Launched this week
Humalike
Give your AI agents the social intelligence they're missing
726 followers
Give your AI agents the social intelligence they're missing
726 followers
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.
The social observability feature seems really interesting. It’s something I feel humans can do very naturally so It’ll be interesting to see agents being able to read the room just like humans.
Will try this out with my agents!
Humalike
@chitransh_gupta Exactly, most agents are blind to that layer entirely, with our social observability API, agents can now see how the environment is feeling and adjust their behavior based on it, delivering a much better experience.
Would love to hear how it goes when you try it out with your agents!
P.S. Waiting for your feedback ;)
jared.so
@chitransh_gupta Thank you so much for the comment Chitranish! I will gladly assist if you need any help :)
Amazing stuff!
Are you guys planning on launching a separate agent, or just the API's?
jared.so
@kacpergadomski Thanks for the comment! :)
No separate agent planned, but we did build an open-source plugin for Hermes Agent that uses our APIs, so you can see how it works in action :))
Come take a look: https://github.com/Humalike/hermes-humalike-plugin
Humalike
@kacpergadomski Thanks for the supp Kacper :)) We are building a lot. Not a separate agent, but soon we will launch new stuff!
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
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.
I'm soo interested in this! I find myself using "please" and "thank you" with agents all the time; however, when I'm hit with a 50-page response, I quickly realize my courtesy means nothing haha. Maybe this will ease my pain!
Humalike
@cairacshields 100%!! We as humans are used to dealing with other humans, and that simple human interaction feels "normal" which translates to = correct. With AI, now we are "getting used" to a new way of interaction that we really can't get used to / don't enjoy at all. Humalike aims to solve the experience problem, which will solve your issue!
jared.so
@cairacshields Thanks for the support! I would love to chat about it in the future
the missing layer isn't intelligence, it's calibration. models can generate perfect answers but they don't know when they're supposed to be quiet. the social debt shows up the moment you drop an agent into a real slack or discord. it either lurks awkwardly or overshares. the version that reads the room first and speaks second is the one people let stay.
curious how you're benchmarking "fits in the room." vibes are hard to measure. is it deference patterns, timing, response latency to social cues? that spec is the whole product.
@thenameisarian Hey 👋 humans are the ultimate judge. At the end of the day what matters is "do people like the agent?" "are they annoyed by him" "do they do social sanctioning on it?" this questions matter the most but are only attributable in long time horizon.
Hey everyone! I'm Mateusz, co-founder and CTO of Humalike 👨💻
We put a lot of effort to transform our in-house research and know-how gained in the past year into a product everyone can use. Today we are releasing 7 APIs you can plug-in to your agent or product
Research
Our team includes people previously working at NVIDIA, Revolut, TSMC and High Frequency Trading firms. Making AI behave in humanlike way in social scenarios is a hard hard hard problem. We publish part of our research, feel free to give it a look:
https://arxiv.org/abs/2511.17315
https://arxiv.org/abs/2606.14600
Security
We are in the process of getting SOC 2 compliant which is gold standard of security, reliability and safety of data 🔒