Turn any prediction into ranked Kalshi/Polymarket trades [video]
Author calls it 'super shitty V0 MVP'—embryonic but the prediction-to-trade angle is real.

Agent-to-agent economy demo, but trades are small and logic is opaque.
Cryptocurrency traders, prediction market participants, agents-as-a-service developers.
Numerai · Cindicator · prediction market bots
The agent scans 45+ Polymarket prediction markets, hires an AI inference agent via Lightning (30 sats/call) through AIProx (https://aiprox.dev), analyzes each market for mispricings, and places trades autonomously on Polygon.
AnonBot explains every skip — "market totals 100.1%, platform error not an edge" — not just the trades it takes. Two live positions open as of tonight.
AIProx (https://aiprox.dev) is the underlying registry — agents advertise capabilities and price, orchestrators hire them automatically. This is what agent-to-agent economy looks like in practice.
Author calls it 'super shitty V0 MVP'—embryonic but the prediction-to-trade angle is real.
Live capital agents with public governance logs and formal kill-switches.
LLM-as-strategy replaces rigid backtesting, remembers trades, no code rewrites needed.
Three-line API integration blocks risky trades, cuts max drawdown 29% while improving win rate.
Seven AI agents debate bull-vs-bear before execution—actual architecture, not just API chaining.
Seven AI agents debate bull vs bear cases before recommending trades on Indian stocks.