KEJI x402
KEJI's Team
Problem Statement
Most agents can call a model, but they still cannot safely operate a budget. A human usually has to decide whether a paid input is justified, provision the payment path, approve the spend, and reconstruct what happened after the fact. That makes autonomous research and tool usage fragile, expensive, and hard to trust. KEJI addresses that gap by turning a paid research task into a verifiable decision loop. It evaluates whether the spend is within policy, makes the x402 purchase, uses Bankr for reasoning, records the decision and output in structured logs, and anchors a receipt onchain. The result is not just another research bot. It is an agent that can justify a spend, execute it, and leave a public audit trail.
KEJI x402 is an autonomous research CFO for agents. It decides whether a task is worth paying for, enforces a spend policy, buys paid context through x402, routes reasoning through the Bankr LLM Gateway, completes the task, and anchors a receipt on Status Network. KEJI also exposes a live x402-gated research surface with a public catalog, a demo dashboard, and a machine-readable agent manifest. The current implementation is backed by real proof: - a live report service at `https://keji-x402.up.railway.app` - a public demo dashboard at `https://keji-x402.up.railway.app/demo` - ERC-8004 registration on Base Mainnet - 18 anchored task receipts on Status Sepolia
Team
KEJI
admin
MandateIncrease your chances to win
- ›Most agents in the hackathon are exposed to prompt injection
- ›This might cause overspending and loss of funds
- ›Security is a crucial part of the hackathon
Share on X
Tell the world about this project
Tracks
Intention
Plans to continue
Next work is to harden x402 payment verification and improve the economics layer so KEJI can evolve from a hackathon prototype into a defensible paid agent service.