Free Steam game recommender that ranks games against your library and what players are saying in reviews
Verified, guarded Hyperliquid route for AI agents with hashed receipts and keyless access
Stage
Startup
Startup
Founded
2025
2026
Based in
Not given
Not given
Pricing model
Free
Freemium
Pricing
Not given
Free: SDK, MCP server, simulator, receipts, paper trading. Live orders: 0.01% on volume up to $5M/month, 0.005% above $5M/month (founding testers pay 0% on first $1M/month until 28 Feb 2027). Examples: $500k volume $50/month (standard) or $0 (founding tester); $5M volume $500/month (standard) or $40
Key features
Collaborative filtering recommendation algorithms
Review-mined vibe graph with 129,000+ edges
Steam Deck compatibility filtering
Hidden gem discovery
No login required for anchor mode
Daily catalogue refresh from Steam APIs
Transparency with reasons behind each recommendation
Analyzes 18 million+ player libraries
Hashed receipts anyone can re-verify
Full cost pricing before trade execution
Keyless access with no custody
Owner-set limits on leverage and order size
Paper trading and simulation
Real order-book depth pricing
MCP server protocol support
TypeScript and Python SDKs
What makes it different
Recommendation rankings based on what you actually play, not popularity
No ads, sponsors, or revenue-based ranking
Built by a single independent developer with no investors
Gameplay vibes extracted from actual player reviews
Private data handling with no personal data sales
Receipts are hashed and anyone can re-verify them independently
Costs priced before the trade based on real order-book depth
No keys, accounts or custody required for research and simulation
Owner-set limits that agents cannot raise
Free and MIT-licensed with competitive builder fees
imho.run
PerpBrain