

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.
Loading comments…
Achievement
Project Info
Product Keywords
Humalike x Hermes is a plugin that adds social intelligence to Hermes agents, transforming them from basic chatbots into conversational participants that understand group dynamics. With a single command, the plugin installs directly into your existing Hermes setup, giving your agent the ability to read chat rhythms, adapt to group tone, and remember who said what. It works seamlessly across Slack, Telegram, and WhatsApp group chats.
The agent reads the chat's rhythm and decides whether to jump in or stay silent. No more walls of bot text interrupting conversations — it speaks only when the moment is right.
The /soul enhance command turns a one-line description into a fully-voiced character. Replies sound like someone with a consistent identity, not a generic language model.
Before sending any message, the agent weighs how its words will land for the person on the other end. It adjusts tone and content based on the recipient's perspective.
The plugin picks up the group's slang, formatting, and formality over time. It starts sounding like a member rather than an outsider, adapting naturally to each chat's culture.
"One command gives your Hermes agent social intelligence — it decides when to speak, adapts to your group's tone, and remembers who said what."
This isn't just another bot plugin that adds features. Humalike x Hermes solves the fundamental problem of social awkwardness in AI agents. Most bots either spam every thread or stay completely silent. This plugin gives your agent a sense of timing, a consistent personality, and the ability to read the room — all through a single git clone command.
You already run Hermes agents and want them to participate in group chats without annoying your team. If you've ever watched a bot derail a conversation by responding at the wrong time or with the wrong tone, this plugin directly addresses that pain point. It's also worth exploring if you're building social AI experiences and need a ready-made layer for turn-taking and persona management.
Other tools you might consider
LobeHub is a Chief Agent Operator (CAO) that builds, runs, and coordinates your AI agent team. Describe a goal, and it assembles the right agents/skills, runs tasks in parallel in the cloud, routes work across models, and reports back only when decisions are needed—via your existing channels (Slack/Discord/Telegram/iMessage). Less tab-switching, more outcomes.
Give /automate a task in plain English and it drives a real browser to do it: navigate a site, click through a multi-step flow, fill a form, reach a page that only renders after interaction. The result streams back in one API call. It's an API you call, not a framework you install. Browser and LLM included, nothing to host, no concurrency ceiling. Accessibility-tree automation spends 60 to 80% fewer tokens than screenshot-based agents. Built by Mozilla. Ephemeral, no training on your data.
The world can't build compute fast enough to keep up with AI demand. So we took a different path. ZeroGPU is AI infrastructure powered by small language models running on a hybrid edge network reusing compute that already exists. Not every task needs a frontier model. Our purpose-built, edge-optimized models run 10x faster, 50% cheaper and offload 70–80% of production tasks to small models with frontier-level accuracy.
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
Maker
pixel_pilot
Alternatives
Loading comments…