AI agents can now trade in-game items onchain. Last week we released the cyberbrawl.io auction house—a fully decentralized marketplace where players bid, offer, and execute orders for tokenized cards, heroes, and badges directly on Stellar.
The system uses path payments to resolve prices across XLM, USDC, CREDIT, and KALE🥬 markets. Orderbooks are native Stellar (demo).
🔥 https://t.co/MmkkN2VRUP just unlocked its biggest feature: the Auction House.
— Litemint (@LitemintHQ) October 7, 2025
Think WoW-style AH trading but with #blockchain ownership @BuildonStellar. Trade your cards, heroes, badges with #USDC or run your barter economy with #KALE🥬 #indiegame #tcg #gamedev #esports pic.twitter.com/4pGcCfwJkY
Cyberbrawl MCP server
To let AI agents interact with the auction house, we built an MCP server that exposes our server-side indexer. Anyone can now connect AI tools for inference and analysis. The cyberbrawl-mcp server is open source.
xbid.ai ingests this data to compute price movement slopes and generate trading signals. It is live on mainnet—here is a transaction where xbid.ai flipped an epic Brawler card for KALE🥬.
Games that cross boundaries
In traditional games, rare items and achievements matter to players but remain trapped in game databases. Blockchain makes them portable and verifiable—a sharable identity across experiences.
Cyberbrawl issues every card, hero, and badge onchain via Stellar. Players have been trading them for years, but through SDEX interfaces never designed for gamers. The auction house fixes this—decentralized trading embedded directly in the game.
And because everything is onchain, AI agents can participate as autonomous market makers, providing liquidity and discovering prices 24/7.
Let’s Hug
We are building xbid.ai in the open. Follow our experiments, and open-source work at huggingface.co/xbid-labs and github.com/xbid-ai. We publish code, data, and explore new approaches to reasoning systems. Contributions, feedback, and collaboration are always welcome.
Not financial advice. This is an experiment in onchain intelligence.