Get the weekly radar
One short email with the freshest products, every week.
Humalike gives AI agents social skills — when to speak, group norms — via seven APIs.
Grounded in available product and source data
Knowing when to speak versus stay silent is a skill most AI agents simply don't have, and it's exactly what Humalike's social skills APIs for humanlike AI agents are built to add — starting with Turn-Taking, the flagship API that decides whether an agent should speak, stay quiet, or interrupt, and which bundles in the other six.
The remaining APIs cover different layers of social awareness: Theory of Mind tracks what each person in a conversation believes, wants, and feels as it unfolds; Norms reads a specific group's inside jokes and unwritten rules; Persona grounds an agent's personality in real community data instead of a generic invented backstory; and Social Memory carries norms, opinions, and behavior forward across every conversation a person has had with the agent, rather than resetting each time. Social Signals and Social Observability round it out by reading behavioral cues — typing pauses, edits, deleted reactions — and surfacing who's actually engaged versus bored or annoyed.
None of this is tied to a specific model or framework: the APIs are built to be model-, use-case-, and stack-agnostic, composing into whatever agent architecture a team already has rather than requiring a rebuild. That flexibility shows up in how broad the named use cases are — gaming NPCs and AI teammates, AI coworkers embedded in a team's existing channels, mental health and therapy agents, hardware companions like pendants or smart glasses, ed-tech study partners, and community-management agents.
Getting started is a free tier with an initial credit allowance and no card required, though the page reviewed doesn't detail what a paid tier actually includes once those credits run out — worth confirming directly before building a product roadmap around it. On the compliance side, SOC 2 Type II, ISO 27001, and GDPR compliance are all listed as in progress rather than already certified, which matters for any team in a regulated space evaluating current versus future compliance status.
Not by design — the intent is for these to layer onto infrastructure a team already has running, rather than a migration forcing a switch to a specific supported model or framework first.
Yes, through the Social Memory API specifically — that continuity is what separates it from an agent that starts fresh every session with no sense of who it's talking to.
Whether an agent should speak, stay silent, or interrupt at a given moment, which is the flagship capability the other six APIs bundle around rather than a standalone feature used in isolation.
Worth checking current status directly — SOC 2 Type II, ISO 27001, and GDPR compliance are all listed as in progress on the site rather than already certified, so a regulated team should confirm where certification stands before committing.
Yes — Social Observability is built specifically to surface engagement levels, identifying who likes a message, who's bored, and who's annoyed based on behavioral signals in the conversation.
These 4 comments were collected from the discovery source. ProductVisit does not host replies in Release A.
Hey PH 👋 Martí here, co-founder of Humalike. What is Humalike? The behavioral infrastructure for humanlike AI agents. The social skills your agents have been missing. The problem A few months ago we built an AI community manager. The second it hit a group chat, everyone knew it was a bot. It talked over people, never knew when to shut up. More features didn't fix it. Today's models are capable enough. Smart enough. Fast enough. But we still feel they don’t fit in the room. The solution: 7 behavioral APIs Turn-Taking (Flagship): Knows when to speak and when to stay silent (bundles all other APIs in one). Theory of Mind: It gives your agent a sense of what people really think and feel. Norms: Reads the group’s tone and responds the way it’s accepted here. Persona: Improve presonality so it’s Opinionated, takes sides, backed by real community data Social Memory: It gives your agent a memory for people, who they are and what matters to them. Social Signals: Catches the pause before sending, a removed reaction, and an edited message. Social Observability: Sees who’s engaged, who’s bored, and who’s annoyed. Model, use-case and stack agnostic, built for groups, not just 1:1. Extra highlights 💸 $20 in free tokens to start building 🔌 One-shot integrations with Hermes, WhatsApp & Telegram 📄 Backed by in-house research: LoSoNA (social-norm benchmark) + HUMA (a human-passing group facilitator) 🔒 SOC 2 / ISO 27001 in progress Who It's for: Anyone building agents that must feel human, AI companions, NPCs, tutors, voice agents, groups, humanoids. If you've ever shipped an agent that was smart but experience using it felt wrong, Humalike is for you. What we'd love from you: Grab your $20 in tokens, and tell us, how did our APIs improve the experience? Try with Hermes, Openclaw, or any agent you have deployed! We'll be here all day reading every comment, your feedback shapes what we ship! Backed by the first investors in ElevenLabs, Revolut & more. Built by a tiny 🇪🇸×🇵🇱 team that hasn't slept much :)) Show more
4 source upvotesHey! Ignacio here, Founding Product Engineer at Humalike. We encourage you to integrate our APIs into your agents and watch their performance improve immediately in social scenarios. Trust me, you won't want to go back to your old agent behaviour. ;) P.S. Enjoy your free credits on sign-up!
4 source upvotesHey everyone, I’m Mateusz, founding researcher at Humalike. For me, the interesting problem is the gap between intelligence and behavior. Agents are getting very capable, but they still often feel awkward in real conversations. Humalike is our attempt to work on that missing layer.
4 source upvotesHey 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 🔒
3 source upvotes