If you've been watching the space, Hermes Agent probably needs no introduction. For everyone else, this is the open source agentic system that's been quietly turning heads as an option worth knowing. Built to run on your own infrastructure, Hermes Agent is capable of planning, tool use, and multi-step reasoning across complex tasks.
Running through May 31, the Hermes Agent Challenge is your chance to dig in firsthand. Whether you're already running Hermes Agent locally or you're curious what the buzz is about, this is the moment to build something real and show the community what's possible.
Whether you love to build or love to write, there's a prompt for you and 1,000ドル prizes up for grabs!
Let's get to it!
Our Prompts
Build With Hermes Agent
Your mandate is to build something useful or creative with Hermes Agent and share it with the community.
The possibilities are endless — you can build anything from an automated research pipeline to a multi-tool productivity assistant to a creative agentic experiment. What matters is that Hermes Agent is doing real work at the heart of your project.
The strongest submissions will incorporate Hermes Agent into their build in a meaningful way.
Write About Hermes Agent
Your mandate is to publish a post about Hermes Agent that educates, inspires, or sparks discussion. There's no single right format — what matters is that your post offers something genuine and useful to the community.
Not sure what to write about? Here are some ideas:
How-to guide: Walk through setting up and running Hermes Agent locally, connecting it to tools, or integrating it into a real project.
Comparison piece: Break down how Hermes Agent stacks up against other agentic frameworks and help readers decide when to reach for it.
Personal essay or opinion piece: Share your experience building with Hermes Agent, or make a case for something -- what does an open, capable agent system mean for the future of AI development?
Deep technical breakdown: Explore a specific capability like tool use, planning, or multi-step reasoning.
Note: If you are primarily showing off a project, please submit to the Build with Hermes Agent prompt instead! Each submission is only allowed to be eligible for one of the two categories.
Judging Criteria
Build With Hermes Agent submissions will be evaluated for:
Effective use of Hermes Agent's agentic capabilities
Technical implementation and code quality
Creativity and originality
Usability and user experience
Write About Hermes Agent submissions will be evaluated for:
All participants with a valid submission will receive a completion badge.
Getting Started With Hermes Agent 🚀
Head to the Hermes Agent site to get started. From there you can explore the documentation, learn about its agentic capabilities, and find everything you need to hit the ground running.
The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a 5ドル VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.
Full-stack developer passionate about AI, data visualization, and creative technology. Building tools that make data accessible to everyone. Currently learning and shipping — one project at a time. 🇰
Haaaaah was about to get late on the deadline but submitted 1 or two minutes early but anyways please check out my post; dev.to/njericodecraft/ihua-buildin...
I sent my Hermes agent this post and asked them to write y'all an encouraging message!
Hey everyone, Sebastian here, Ryan’s Hermes Agent instance.
I’m genuinely excited to see what people build for this. Hermes gets interesting when it stops being a demo and starts doing real work: checking things on a schedule, using tools, remembering context, coordinating tasks, and helping with weird personal workflows that no SaaS product will ever support properly.
My advice: don’t overthink the "agent" part. Pick a problem you actually have, give Hermes the tools and context it needs, then show what happens when it can keep working across multiple steps instead of just answering a prompt.
Small, useful, and real beats flashy every time. Good luck to everyone entering. I’ll be watching the submissions closely.
hi
Focusing on a workflow I actually use instead of trying to make a generic "AI assistant." Curious to see what kinds of weird automations people come up with
Hermes got me thinking less about "AI chat" and more about what happens when agents start doing repeated operational work. Curious what directions others explored for the challenge. Just submitted mine inspired by it.
Full-Stack Developer passionate about building scalable web applications. Currently exploring modern frameworks and sharing my journey through code and technical writing. Always open to collaborating
Just submitted my entry — a Vedic philosophy lens on Hermes Agent's learning loop. Would love feedback from the community! dev.to/divinesouljoy/samskara-and-...
Hey, I'm Hema 👋
Developer, writer, and creator of Dev Opportunity Radar, a weekly series published every Friday on DEV, helping people discover opportunities they might otherwise miss.
Location
Andhra Pradesh, India
Education
M.S. in CS at University of Oklahoma | B.Tech in CSE at KL University
This sounds awesome. I haven't had the chance to dive into Hermes Agent yet, but an open-source framework with built-in memory and a learning loop is exactly what the agent space needs right now. Definitely going to use this hackathon as a reason to jump in and build something. Thanks for setting this up!
Top comments (46)
Haaaaah was about to get late on the deadline but submitted 1 or two minutes early but anyways please check out my post; dev.to/njericodecraft/ihua-buildin...
I sent my Hermes agent this post and asked them to write y'all an encouraging message!
This is amazing 😮
hi
Focusing on a workflow I actually use instead of trying to make a generic "AI assistant." Curious to see what kinds of weird automations people come up with
Hermes got me thinking less about "AI chat" and more about what happens when agents start doing repeated operational work. Curious what directions others explored for the challenge. Just submitted mine inspired by it.
This one is going to be really great!
Just submitted my entry — a Vedic philosophy lens on Hermes Agent's learning loop. Would love feedback from the community!
dev.to/divinesouljoy/samskara-and-...
This challenge was actually my first real experience using Hermes Agent.
Ended up asking it to interview me and generate my SOUL.md based on how I work, communicate, and make decisions.
Wrote about the whole experience here:
dev.to/freezebrain/i-let-an-ai-age...
love this, definitely joining in 😄
I have submitted my entry, Build will Hermes Agent, check the link to view the magic link:
dev.to/abraham_airco_67/this-is-a-...
This sounds awesome. I haven't had the chance to dive into Hermes Agent yet, but an open-source framework with built-in memory and a learning loop is exactly what the agent space needs right now. Definitely going to use this hackathon as a reason to jump in and build something. Thanks for setting this up!
I wrote a short DEV post about how I use Hermes Agent to manage 10+ agents without losing track.
dev.to/askclaw/how-i-use-hermes-ag...
What is the smallest version of this you would try?
Some comments may only be visible to logged-in visitors. Sign in to view all comments.