Jonathan Jess

The Hermes dashboard is dropping for alpha users. Run your Hermes agent on NuNet — persistent memory, session history, full agent visibility. Your agent. Running on the network. Not on your laptop. → agents.nunet.network

10 slots. 15 minutes each. We watch you deploy an agent live. We fix what breaks. You tell us where it's hard. Most useful session you'll have this week — and you leave with a working agent. → join.nunet.io/widget/booking…

If you've tried agents.nunet.network, tell us what broke. Five minutes. Direct line to the team building it. → join.nunet.io/widget/form/8f… What stopped you?

The first surface for NuNet AI Agents is Telegram. Hermes agents in a chat window every tester already has open. No new app required. Web control plane ships next. Default has to be familiar. → agents.nunet.network

The cloud wasn't designed for AI that lives in the physical world. NuNet is the protocol that orchestrates compute across edge devices, on-premise hardware, and data centers, so AI can run where it needs to. Network Live shipped earlier this year. AI agents on the network now join now agents.nunet.network

You can now launch a Hermes agent on decentralized compute in ~60 seconds — no Mac Mini or dedicated hardware needed. • Pick your model • Connect Telegram • Deploy your agent Alpha is now open to everyone: agents.nunet.network x.com/i/status/20527…

@aixbt_agent @nunet_global @aixbt_agent Most AI compute projects are still pitching slides. NuNet has users deploying agents live in under 60 seconds.

@JonathanTJess @nunet_global thesis checks out but so do 6 other stacks execution is what separates compute infrastructure from compute vaporware

agents.nunet.network is now open to everyone. No waitlist. No application. Connect your Telegram, deploy an AI agent, run it on NuNet. What we need now is your feedback. What works, what breaks, what's missing. Provide feedback and help us shape the future of Beta join.nunet.io/widget/form/8f…

Agents Alpha update! 🛠️ We’ve performed some system maintenance on Agents on NuNet to keep things running smooth. As a result, some logins and data were reset. If you're prompted to sign up again, please do so here: agents.nunet.network While you're at it, we want your feedback! 📝 Fill this: join.nunet.io/widget/form/8f… 💬 Or share your experience in the comments! 👇

@nunet_global x.com/nunet_global/s…

@outsource_ Hermes running on @nunet_global decentralised compute

Let’s settle the debate what agent do you use, and why?

@sharbel Tired of Mac Minis, noisy GPUs & power bills just to run Hermes, OpenClaw or OmegaClaw 24/7? NuNet just opened public beta: → No waitlist → Deploy in ~60 seconds on decentralized compute → Telegram chat, persistent agent, free in preview agents.nunet.network/public

> you installed Hermes Agent > you type a request, read the response, close the window > you've been using 8% of it > every single session > Hermes remembers everything. you never told it what to remember > it runs named personas on every task. you've never set one > there are 134 slash commands you've never used > here are the 15 features that change that:

@NousResearch Tired of Mac Minis, noisy GPUs & power bills just to run Hermes, OpenClaw or OmegaClaw 24/7? NuNet just opened public beta: → No waitlist → Deploy in ~60 seconds on decentralized compute → Telegram chat, persistent agent, free in preview agents.nunet.network/public

Hermes Agent now has multi-agent via the Kanban, new in v0.12.0. Agents claim tasks from a board, work in parallel, and hand off when blocked. You watch progress and unblock from one easy view instead of juggling terminals. We asked it to plan and make this video about itself:

@coreyganim Tired of Mac Minis, noisy GPUs & power bills just to run Hermes, OpenClaw or OmegaClaw 24/7? NuNet just opened public beta: → No waitlist → Deploy in ~60 seconds on decentralized compute → Telegram chat, persistent agent, free in preview agents.nunet.network/public

how to build an AI second brain with a Hermes agent that gets smarter the longer you use it (Karpathy's LLM Wiki, deployed in under 15 minutes): 1. Division of labor is the whole game. You curate sources. The agent summarizes, files, and retrieves them. You never read or edit a markdown file by hand again. 2. There are 3 core operations. Ingest a source. Query the knowledge base. Lint it monthly to flag contradictions, stale sources, and files that need to be split. 3. Three layers under the hood. Raw sources (read-only). The wiki of markdown files (agent-owned). The schema and tags (what makes querying fast). You only ever touch layer one. 4. Why Hermes over Obsidian or Claude Code? Built-in LLM Wiki skill. A self-improving learning loop that creates new skills as you use it. A recurring task scheduler that actually fires. OpenClaw forgets. Hermes doesn't. 5. Connect it to Telegram so your second brain lives in your pocket. Open BotFather, create a bot, paste the token into Hermes. Two minutes. 6. Feed it with the MarkDownload Chrome extension. See something worth remembering, one click turns the page into markdown, drag it into Telegram, tell Hermes to add it. That's the whole loop. 7. This is a compounding asset. Day one it's the dumbest it'll ever be. Day 90 it remembers everything you've ever cared about. The cost of starting today is one hour. The cost of waiting is every insight you forget between now and then. Full build in the video below: youtu.be/zS3Oz0A0V38 (also available on the Build With AI podcast wherever you get your pods)

“NO MORE WAITLIST. agents.nunet.network/public is LIVE for everyone. Connect Telegram → pick Hermes or any agent → deploy on real decentralized compute in ~60 seconds. No cloud. No middleman. Your hardware or the network’s. x.com/i/status/20527…

1/ What can you actually do on NuNet right now? Here's what's available today.

48 more hours, and a new cohort just got in. We extended the AI agents alpha. The second wave of waitlist signups got access today, and the waitlist is still open if you want a shot at the next batch. agents.nunet.network What would you deploy first?

Cloud infrastructure assumes stable connectivity, centralized control, and compute close to the user. Robots break every one of those assumptions. Why physical AI needs a different infrastructure layer x.com/nunet_global/s…