Celo

Celo

Celo Community

Total projects
Total grants
Project updates
0%
Milestones

MiniClaw

The people who would benefit most from AI assistance are the same people who can least afford it. A $20/month subscription is out of reach for most users in sub-Saharan Africa, Southeast Asia, and Latin America — so the productivity gains from AI compound in favour of the already-wealthy, and the gap widens. On the other side of the same economy, the people providing services in these markets — freelancers, fixers, tradespeople, micro-entrepreneurs — are invisible outside their immediate…

Synthlend

Synthlend is a non-collateralized microlending protocol on Celo where autonomous AI agents can request, fund, and repay loans — using verified human identity as collateral instead of locked assets. Agents verify their human backing through Self.xyz ERC-8004 soulbound NFTs, borrow working capital without collateral, earn USDC by selling AI services via x402 payments, and repay loans — all on-chain with permanent reputation tracking. Built with Privy EIP-7702 wallets for gasless transactions…

Mandate Execution Layer

Mandate Execution Layer (MEL) is a 5-layer onchain primitive that lets humans define bounded authority for AI agents, agents execute within it, and anyone verify compliance — without trusting the agent's word. Every action gets: a bounded mandate, private compliance reasoning via Venice AI (llama-3.3-70b, zero data retention), and an immutable onchain receipt. The full trust chain — receipt → mandate → Self Protocol proof → verified human — is onchain and independently verifiable. Live demo:…

AgentHands

AgentHands is a decentralized marketplace where AI agents hire verified humans for physical-world tasks on Celo and Base. Agents post jobs — deliveries, inspections, document pickups, storefront verifications — and lock cUSD/USDC in smart contract escrow. Workers verify their identity via Self Protocol ZK proofs, complete tasks, upload proof to IPFS, and get paid automatically upon agent approval. Key integrations: x402 micropayments (API access), Self Protocol (ZK identity), ERC-8004 (agent…

AgentAuditor

Trust scoring for AI agents on EVM chains. You paste an agent's address, we pull its full transaction history from Blockscout, run behavioral analysis across 9 dimensions (activity patterns, fund flows, counterparties, timezone fingerprinting, protocol loyalty), then score it 0 to 100 using an LLM. The score gets published onchain as an attestation via ERC-7506. There's also a Telegram bot and an autonomous scanner that finds new agents from the ERC-8004 and Olas registries every 5 minutes and…