.
It doesn't respond to every message, it notices if people are still sending messages. It waits for the opening and then addresses everything it seen so far.
You can tune lurking by adjusting your agent personality and passing it to turn-taking component!
Nas.com
Can developers tune how proactive or reserved an agent behaves for different communities?
Humalike
@nuseir_yassin1 Hey Nuseir! It's not something you turn on or off, but agent will adapt according to the situation as you would expect :))
@nuseir_yassin1 Yes, and it happens on few levels:
1. Norms API helps agent learn the pattern on it's own
2. If you use Persona API it will create good baseline persona for that group
3. If you still need minor tweaks, the turn-taking component accepts a prompt that you can tune on your side
This is a really interesting angle — most of the conversation around AI agents focuses on capability (can it use the right tools, in the right order?) but the social layer is almost always missing. I've been studying agentic AI recently and the gap between 'task completed correctly' and 'response that feels right for the situation' is huge. How are you thinking about measuring whether an agent is actually reading the room vs. just following social scripts?
Humalike
@giulia_lemme The reason the current solution is split into various components is because just one didn't solve the problem at all. When you combine all components, agent behaves accordingly! tysm for the supp!
@giulia_lemme Hey, thanks for question! It's hard to evaluate and there is very little pre-existing research on this topic. We try to evaluate different capabilities separately - "was this social" is super hard to answer, but "did this agent follow a norm of behavior, style and humar that this group operates in" is easier. We still need to improve on evaluations side, but one of the steps we did was releasing an open-source benchmark: https://arxiv.org/abs/2606.14600
Makers building AI agents have social intelligence as a much bigger bottleneck than reasoning quality. Humalike is solving a very important problem. Congrats on the launch.
Humalike
@zerotox Tysm Kumar!!
@zerotox Thanks for your support! 🫶
GrowMeOrganic
how the APIs perform in really fast-moving group chats where multiple conversations happen simultaneously?
Humalike
@iamanantgupta In extremely fast-paced chats (messages per second), it's not perfect, but anything a bit slower, Humalike handles it perfectly!
@iamanantgupta They were designed exactly for this scenario. The first use case that inspired us was AI bots for discord, that can have dozen of people chatting at the same time on different topics, interrupting each other, having very specific jokes and style.
ConnectMachine
I'd love to see benchmark videos comparing baseline agents against Humalike-enhanced agents in the same conversation.
Humalike
@syed_shayanur_rahman We are working on that rn!! Soon :))
@syed_shayanur_rahman Good idea, we should prepare demos like that!
Documentation.AI
How does Humalike adapt when community norms evolve over weeks or months instead of remaining static?
Humalike
@roopreddy Good question! Norms are extracted from the live transcript, it re-runs extraction on recent windows (new jokes, diff behavior, etc), then Social Memory ingests info continuously. Both combined deliver really well!
@roopreddy That's what inspired us to create Norms API in the first place. People often set up personality once and forget about it. Norms API is meant to be used continously, updating the agent behaviour every few messages.
Is there analytics showing why an agent chose not to respond? That would be incredibly valuable for debugging.
Humalike
@ranjan_kumar45 The component social observability allows you to control that (among extra usefull things)!!
@ranjan_kumar45 Valid point, we already have that for internal debugging but we didn't include it in public API yet.
As a community manager, I'd use this immediately for Discord and Slack community assistants. :D
Humalike
@himani_sah1 Go for it! :)))
@himani_sah1 Great to hear that! Can you join our Discord and open ticket? Maybe we can help ;)