Humalike x Hermes - Social intelligence plugin for Hermes Agent
by•
One command gives your Hermes agent social intelligence. It decides when to speak, adapts to your group's tone and remembers who said what. Works in group chats on Slack, Telegram and WhatsApp.
Replies
Nice work team!
Good to see you shipping new things fast :)
Does this support Discord? I have my Hermes agent on Discord.
Humalike
@chitransh_gupta Tysm! Always :))
We might build integration today, I'll confirm later!
jared.so
@chitransh_gupta Hello! Discord is now officially supported by our plugin :))
I will gladly hear your feedback on it and answer to any questions you might have.
Pushary
#1 today let's gooo!!!!
<3
Humalike
@aadilghani <33
the 'decides when to speak' bit is the whole game imo. most agents in a group chat have zero restraint and just talk over everyone
Humalike
@alex_watson2110 100%.. it's unusable by default. Give our plugin a try :))
jared.so
@alex_watson2110 Thanks for the comment Alex! I'm here if you have anymore questions
Finally someone tackling the awkwardness problem head on. Tried the API and the proactivity cues feel way more natural than the stiff reminders my agent used to send.
Humalike
@savazverjtjn :)))) That's great to hear!
Humalike
@savazverjtjn Thanks for trying! That's the gap we are trying to bridge. We want to offload the weight of trying to make your agent feel human. That's why the turn-taking API exists!
Congrats on the launch. Social intelligence gets useful only when the signal is explainable. When Hermes surfaces an insight about a person or community, can users inspect the evidence behind it and correct the signal if the system gets it wrong?
@yaroslav_stelmakh Hermes is the definition of auto-improving agent, it has memory and learns new skills. Humalike plugin also uses this information to adjust behavior, and even makes it stronger thanks to Social Learning API used under the hood.
Humalike
@yaroslav_stelmakh tysm!
Congrats team! 🚀 Love that you’re treating social skills as infrastructure rather than a prompt-engineering problem. Quick technical question: how does the Social Signals API detect things like typing pauses and deleted reactions? Does it need platform-level event hooks like Discord or Slack webhooks, or can it infer these from message streams alone? Curious how portable that is across stacks.
Humalike
@waqas_baloch4 Tysm!!
I have several questions about how this plugin operates in large and highly active group chats.
First, does the plugin have any limitations regarding the total number of group members or the number of simultaneously active participants? For example, in a group with dozens or even hundreds of members, where many people may be chatting at the same time, can the system still identify conversation structures accurately and operate reliably?
Second, when multiple participants are speaking and several topics are developing in parallel, how does the plugin determine whether it should join the conversation or remain silent? Does it make this decision based on keywords, contextual relevance, direct mentions, participant identities, urgency, or some other form of conversation analysis?
Third, in a fast-moving group chat, more than ten messages may be posted within only a few seconds. How does the plugin accurately determine which topic each message belongs to and avoid confusing an outdated discussion with a newer one?
Fourth, the description states that the plugin simulates human typing speed, pauses, and response pacing. What happens if the plugin decides to respond to a topic and begins “typing,” but the discussion ends or shifts to another subject before the message is sent?
Would the system:
cancel the pending response;
regenerate the response based on the latest messages;
send the original response even though it may already be outdated; or
reassess whether the response is still relevant before sending it?
Finally, the plugin may split a response into one to three short messages. This may feel natural in a slow-moving conversation, but in a highly active group chat, those messages could easily be separated by messages from other participants.
How does the plugin maintain the coherence and readability of its response in this situation? Can it automatically switch to a single complete message when the chat is moving quickly, or use features such as quoted replies, threaded replies, or direct mentions to make it clear that the messages belong to the same response?
Otherwise, users may need to search through the conversation to locate each part of the plugin’s reply. This could make the response difficult to understand, reduce users’ willingness to read it, and negatively affect the overall group-chat experience.
Been waiting for something like this honestly. Social intelligence layer for agents is kind of missing piece in most setups. Does it handle context persistance across long sessions or its mainly per-conversation?
jared.so
@abdurrahman_fakhrul It handles context persistence across long sessions :)) We want it to learn and use information from across many conversations.
I will gladly answer some more questions if you have any :))
Humalike
@abdurrahman_fakhrul :))))))
One thing that would help us a lot is a built-in persona memory layer where the agent remembers how it adapted its tone with a specific user last time, so we don't have to manually re-tune behavior across sessions.
Humalike
@hasanirantcwnt Exactly! That is our social-memory component. The agent remembers who people are and how past conversations went, and carries that into the next one, so it doesn't start cold or need re-tuning every session. Works across sessions and channels out of the box.
Humalike
@hasanirantcwnt Give it a try!
Can this be used with other agent frameworks like Eve or OpenClaw?
@gilad_tsehori Hey, humalike APIs are easy to build with. You can connect any kind of agent to Humalike. We don't have out-of-the-box integrations with Eve or OpenClaw though, let us know your use and let's chat!
Humalike
@gilad_tsehori Not yet, Hermes is first integration for now. If people find value on Hermes x Humalike, really soon it will be on Eve or OpenClaw