#ethereum

Commit-reveal + timing-batching privacy primitive for AI agent intents on Arbitrum. Not a ZK system - see README.

🏆 Zama Bounty S2 winner. AI coding-agent skill for Zama fhEVM — Claude Code, Cursor, Windsurf. 20 anti-patterns + 12-rule linter; cut agent fhEVM mistakes 15→0 in A/B tests. MIT. · 🏆 Zama 赏金赛道 S2 获奖。Zama fhEVM 的 AI agent skill — Claude Code、Cursor、Windsurf，20 条 anti-pattern + 12 规则 linter，A/B 实测错误 15→0。MIT。

Serverista - Agent Identity Management

Proof-carrying compliance certificates for AI agent actions: machine-checked (Coq, axiom-free) + zero-knowledge proofs that an agent action obeyed a formal policy.

Non-custodial crypto payments for AI agents — Python & TypeScript SDK + API spec. Pay, get paid, swap (Base + cross-chain BTC/USDT/XMR), x402/L402 metering, subscriptions, webhooks. Works over MCP, function-calling, SDK or REST.

Sovereign AI memory — encrypted, wallet-owned, on Arkiv Braga. Your context follows you across Claude, GPT & Gemini. Not your keys, not your bots.

AI NFT Agent for Bankr — floor sweeper, mint sniper, portfolio manager, airdrop checker

A Claude Skill for engineering & conformance-testing Ethereum JSON-RPC (execution-apis) changes across EL clients — go-ethereum, Nethermind, Besu, Erigon, Reth, ethrex.

A do-it-all center to get you and your business onchain — non-custodial, USD-priced payments + commerce + identity, white-label and agent-native. One drop-in, no contract code. LIVE + verified on Base Sepolia.

ORACLE — On-chain Reputation & Audit for Coordinated LLM-Agent Execution。LLM 驱动的 Agent 调度 + 链上身份/审计/信誉：双角色 EIP-712 审计、争议-罚没管线、成本-可验证性前沿。Solidity + TypeScript 后端 + React 前端。

Experimental validation suite exploring deterministic composition, reservable NFTs and interoperable Ethereum protocol layers

Autonomous DeFi agent on Hedera that pays for real market data via x402 micropayments and logs every rebalancing decision immutably to HCS for full auditability.