InsecureJezza

@JustinPerea @NousResearch You win. So good.

@NousResearch Try it here github.com/JustinPerea/ne…

My submission for the @NousResearch Hermes Creative Hackathon is my Hermes agent, Daedalus. He works inside Nebula Nodes — my open-source, node-based, infinite-canvas AI system. > Daedalus is a master-craftsman agent for creative AI. > Tell him what to build; he picks the right model for the job from the catalog (image, video, 3D, audio), wires it on a node canvas, and iterates with you. > He has skills for each model available so he knows how to achieve a goal you give him > You can work in the node without him and then chat to him when you are not sure how to do something > He has full context awareness of what is on the canvas and what is connected > You can let him run automatically towards a goal where he views and judges the output at each step on his own or you can let him ask for your opinion at each step Hermes Agent + Kimi K2.6. Learns your style across sessions. If Daedalus encounters and bugs, he will report that in his learnings so it doesn't happen again. @Teknium @Kimi_Moonshot

@Shpigford @_adembilican_ Every community is insufferable. I am yet to find an exception. Whether you let that blight the associated thing is kind of up to you 🤷‍♂️

@_adembilican_ because the hermes community is insufferable. massive blight on what may very well be fantastic software.

i'm so disappointed in myself right now

@harsette @outsource_ Original

@insecurejezza @outsource_ Ask your agents

HermesAgent SWARM is HERE Hermes-Workspace.com 🚨 NEW RELEASE v2.1 > Unlimited Hermes Agents > 1 Orchestrator > 0 Humans 💻 Orchestrator Chat 🤖 Multi-Agent Control Plane 🏆 Kanban TaskBoard 📄 Reports + Inbox ⌨️ TUI View, built in

@sudoingX Agree. Context being capped at 200k sucks though.

hermes agent with gpt 5.5 is fucking godly man. nothing anon, nothing else comes close. the way it keeps the thread, understands what i’m trying to do, and actually moves work forward. this is the daily driver feeling i was missing.

@thekitze Looks like freezer burned chocolate ice cream

i haven't had red meat in 8+ years so first time cooking steak roast my technique pls

@0xSero Man’s Search for Meaning - Victor Frankl Exhalation - Ted Chiang

What am I missing here? I’ve read tons of technical books, many classics, manga

@thekitze @tinkererclub I use Hermes. It’s an agent I can rely on and use remotely. I can self host things easily, I’m learning a lot using it and it surprises me every now and then. As a normie, I have infinitely more capability at my fingertips than I had at the beginning of February.

i'm glad it's not only me and ppl in @tinkererclub when so many ppl try to give this a PROPER CHANCE it might be an issue with the product [ffs do not tag the project or maintainers, if i wanted to i would]

@thekitze They’re good because they’re low friction.

discord and telegram are such a bad way to manage agents it's incredible it's gigacope wrapped in a ui

@MatthewBerman @steipete

I have to say it again - nothing but love for OpenClaw and @steipete. I am not abandoning OC. I just need to spend time fixing it.

@stevibe Z.ai more than doubled their coding plan prices btw. No warning. These prices aren’t accurate anymore.

Day 3 on Hermes Agent. Here's what happened so far. The brain: GLM 5.1 on Z.ai. Started on the Lite plan ($10/mo), but kept hitting rate limits during peak hours. Upgraded to Pro ($30/mo) by day two. Quality-wise? Had it write web tutorial content for my students, honestly on par with GPT and Claude. Not using it for code tho, Codex has been my coding brain for 6+ months already. First thing I tried: sent it a voice memo. It immediately started setting up Whisper. Told it to grab the V3 model, fully working in minutes. All running locally on a Mac Mini M1. Then I found a bug. Every time I asked it to install something, it fired off a "Hi~ I don't recognize you yet!" pairing message. Lowkey scared me at first. So I just… asked the agent to read its own logs, find the root cause, reproduce the bug, fix it, and restart the gateway. It did all of it. Didn't crash once. Was about to submit a PR but turns out there was already a fix on main. GLM Pro comes with web search and web read MCP. The agent read its own docs and configured the MCP servers by itself. Then I casually asked it to grab daily AI/tech/science news for me, it set up a cronjob on the spot. Still exploring.

@Teknium Hermes tool calls give me the warm and fuzzies

Do you prefer if tool call notifications were on or off by default in your favorite messenger in Hermes Agent?

@thekitze Doomer bait

🤣🤣🤣🤣 bros seriously need to fucking relax jesus christ

@Shpigford Sounds like you’ve decided on the Anthropic ecosystem offerings. If you can’t move past Opus and cost, don’t really see any other option 🤷‍♂️

what i want out of a personal ai system... * dynamic memory * plugins (for interacting w/ APIs) * skills (for running common workflows) * scheduling * remote access * chat threading/topics and i want it all powered by opus. and i don't want to pay $50-100/day for it. 🫣

@leftcurvedev_ Doubt

how to use siri with your hermes agent >create a new contact >add a url field with your bot link >select telegram as url type voila — you can now send anything to your agent through all your apple devices *you need to have an opened conversation for it to work

@Shpigford @Zai_org Did you give mimo-v2-pro a try?

my opus replacement: @Zai_org's GLM 5.1! spend the past couple of hours with it and so far it feels as close to opus/sonnet as i've seen. loving it. you need a glm coding plan to access it: z.ai/subscribe set up in 🦞: docs.z.ai/devpack/tool/o…

@Shpigford @Zai_org Chuck us a referral code. You may as well make some bread. Going to try it out myself.

@NousResearch The Pantheon update

The Hermes Agent update you've been waiting for is here.

@robinebers Seems like a proving ground for open source models. They can switch models in and out when they want. Great value, but the models you actually get on a weekly basis through Firepass will likely change.

this could be a great one to invest in early 250 tok/s is fucking insane

@RealRossRight @JulianGoldieSEO github.com/outsourc-e/her…

@JulianGoldieSEO Any recommendations for a command center to run this (paid or not) that doesn’t require terminal? There are so many for OpenClaw, any for Hermes…

This guy literally tested Hermes Agent vs OpenClaw side by side. Hermes won. And it wasn't close. Here's what made the difference: → Hermes built the website faster → Hermes gave live updates the whole time. OpenClaw went silent. → Hermes designed a cleaner page using the exact same AI model → And then Hermes did something OpenClaw can't do at all. It learned from the task. Every mistake gets logged. Every win gets saved as a reusable skill. The more you use it, the smarter it gets. OpenClaw doesn't do this unless you manually set up a learning file. Hermes does it automatically. Every single time. Other wins: → Runs free with Ollama + MiniMax → Works on Telegram, Discord, Slack, WhatsApp, Signal, and Email → Supports 200+ AI models → Built-in migration tool from OpenClaw — one command to switch 11,600 GitHub stars. 142 contributors. If you're already on OpenClaw, you don't have to start over. Just ask Hermes to import everything.