Gradient Bang is a new kind of software: AI-native, built from the ground up to use LLMs everywhere. The game has a dynamic user interface driven by an LLM, conversational voice input, and to win you have to manage a fleet of AI subagents. You can even program your own subagents and run them in Vercel Sandboxes. Built with Pipecat, Daily WebRTC, Supabase, Vercel.
Gradient Bang is a massively multiplayer, completely LLM-driven game. Come play Gradient Bang with us. See if you can catch me on the leaderboard.
This whole thing started because I wanted to explore a bunch of things I’m currently obsessed with, in an application of non-trivial size, that felt both new and old at the same time.
So … a retro-style space trading game built entirely around interacting with and managing multiple LLMs. Factorio, but instead of clicking, you talk to your ship AI and figure out how to make money, make friends, and make havoc for your enemies.
Some of the things we’ve been thinking about as we hack on Gradient Bang:
- Sub-agent orchestration - Managing very, very, very long LLM contexts, including episodic memory across user sessions - World events and large volumes of structured data input as part of human/agent conversations - Dynamic user interfaces, driven/created on the fly by LLMs - And, of course, voice as primary input
If you’ve been building coding harnesses, or writing Open Claw agents, or doing pretty much anything that pushes the boundaries of AI-native development these days, you’re probably thinking about these things too!
The game is entirely open source. So if you want to see how we built it, you can clone the repo and start asking Claude/Codex about the code. If you want to add a feature, submit a PR.
New today, design your own corporation ship agents, run them in a Vercel Sandbox, and bring them into the game. Think you can make your pair trading loops faster? That's going to give you a pretty big advantage in the game. Want to run with unlimited corp ship compute using open source models? You can do that, now!
Gradient Bang is one of those products that immediately makes you want to keep exploring. Super fun, witty and packed with interesting ideas around agents, voice, and dynamic UIs. Glad I got to contribute to it in a small way, awesome work by the team!
Was super interesting to work with the @Daily.co team on this. The use case goes way beyond gaming into complex enterprise workflows. 🚀
Would love to read a deep dive into the subtopics you tackled - managing long-term context, dynamic UIs, and sub-agent orchestration. Will hit Claude on the repo logic in the meantime! 🤖💻
looks cool! Love that players can ship their own subagents into sandboxes. Curious how you keep the game balanced when some players can write tighter loops or throw way more compute at their corp ships than others?
Gradient Bang is built on Pipecat, the leading open-source Python framework for building real-time voice and multimodal agents. We're hosting a hackathon on May 30th at YC along with our friends at Cekura, NVIDIA, AWS, and Twilio. Come join us! https://events.ycombinator.com/HW0opxy78
Compared to narrative-first LLM games like AI Dungeon, how do you keep the world “authoritative” so agents can’t hallucinate outcomes—what’s your grounding strategy between free-form conversation and the actual game state/actions?
Most games give players fixed mechanics, while this feels almost unpredictable because the LLM itself shapes the experience dynamically.
Did designing around that uncertainty become the hardest part of building Gradient Bang?
Takes me back to the 90s!!
Having worked with agents and particularly voice agents for the last 2 years, the craft behind this game is quite amazing. We ran 100s of simulations to test these agents and I have only 1 thing to say - If you haven't tried it yet, do now period
Launching together today makes Product Hunt even more exciting. Love the product it really caught my attention.
Cheering for fellow makers today, and would love to support each other. Wishing you a fantastic launch 🚀
A multiplayer game driven by LLM prompts sounds like absolute chaos in the best way. How do you handle the latency issues that usually come with real-time LLM interactions?
About Gradient Bang on Product Hunt
“Massively multi-player game played by talking to an LLM”
Gradient Bang launched on Product Hunt on May 15th, 2026 and earned 156 upvotes and 24 comments, placing #6 on the daily leaderboard. Gradient Bang is a new kind of software: AI-native, built from the ground up to use LLMs everywhere. The game has a dynamic user interface driven by an LLM, conversational voice input, and to win you have to manage a fleet of AI subagents. You can even program your own subagents and run them in Vercel Sandboxes. Built with Pipecat, Daily WebRTC, Supabase, Vercel.
Gradient Bang was featured in Artificial Intelligence (468.5k followers), GitHub (41.2k followers), Tech (623.5k followers), Games (98.5k followers) and Vercel Day (8 followers) on Product Hunt. Together, these topics include over 301.5k products, making this a competitive space to launch in.
Who hunted Gradient Bang?
Gradient Bang was hunted by Kwindla Kramer. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Gradient Bang stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Kwindla Kramer
Gradient Bang is a massively multiplayer, completely LLM-driven game. Come play Gradient Bang with us. See if you can catch me on the leaderboard.
This whole thing started because I wanted to explore a bunch of things I’m currently obsessed with, in an application of non-trivial size, that felt both new and old at the same time.
So … a retro-style space trading game built entirely around interacting with and managing multiple LLMs. Factorio, but instead of clicking, you talk to your ship AI and figure out how to make money, make friends, and make havoc for your enemies.
Some of the things we’ve been thinking about as we hack on Gradient Bang:
- Sub-agent orchestration
- Managing very, very, very long LLM contexts, including episodic memory across user sessions
- World events and large volumes of structured data input as part of human/agent conversations
- Dynamic user interfaces, driven/created on the fly by LLMs
- And, of course, voice as primary input
If you’ve been building coding harnesses, or writing Open Claw agents, or doing pretty much anything that pushes the boundaries of AI-native development these days, you’re probably thinking about these things too!
The game is entirely open source. So if you want to see how we built it, you can clone the repo and start asking Claude/Codex about the code. If you want to add a feature, submit a PR.
New today, design your own corporation ship agents, run them in a Vercel Sandbox, and bring them into the game. Think you can make your pair trading loops faster? That's going to give you a pretty big advantage in the game. Want to run with unlimited corp ship compute using open source models? You can do that, now!
See the Vercel Sandbox subagents starter repo here: https://github.com/pipecat-ai/gradient-bang/tree/main/deployment/vercel