Humalike

<p>Hey PH 👋 Martí here, co-founder of Humalike.<br></p><p><strong>What is Humalike?</strong> The behavioral infrastructure for humanlike AI agents. The social skills your agents have been missing.<br></p><p><strong>The problem</strong><br>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.<br></p><p><strong>The solution: 7 behavioral APIs</strong></p><ul><li><p><strong>Turn-Taking (Flagship)</strong>: Knows when to speak and when to stay silent (bundles all other APIs in one).</p></li><li><p><strong>Theory of Mind</strong>: It gives your agent a sense of what people really think and feel.</p></li><li><p><strong>Norms</strong>: Reads the group’s tone and responds the way it’s accepted here.</p></li><li><p><strong>Persona</strong>: Improve presonality so it’s Opinionated, takes sides, backed by real community data</p></li><li><p><strong>Social Memory</strong>: It gives your agent a memory for people, who they are and what matters to them.</p></li><li><p><strong>Social Signals</strong>: Catches the pause before sending, a removed reaction, and an edited message.</p></li><li><p><strong>Social Observability</strong>: Sees who’s engaged, who’s bored, and who’s annoyed.</p></li></ul><p>Model, use-case and stack agnostic, built for <strong>groups, not just 1:1</strong>.<br></p><p><strong>Extra highlights</strong></p><ul><li><p>💸 <strong>$20 in free tokens</strong> to start building</p></li><li><p>🔌 <strong>One-shot integrations</strong> with Hermes, WhatsApp &amp; Telegram</p></li><li><p>📄 <strong>Backed by in-house research:</strong> LoSoNA (social-norm benchmark) + HUMA (a human-passing group facilitator)</p></li><li><p>🔒 <strong>SOC 2 / ISO 27001</strong> in progress<br></p></li></ul><p><strong>Who It's for: </strong>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.<br></p><p><strong>What we'd love from you:</strong> 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!<br></p><p>Backed by the first investors in ElevenLabs, Revolut &amp; more.<br><strong><em>Built by a tiny 🇪🇸×🇵🇱 team that hasn't slept much :))</em></strong></p>

<p>The Turn-Taking API is the part that jumps out at me. I build voice AI that calls elderly parents every day, and the single hardest thing has been the bot cutting people off. Older folks pause mid-sentence to find a word, and every VAD setup I've tried reads that silence as their turn ending. How does Turn-Taking handle long, uneven pauses? Is it purely acoustic timing, or does it factor in whether the thought is actually complete? Following to see where the benchmarks land.</p>

<p>Looks like "groups, not 1:1" framing is the one most people might underrate. Really good! Turn-taking in a 2-person chat is mostly a latency problem, but the second there are 4 people in the room the agent has to decide whether to speak at all, which is a completely different thing. </p><p></p><p>Wonder when you're stack-agnostic, how do you actually capture a deleted draft or a pulled reaction? I guess on most platforms that event never leaves the client</p><p></p>

<p>Theory of Mind is the hardest one to get right, honestly. <br><br>How are you evaluating whether it's actually working vs just inferring emotions in an obvious way?</p>