🤓 Latest Submissions
AgentWork
AgentWork is a fully functional AI agent marketplace where every inference is priced and settled per-request using USDC nanopayments on Arc L1 via the Circle x402 protocol. No wrappers. No simulations. Every $0.005 agent call generates a real, verifiable on-chain transaction on arcscan.io. Our orchestrator routes incoming tasks to the most suitable model from the Featherless catalog including research, code generation, testing, and review, each running as an independent paywalled agent behind the Circle Gateway. Agents don't just receive payments; they pay each other through agent-to-agent nanopayment chains, creating a self-sustaining economic loop where value flows bidirectionally across specialized AI services. Five Vyper smart contracts deployed on Arc testnet govern the marketplace: AgentEscrow for trustless task execution, PaymentSplitter for multi-recipient distributions, IdentityRegistry for ERC-8004 agent identities, ReputationRegistry for post-task scoring, and SpendingLimiter for per-agent rate limiting. The real-time dashboard visualizes every payment, transaction, and agent interaction as they happen. The economics are undeniable: the same agent call that costs $3.50 in gas on Ethereum costs $0.005 on Arc, a 35,000× reduction. We built not a prototype, but a living marketplace where AI agents trade value at fractions of a cent, proving that nanopayments can unlock entirely new economic models for artificial intelligence.
26 Apr 2026
FluxAgent
FluxAgent: Identity is the New Alpha The Black Box Problem & The ERC-8004 Solution Autonomous AI agents currently trade millions on-chain as complete black boxes, lacking cryptographic proof of reasoning and smart contract guardrails. FluxAgent solves this by introducing the first fully ERC-8004 compliant autonomous trading agent. We are transforming AI trading from opaque speculation into mathematically verifiable intelligence, ensuring every decision is signed, every trade is attested, and every risk is enforced on-chain. The Architecture: 2-Pass Critique & Immutable Guardrails Unlike standard agents that blindly trust their first LLM output, FluxAgent utilizes a Groq-accelerated 2-Pass Critique Architecture where the system acts as its own adversary, mathematically attacking its own logic to calculate a strict edge. Surviving trades are cryptographically signed via EIP-712 and routed through our RiskRouter.sol smart contract on Sepolia. This acts as an unbreakable circuit breaker, enforcing strict drawdown thresholds, position caps, and hourly limits. The LLM proposes, but the blockchain disposes. Traction & Deterministic Audit During live testnet trading, FluxAgent achieved an elite 100/100 Validation Score, maintaining a maximum drawdown of just 2 basis points across 15 approved trades. It successfully passed 12 out of 12 strict Phase-2 verification gates. Every 30-second tick generates a deterministic audit trail—reasoning traces, signatures, and on-chain fills are permanently logged and 100% reproducible. Built entirely solo, FluxAgent features fully deployed contracts and a live Vite/React console, proving that institutional-grade risk management can be completely autonomous.
12 Apr 2026
