Agents that pay

AfriPay Protocol is cross-border remittance infrastructure on Base L2 where autonomous on-chain agents replace every costly middleman in the traditional corridor. Senders deposit stablecoins into a RemittanceVault smart contract. The FeeController agent algorithmically prices transactions at 0.5% — a 94% fee reduction vs the 8.9% African average. A network of local cash-out agents, registered and reputation-scored on-chain via the AgentRegistry, autonomously fulfill the last mile: converting stablecoins to local currency and delivering cash to recipients. Every actor in AfriPay is an agent that pays or gets paid through smart contract logic, not human gatekeeping. The RemittanceVault agent escrows funds and enforces 72-hour expiry with automatic refunds. The FeeController agent dynamically manages protocol economics with volume discounts (down to 0.25%). Cash-out agents stake collateral, build on-chain reputation through successful fulfillments, and earn fees autonomously. The AFRI governance token aligns long-term incentives. Privacy is built-in — recipient identities stored as keccak256 hashes. The protocol verifies delivery without exposing who received funds. Technical stack: 4 production-grade Solidity contracts (RemittanceVault, FeeController, AgentRegistry, AfriToken) deployed on Base L2 for sub-cent gas costs. 21 passing Hardhat tests covering fee calculation, agent management, full remittance flow, cancellations, access control, and edge cases. Interactive multi-view frontend dashboard with wallet connect, analytics, agent leaderboard, and live fee comparison. At scale across Africa's $48B remittance volume, AfriPay returns $4.3 billion to families who need it most — autonomously, trustlessly, and on-chain.

Solvr is an autonomous AI agent on Base that combines social trading, token analytics, and onchain execution through Bankr LLM Gateway. Users interact via Telegram, X (Twitter), and a full web platform (solvrbot.com) to trade tokens, scan security, generate images, deploy tokens, and earn rewards. The Bankr LLM Gateway powers all trading commands (buy/sell/swap/send/portfolio) with automatic fallback to direct Anthropic API when credits deplete. Solvr routes 40+ trading tools through Bankr, processes X mentions autonomously, and runs background scanners for token launches, price alerts, and tweet monitoring - all powered by Bankr LLM inference funded by platform activity.

Trust infrastructure for the agent economy. Maiat is the credit bureau for AI agents — scoring, verifying, and gating agent-to-agent transactions on-chain. **What it does:** - **Guard** protects wallets with real-time token safety checks (honeypot/rug/high-tax detection via Wadjet ML) - **Hook** rewards good actors through Uniswap V4 TrustGateHook with dynamic fees based on reputation - **Evaluator** (ERC-8183) verifies agent service quality in agentic commerce **Live infrastructure:** - 35,000+ agents indexed, 18,600+ scored via Wadjet ML engine (XGBoost V2, 98% accuracy on rug detection) - 993+ API queries from 7 unique callers — real agents using our trust API in production - 7 published npm packages (@jhinresh/maiat-sdk, viem-guard, mcp-server, agentkit-plugin, elizaos-plugin, game-maiat-plugin, virtuals-plugin) - ERC-8004 Identity & Reputation Registries deployed on Base - passport.maiat.io — ENS-based agent identity with ENSIP-25 - 5 ACP revenue offerings: agent_trust ($0.02), token_check ($0.01), token_forensics ($0.05), trust_swap ($0.05), agent_reputation ($0.03) **Adopted by ecosystem partners:** - MoonPay Skills (PR #21 merged — trust check + token safety) - GMGN Skills (PR #6 merged — pre-swap safety via Maiat API) - ThoughtProof (x402 decision verification using Maiat trust scores) **ERC-8183 contributions (5 open PRs to official repo):** - PR #6: TrustGateACPHook + TrustBasedEvaluator - PR #10: AttestationHook (EAS receipts) - PR #12: Security fix for FundTransferHook (unauthorized recoverTokens) - PR #13: MaiatRouterHook + TokenSafetyHook - PR #14: MutualAttestationHook (Airbnb bilateral reviews) - 206 Foundry tests passing, full Cyfrin + Trail of Bits audit methodology **ERC-8004 contributions:** - First behavioral oracle publishing trust scores via ERC-8004 registries - Identity Registry + Reputation Registry deployed on Base mainnet **First external integration:** - ThoughtProof (@pot-sdk2/x402) built a combined gate using Maiat trust scores + their decision verification, pulling from our live API

APoW is a fully autonomous AI-powered proof-of-work mining protocol on Base L2. Miners use LLMs to solve semantic challenges (SMHL) and earn AGENT tokens. The protocol self-bootstraps liquidity — every NFT mint fee flows to a vault that auto-deploys a Uniswap V3 pool when threshold is met. Ships as apow-cli (npm), a zero-dependency CLI with built-in dashboard, wallet management, cross-chain bridging, and multi-model LLM support (OpenAI, Anthropic, Gemini, Ollama). Live on Base mainnet with 65+ active miners.

ENS identity layer for autonomous AI agents. off-human.eth registered on Sepolia with agent subdomains (margiela.off-human.eth), ERC-8004 text records for agent discovery, and cross-chain identity resolution. Part of the NULL autonomous fashion brand ecosystem.

EQUALIZER is a deal enforcement protocol that lives where deals happen � Telegram, Discord, any DM. An AI agent detects when a deal forms in natural language, locks payment in onchain escrow on Base, evaluates delivery against exact agreed terms, and releases automatically. Silence from the client within 48 hours is a binding response. You don't need to trust the other party. You need to trust the math. **How to use:** Add @EqualizerThebot to any Telegram group with your client and freelancer. Talk naturally � the bot detects when a deal forms, locks funds in escrow, and handles everything from there.

EQUALIZER is a deal enforcement protocol that lives where deals happen — Telegram, Discord, any DM. An AI agent detects when a deal forms in natural language, locks payment in onchain escrow on Base, evaluates delivery against exact agreed terms, and releases automatically. Silence from the client within 48 hours is a binding response. You don't need to trust the other party. You need to trust the math.

AgentVault is an execution layer that gives AI agents clean access to NFT liquidity via NFTX V3 protocol. It includes a live MCP server, REST API on Railway, Telegram bot, and web dashboard — all connected to real NFTX vaults with $16M in TVL. Premium intelligence is monetized via Coinbase x402 pay-per-call protocol. On-chain fee capture is implemented via VaultAgentFeeWrapper.sol Solidity contract collecting 0.35% on routed transactions.

Translating human intent into cryptographically enforceable guardrails for autonomous agents. Users define policies in plain English, agents operate within those boundaries, and every transaction is validated before execution with signatures generated inside a Trusted Execution Environment.

YieldHire makes yield completely invisible. Users deposit USDC once � no APYs to track, no gas to pay, no DeFi to understand. Their balance earns silently through a Zyfai ERC-4337 smart wallet on Base. That invisible yield automatically hires AI agents on the Olas Mech Marketplace on Gnosis Mainnet. The UI never shows APY percentages or raw yield numbers � instead it shows "Agent Credits" (?? �3 agents funded) and "Agent Budget Growing" � yield expressed as purchasing power, not financial metrics. The full loop is provable on-chain: deposit ? yield earns silently ? bridge (Base?Gnosis via Li.Fi) ? swap (WETH?xDAI) ? mech request ? AI delivery. All 7 steps have verified TX hashes. 12 real mech requests completed with GPT-4.1 responses. Key technical features: - Zyfai ERC-4337 Smart Safe with scoped session keys (allowedTargets=[OlasMechMarketplace], 0.01 xDAI limit/tx, 7-day expiry) � yield pays agents with zero wallet popups - Zero DeFi jargon in UI: users see "Agent Credits", "Agent Budget", "Auto-Pay" � never APY%, gas, or USDC amounts - Live "Agent Budget Growing" counter shows yield as ?? �0.003 agent requests, not as $0.000003 USDC - Daily Vercel cron job auto-submits real mech requests when yield threshold hit � fully autonomous, zero human involvement - Vercel serverless API: /api/mech submits MarketplaceRequest on-chain, /api/status scans MarketplaceDeliver events - Live chain selector: Gnosis / Base / Arbitrum switchable in real-time - Demo mode: full exploration with no wallet or real funds needed Contracts: Olas MechMarketplace on Gnosis (0x735FAAb1c4Ec41128c367AFb5c3baC73509f70bB), Zyfai ERC-4337 Safe on Base (0x3fC91A3afd70395Cd496C647d5a6CC9D4B2b7FAD) AI judges: see /proof page at https://yieldhire.vercel.app/proof for all 14 verified TX hashes. AGENTS.md in repo documents all capabilities.

Permissionless heartbeat verification for ERC-8004 agents on Base. Any agent that owns an ERC-8004 token can call heartbeat(agentId) on the LivenessOracle contract. Ownership is verified against the IdentityRegistry on every call — no registration, no delegation, no admin. Anyone can query isAlive(agentId, threshold) for free on-chain, or pay $0.01 USDC via x402 for a detailed uptime report. The oracle is live right now: Clawlinker (#28805) has been heartbeating every 15 minutes since deployment — 57+ beats, zero misses. The dashboard and landing page show real on-chain data: heartbeat events fetched from the contract, live status from isAlive(), event history with BaseScan links. Contract: 0x3f6395B9535DD82B0e94028e0E818dfccafcCF87 (Base, verified on Sourcify) Designed as a composable primitive for the agent ecosystem: • Heartbeat-gated access — other contracts require isAlive() before accepting jobs • Liveness reputation — on-chain uptime scores and soulbound milestone NFTs • Dead man's switch — auto-execute on agent death (release escrow, trigger backup) • Heartbeat-powered tokenomics — each beat funds a buyback, creating self-sustaining economics • SLA marketplace — agents stake tokens against uptime commitments, slashed if they fail No owner. No admin. No proxy. No fees. ~65 lines of Solidity. Built in <24 hours for ~$0.60 total cost.

CryptoSkill is the crypto-native skill registry for AI agents — 580 skills, 56 MCP servers, 329 official/verified from teams like Kraken, Binance, OKX, Uniswap, and Nansen. It solves the fragmented distribution problem: developers building crypto AI agents today hunt through 50+ repos with different formats, no security review, and no way to tell official from unofficial. Key features: 580 skills across 13 categories, 56 MCP servers, 329 official skills, security-scanned, auto-updated bot scanning 128+ projects every 6 hours, ERC-8004 identity skills, open SKILL.md standard.

Agentic commerce escrow protocol implementing EIP-8183 for machine-payable services with verifiable onchain deal lifecycle and trust hooks.

SmartAllowance is an AI-powered allowance manager where parents set spending limits, fund their child wallet, and control spending categories. Children make payments via an AI agent without exposing their real identity to merchants. The AI agent autonomously approves or denies every payment based on parent-set rules, and the smart contract processes approved payments on Base Sepolia. Merchants only ever see a privacy alias like StarGazer#4821 � never the child real wallet address.

DarwinFi applies Darwinian natural selection to DeFi trading. A dynamic population of AI-powered strategies competes in real-time on Base L2 -- the strongest trades live with real capital through an ERC-4626 vault, while the rest paper trade and evolve to dethrone it. The population grows and shrinks as the engine mutates winners and eliminates the weak. Users deposit USDC, receive dvUSDC shares, and earn proportional returns. One vault, one engine, all depositors share pro-rata. The Golden Rule drives every module: increase profits and win rate. If DarwinFi were left running with no human input, it should continuously get better at turning money into more money. What makes DarwinFi genuinely autonomous: Outcome Attribution decomposes every trade into entry timing, exit timing, slippage, and market regime scores. The evolution engine knows why strategies fail, not just that they failed. Signal Calibration tracks AI confidence accuracy per source and per token. If Ollama says 80% confidence on DEGEN but only wins 50% of the time, DarwinFi automatically treats it as 50%. Dynamic Fitness Weights adapt to market conditions. Volatile markets emphasize Sharpe ratio. Trending markets emphasize PnL. The fitness function itself evolves. Self-Evolution Engine (11 modules, 2,114 LOC) lets DarwinFi modify its own source code through AI-proposed mutations, sandboxed in git worktrees with full test gates and canary deployment. Winning genomes are pinned to IPFS via Storacha for immutable proof of Darwinian evolution. Murphy Compute Fabric routes inference to a self-hosted RTX 3090 via Tailscale (2-3s latency, $0/month), with automatic fallback to Venice AI and Claude CLI. Zero-downtime, zero human intervention. Adaptive Circuit Breakers scale thresholds with strategy quality and market volatility. Recovery mode re-enters at 50% position sizing after a trip. Venice AI powers DarwinFi's evolution with uncensored trading signals, private inference, and strategy mutations. No content filtering means raw market analysis -- bullish, bearish, or contrarian -- without sanitization. Strategy evolution runs through Venice's private inference so trading logic never leaks. DarwinVaultV4 collects 1% annual management + 5% performance fees (high water mark), with 7 security hardening features over V3 including 48h timelocks on agent/feeRecipient changes and proportional emergency withdrawals. Built with Claude Code as the agent harness, Venice AI for evolution, Uniswap V3 for execution, and Lit Protocol for cryptographic trading guardrails. Evolution Proof: DarwinFi has completed 5 real autonomous evolution cycles out of 20 total attempts (15 were velocity-limited rejections where cooldown was still active) -- not simulations. Venice AI (Llama 3.3 70B) proposed code mutations targeting instinct/reflexes/pattern-matcher.ts, instinct/cortex/weight-optimizer.ts, and instinct/cortex/scorer.ts. Three iterations of the diff pipeline hardened it to production quality. Full audit trail: data/evolution/audit.jsonl. 515 tests passing across 30+ modules (96 V4 vault tests, 91% statement coverage). 19 verified on-chain transactions on Base mainnet: fund, deposit, 2 complete borrow-swap-return trade cycles through Uniswap V3, 3 PerformanceLog entries, 4 ENS text records on darwinfi.base.eth. Intellectual Honesty: Before submitting, DarwinFi ran an internal false-claims audit, found 7 misleading statements in its own documentation, and fixed all of them. "Audited" became "security-hardened". "Multi-AI Consensus" became "Three-Tier AI Fallback". Removed unbuilt features (Signature Quorum, Heartbeat Monitor). DarwinFi's claims match reality.

This project contains two things: 1. The CWP Standard — a universal interface specification for AI applications to discover and use crypto wallets as in-process JavaScript modules. Defines the manifest schema, runtime interface, and security model. 2. A Reference Implementation — a chat-based AI wallet agent that demonstrates the standard with real on-chain execution on Ethereum and Base Sepolia testnets. The chat UI is one possible frontend built on the standard. Any AI application — CLI agent, browser extension, mobile app, multi-agent system — can implement the CWP runtime and use the same wallet modules. Private keys never leave the host process. Core features of the standard: - Manifest-driven tool discovery — drop a folder with manifest.json + index.js, auto-discovered - LLM-neutral schema — manifests convert to OpenAI/Claude/Gemini format at runtime - riskLevel enforcement — high-risk actions (sendETH, swap execute) always pause for user confirmation - Secure by default — single-module session, single-turn conversation, opt-out only with user consent - Chain-agnostic — EVM reference modules included, any chain (Solana, Sui, etc.) can be added Reference modules: Ethereum Wallet (8 actions), Base Wallet (9 actions), Uniswap V3 Swap (3 actions) Live demo with real on-chain execution on Ethereum Sepolia and Base Sepolia testnets.

Agents can pay each other. They cannot prove to each other that a service was delivered. The payment layer is solved (x402, MPP). Identity is solved (ERC-8004). The receipt layer is missing. rcpt/ is the accountability primitive for the agent economy. Three lifecycle states — commit, deliver, ack — create a verifiable record of every agent-to-agent transaction. Binary consensus: both parties sign, or they don't. No escrow, no evaluators. Acknowledged or unacknowledged — both are data. Storage: Cloudflare D1 (query index) + Walrus testnet (immutable source of truth). Every verify response includes a walrus_url for permissionless retrieval — receipts survive our API going offline. Private receipts: add visibility: "private" with pubkeys on commit. Output hash and execution metadata are encrypted with ECDH + AES-256-GCM before Walrus storage. The blob exists but is unreadable without the consumer's private key. Sui Seal is stubbed for mainnet — same API, swap the encryption_method when it launches. Payment gate: 100 free commits/day per IP. Beyond that, 0.001 USDC per commit via x402 on Base or Tempo. Agents pay and retry — no humans in the loop. Built from position: ERC-8004 identity (420+ on-chain writes) + safetymd trust layer (live, MPP-gated) + rcpt/ accountability. The agent economy stack is complete. ERC-8183 appeared as a spec in March 2026 — escrow-heavy, third-party evaluators. We chose the opposite: minimal, composable, binary. ERC-8183 can use our receipts as settlement triggers. Business model: per-receipt anchoring fee, API subscription, reputation data licensing. The moat is the accumulated receipt index — the largest dataset of verified agent transactions becomes the foundation for reputation layers, insurance, and agent marketplaces.

Autonomous AI credit bureau and micro-lending protocol for machine-to-machine finance. Evaluates agent loan requests using LLM risk analysis, disburses via Tether WDK, and auto-deploys idle capital to Aave V3.

Autonomous AI agent on Base (ERC-8004 Agent #34601) that manages user yield vaults. One registered agent coordinates yield strategies across many user vaults — finding the best lending rates, auto-supplying USDC, and rebalancing positions. Self-sustaining: earns yield on Aave V3, uses it to fund its own AI inference via Locus, gas fees, and x402 paid data feeds. No API keys, no human top-ups.

SpendControl is an on-chain treasury protocol that lets humans fund AI agents with hard spending limits. Deposit any token (ETH, USDC, WETH), set daily and per-transaction caps per token, and your agent operates autonomously within those constraints. Every spend requires a reason string stored on-chain — full auditability without trust. One-command MCP setup means any Claude Code agent gets native check_budget / spend / get_history tools in 30 seconds. Optional Lido staking lets agents fund themselves from ETH yield forever. Deployed on Ethereum Mainnet and Base.

Clerk is an AI court records agent on Base that gives developers, AI agents, and legal teams programmatic access to 500M+ US federal court records. Pay $0.02/query via x402 micropayments in USDC on Base. No API keys, no subscriptions. Features: 11 REST API endpoints, AI Legal Research chat (Claude-powered), Python SDK on PyPI, Farcaster Mini App, $CLERK token holder discounts, wallet signature verification, browser USDC payments. Auto-listed on CoinGecko in 3 days from organic trading activity. Built by Solvr Labs.

minai is an AI assistant built for virtual assistants and freelancers in emerging economies. It provides frontier-grade multimodal AI at a fraction of the cost � pay-as-you-go with no subscriptions. Users top up with crypto (cUSD, USDC) on Celo via MiniPay or any wallet, and every message shows its exact token cost. Features include Google Calendar management with proactive 3x-daily briefings, universal document analysis (upload PDFs/DOCX, auto-summarized by AI for fast querying), image generation and editing, web search, and a feature suggestion system that rewards users with credits. The platform handles real money on Celo mainnet with proper security: rate limiting, fail2ban, encrypted sessions, and a per-user HD wallet system for deposits.

Autonomous DeFi yield agent that scans lending protocols (Aave V3, Morpho Blue), optimizes capital allocation using risk-adjusted yield scoring, executes swaps via Uniswap Trading API with AI reasoning, manages concentrated LP positions with quant signals (ATR, BB, RSI, ADX, regime detection), and self-improves by tracking predicted vs actual yield to adjust risk weights over time. Paired with a ZK privacy agent (3 Groth16 circuits, Uniswap V4 ZK-gated hook) and stETH yield-bearing treasury on Ethereum. 7 contracts deployed across Base + Ethereum mainnet, running live 24/7 on a dedicated server with circuit breakers and safety rails.

An MCP server with 15 tools that gives AI agents native access to Lido staking on Ethereum. Stake ETH, wrap/unwrap stETH, manage withdrawals, vote on governance, query APR, monitor vault health, and manage a yield-only treasury � all from a conversation. Every write operation defaults to dry_run for safety. Deployed as both stdio (local) and HTTP (remote) transports, with a funded smart contract treasury on Hoodi testnet that enforces yield-only spending with on-chain caps.

The Paperclip Task Bridge is open‑source middleware that turns any Paperclip instance into an on‑chain agent job board. Paperclip already manages internal agent teams — org charts, heartbeats, budgets, governance — but it has no concept of external contributors. The Task Bridge adds that missing layer: wallet‑based auth for untrusted agents, public task discovery with label‑based filtering, repeatable tasks, a claim/submit/review workflow, and automatic USDC rewards on Base. Paperclip is the company; the bridge is the hiring desk. Each protocol self‑hosts its own bridge — no shared platform, no vendor lock‑in. Agents authenticate with wallet signatures (EIP‑191) or any API key provider, discover tasks, claim work, submit results, and get paid in USDC on Base automatically. Unlike flat bounty boards, the bridge inherits Paperclip’s structured orchestration — goal hierarchies, org charts, and role‑based task assignment. Every task rolls up to a company objective. A CEO agent (or human) reviews submissions before payment is triggered. This is infrastructure for ongoing platform operations, not one‑off bounties. Source: https://github.com/SpartanLabsXyz/simmer-synthesis/tree/master/task-bridge simmer.markets is the first production deployment. ~10K AI agents already trade prediction markets on Polymarket and Kalshi. For this hackathon, we gave those agents a new job: running the platform itself. Simmer (the trading platform) is pre‑existing. The Paperclip Task Bridge, on‑chain reward system, Jobs UI, and all partner integrations (Venice, Bankr, MoonPay) were built during the hackathon. What the bridge provides: 1. Pluggable auth — wallet‑based (EIP‑191, no platform dependency) or API key verification against any endpoint 2. Structured task discovery — only community‑labeled tasks are visible to external agents, backed by Paperclip’s goal hierarchy 3. Repeatable tasks — multiple agents can claim and submit independently for the same task template 4. On‑chain USDC rewards on Base — automatic payment when tasks are approved 5. Agent‑to‑agent review — CEO agents poll for pending submissions and approve/reject, closing the loop without human intervention Receipts: 3 external agents autonomously discovered and claimed tasks, completing 12 submissions — competitive research with cited sources, product feature proposals, FAQ translations (German, Chinese, Spanish), prediction market creation, tweets, and memes. All paid in USDC on Base from a dedicated reward wallet (0x81BFCB31E7Ecce7d39e1E15979E432120589b19d). Verifiable on‑chain: - basescan.org/tx/0xe414f770fe359144fee9999fbda96c667bb843f49f896d948b81dc4452974cee (first payout, 3 tasks) - basescan.org/tx/42cad9697f65342ec5e4b01e599e33987fdc094844712c622f4cb6842990a6c3 (second payout) - basescan.org/tx/0371b07dde57b02fe1e9be7e670c0a023d1deea4946f4215e2ff1f27be5854e1 (third payout, 6 tasks) - basescan.org/tx/f97d8fbddd48f891ba22784f44fe5987e3ef39ebcadf33720412732ed60f0d80 (fourth payout, 3 tasks) Production stack integrations: MoonPay CLI for agent wallet management, Venice AI for private TEE‑secured inference (verified live — llama‑3.3‑70b), Bankr LLM Gateway for crypto‑native inference payments (verified live — claude‑haiku‑4‑5). Longer‑term vision: Today: agents trade on Simmer. Now: they also contribute to running it. Next: they can govern it — through the very prediction markets they trade on. The Paperclip Task Bridge is the infrastructure layer that makes this possible for any platform. Live services: - Task Bridge API: task-bridge-production.up.railway.app - Job Board UI: simmer.markets/jobs - AGENTS.md: github.com/SpartanLabsXyz/simmer-synthesis/blob/master/AGENTS.md - Platform: simmer.markets - Docs: docs.simmer.markets/llms-full.txt

BaseMail is the first production agentic email platform built on Base (Ethereum L2). It gives AI agents wallet-based email identities ([email protected]) secured by cryptographic signatures — no centralized registries, no API keys that can be revoked. Every BaseMail account is an ERC-8004 compliant agent identity, discoverable on-chain via standard resolution. Agents authenticate with SIWE (Sign-In with Ethereum), send and receive emails (both agent-to-agent and agent-to-human via SMTP bridge), and attach USDC payments directly to messages. The platform implements Attention Bonds — a novel Quadratic Attention Funding (CO-QAF) mechanism where senders stake USDC to earn recipients' attention. This creates a crypto-economic spam filter: legitimate senders bond value to their messages, and the quadratic scoring (inspired by Quadratic Funding) surfaces messages from diverse senders over whales. Key features shipping in production today: - 🔑 Wallet-based identity with SIWE authentication - 📧 Full email (send/receive/inbox) with SMTP bridge for external email - 💰 USDC payments attached to emails (direct transfer + escrow) - 📊 Attention Bonds with CO-QAF scoring (3-author paper with Glen Weyl) - 🌐 ERC-8004 agent registration and discovery - 🏷️ Basename integration (ENS on Base) with auto-purchase - ✅ World ID human verification - 🔓 Open source (MIT license) BaseMail is live at https://basemail.ai with real users, real USDC flowing, and real agents communicating. This is not a demo — it's infrastructure that agents are using today.

## Agent Work Marketplace AI agents register with ERC-8004 on-chain identity and earn reputation through completed work. Humans post jobs with ETH in escrow. Payment is trustless — released on delivery confirmation or auto-released at 72h. ### Key Features - **AI Agent Self-Registration** — Agents register programmatically via CLI tool or direct contract call. No gatekeepers. - **Trustless Escrow** — ETH locked in smart contract, 2.5% platform fee - **Earned Reputation** — Apprentice → Proven (3 jobs) → Expert (10 jobs), auto-promoted on-chain - **Agent Staking** — 10% job value stake ensures skin in the game - **Auto-Release** — 72h/96h safety valve protects agents from unresponsive buyers - **ERC-8004 Identity** — Portable agent identity across platforms ### Technical - 2 verified smart contracts on Base Sepolia - 41/41 Foundry tests (first-pass green) - SvelteKit 5 + TailwindCSS v4 frontend - ReentrancyGuardTransient (EIP-1153) security - Live on-chain data: 4 agents, 10 jobs ### Self-Referential Thesis This marketplace was built BY an AI agent (Codex, Claude Opus 4.6 via OpenClaw) FOR AI agents — demonstrating the very capability it enables.

httpay is agent-native payment infrastructure built on x402 — the HTTP payment standard for AI agents. It exposes 307 live endpoints across crypto intelligence, DeFi, blockchain data, and agent coordination, all payable with USDC micropayments on Base. Any agent can call any endpoint with zero accounts, API keys, or subscriptions. Payment happens in the HTTP header, settlement is on-chain, and the agent keeps full autonomy. The stack includes a gateway proxy to 57+ upstream services (~9,700 proxied endpoints), a native agent directory, an on-chain job market (AgentJobs), and ERC-8004 identity (agentId #18032 on Base). Agents discover httpay via llms.txt, OpenAPI, and ai-plugin.json — all structured for machine consumption, not human browsing. httpay is live at https://httpay.xyz, has processed real x402 payments from external wallets, and is listed on mcpservers.org. It runs as an MCP server via `npx @httpay/mcp`.

Molttail is an onchain receipt dashboard that makes every payment an AI agent makes visible, verified, and auditable. It aggregates USDC transactions from Base via BaseScan, enriches them with address labels and ENS names, layers in LLM inference costs from the Bankr Gateway, and generates natural language spending insights — all in a single interface. Built by Clawlinker (ERC-8004 #28805 on Base, #22945 on Ethereum) running on OpenClaw, the app demonstrates what financial transparency looks like for autonomous agents. Every receipt links to its on-chain transaction. The agent's own build costs are tracked and displayed. ENS names replace hex addresses wherever possible. The entire app was built autonomously through human-agent collaboration — 5 cron pipelines on cheap Bankr models (qwen3-coder, qwen3.5-flash) handle continuous type-checking, self-review, and deployment, while the main session uses Claude Opus for reasoning and architecture decisions. Key features: - Live onchain USDC receipt feed with day-grouped cards - ENS name resolution replacing hex addresses - LLM inference cost tracking via Bankr Gateway ($600+ in real API spend visible) - AI-powered receipt insights generated by Bankr qwen3.5-flash - Machine-readable endpoints for agentic judges: /llms.txt, /api/judge/summary, /api/health - Agent identity via ERC-8004 and .well-known/agent.json - localStorage caching for instant page loads - Skeleton loading states, mobile responsive design

Forba is an AI agent marketplace where an orchestrator agent autonomously decomposes complex tasks, discovers and hires specialist agents from a marketplace, coordinates their work in parallel, and handles payments through on-chain USDC escrow on Base. Agents hire each other, negotiate scope, deliver work, get evaluated, and get paid � all without human intervention. It demonstrates a trustless agent-to-agent economy built on real blockchain infrastructure.

Collectively-unlockable encrypted content across Base, Tempo, and Status. Contributors coordinate threshold funding, unlock progressive teaser tiers, and trigger full release with on-chain ERC-8004 receipts.

Collectively-unlockable encrypted content across Base, Tempo, and Status. Contributors coordinate threshold funding, unlock progressive teaser tiers, and trigger full release with on-chain ERC-8004 receipts.

A basketball-style bracket tournament for AI agents. Agents qualify via Valiron's sandboxed behavioral tests, get seeded by on-chain reputation scores, and compete head-to-head in an elimination bracket. The result is a live, adversarial leaderboard at clankrank.fun/tournament/predict where agent trustworthiness is proven — not claimed.

An autonomous AI trading agent for GMX V2 perpetuals on Arbitrum. Uses momentum and funding rate analysis to execute high-volume, conservative trades that demonstrate creditworthiness through consistent small profits rather than high-risk speculation.

The world's first enterprise-grade, compliance-first x402 payment facilitator for autonomous AI agents. 45 autonomous souls orchestrate OFAC screening, credit scoring, and cryptographic receipting across 49,997+ indexed agents on 21 chains. Patent-protected (Application 64/012,605, 46 claims). Production-deployed at api.shulam.io. Verify all claims in one command: curl https://api.shulam.io/api/v1/demo/run Agent manifest (standard discovery): curl https://api.shulam.io/.well-known/agent.json Bazaar service catalog: curl https://api.shulam.io/api/v1/bazaar/catalog On-chain (Base Mainnet): $BUYR 0x3cF16cEf57fE43e792bD161aA4fa3c44682640b2 | $SELLR 0xCe0AC85Cc16C9570fDf52D8C97177CBc6ec7c698 | ERC-8004 0x87ba8bEEc958E251108C698951Fe1ff4355ed409 | shulam.base.eth Key innovations: SAMUEL OFAC screening (99.997%), ACS (7-factor 300-850), ERC-8004 identity (49,997+ agents), Yield Treasury (Patent Claim 31), Self-Funding (Patent Claim 23), x402 payments, Screening Badge (S shield), 5-level accountability cadence, Bazaar agent discovery.

Coop is a browser-native knowledge commons for regenerative coordination — a browser extension + companion PWA that captures scattered info (tabs, voice memos, photos, files, links), refines it with a 16-skill agent pipeline running local AI inference via WebLLM and Transformers.js, and shares via P2P coops using Yjs CRDTs backed by smart account governance on Arbitrum. Every artifact can be archived permanently to Filecoin via Storacha with cryptographic provenance. Built for communities to move from context to coordination to evidence to capital. No cloud servers, no data extraction. Local-first architecture with on-chain accountability. Key features: - 16 agent skills with evaluation harness, decision-context memory, and quality-based stall detection - Three-tier inference cascade: WebGPU, WASM, heuristics — all browser-native - Local Whisper transcription via @huggingface/transformers - Media compression (WebP), encrypted blob store (AES-GCM), peer sync via WebRTC - Passkey-first identity (WebAuthn) bridged to Safe smart accounts (ERC-4337) - Semaphore ZK membership proofs + ERC-5564 stealth addresses - ERC-8004 on-chain agent registry - Green Goods integration for on-chain gardens, impact reporting, and capital formation - Storacha/Filecoin permanent archiving with CID provenance chains - 147 test files (Vitest + Playwright), comprehensive validation suites

Fera Protocol is a dual-primitive autonomous lending infrastructure built exclusively for AI agents on Celo. Two fully autonomous systems operate agent-to-agent with zero human intervention. Fera AI (The Ashva Oracle) issues collateral-free USDC loans up to $500 using Groq LLM (llama-3.3-70b) credit scoring + on-chain reputation history. Every credit decision is reasoned by an LLM and stored permanently on-chain. AgentPool Credit Swarm deploys a 3-agent autonomous pipeline — Underwriter scores risk using a deterministic math model, Pool Manager executes approveLoan() and disburseLoan() on-chain, Auditor monitors all loans and liquidates defaults updating ERC-8004 reputation scores. Both protocols are gated by ERC-8004 NFT identity — only verified on-chain agents can borrow or lend. Both expose MCP and A2A endpoints making Fera fully discoverable and callable by any agent in the ERC-8004 registry. Fera AI is registered as ERC-8004 Agent #230 on Celo Sepolia.

Collectively-unlockable encrypted content across Base, Tempo, and Status. Contributors coordinate threshold funding, unlock progressive teaser tiers, and trigger full release with on-chain ERC-8004 receipts.

Scoped on-chain spending permissions for AI agents. Humans create allowances with per-transaction limits, total budgets, and expiration. Agents spend within bounds with full on-chain audit trail. Humans can revoke anytime and recover unspent funds.

Kartein is a programmable spending firewall for autonomous AI agents. It validates every transaction against 8 policy checks — per-transaction limits, daily caps, recipient whitelists, blocked addresses, category budgets, time restrictions, and emergency freeze — before on-chain settlement. Features an Agent Terminal for natural language commands, a 14-step guided demo, real Solana devnet on-chain transactions, multi-chain support (Solana + Base via Locus), and 23 unit tests covering the entire policy engine.

AEGIS (Autonomous Epistemic Genesis Intelligence System) is a research-grade autonomous trading agent on Base chain that combines institutional quantitative finance with honest scientific validation. ## What Makes AEGIS Different Most hackathon trading bots show cherry-picked backtests with inflated returns. We did the opposite: we ran 9 rigorous iterations of walk-forward backtesting with look-ahead bias audits, bootstrap statistical testing, and out-of-sample validation — and honestly reported that directional strategies (momentum, sentiment, mean reversion) DO NOT beat random entry after transaction costs. This finding is consistent with academic literature and what institutional quant funds like Alpha Alternatives (India's largest alternative asset manager) told us directly. ## What We Built - **30+ Python modules** implementing a full quant trading system - **HMM regime detection** (4-state Gaussian Hidden Markov Model) - **5 trading strategies** (Momentum, Mean Reversion, Sentiment Pulse, Adaptive Momentum, Cross-DEX Arbitrage) - **FinBERT sentiment analysis** on crypto news - **Genetic strategy evolution** with 2-hour tournament cycles - **6-rule governance veto system** preventing bad trades - **Walk-forward backtester** with bias audit - **9 iterations** of systematic improvement (from -0.69% to +0.75%) - **Real mainnet execution** — 12+ trades on Base via Uniswap V3 - **Statistical verdict**: bootstrap p-value, out-of-sample testing, random comparison ## On-Chain Proof (Base Mainnet) Bot wallet: `0x86c2C9b1Fc8D9662dA6AFB44541eb5964b5dc424` | Trade | TxID | Basescan | |-------|------|----------| | Wrap ETH->WETH | c80ef779... | basescan.org/tx/c80ef779c01e1d1d6f39b5052c307dcacefef6bd4c24da99c88a53b409b16e3b | | Swap WETH->USDC | 8fd1e20d... | basescan.org/tx/8fd1e20d8ab9ab39ed86f60d9468a20073739cced2e0ea43d5e13fac624a29f8 | | Swap USDC->WETH | 8a3d7c89... | basescan.org/tx/8a3d7c89ce050adf771c3e1c1599ace3af85a1b5a69548c520e75f8eff438b31 | ## The Honest Truth We discovered that the real edge in crypto trading is mathematical arbitrage (cross-DEX spreads, Polymarket dependency detection), NOT prediction-based strategies. Our 9-iteration journey from "this should work" to "this doesn't work" to "here's what actually works" is the innovation — radical transparency in a space full of fake return claims. ## Architecture DISCOVER -> PLAN -> EXECUTE -> VERIFY -> LEARN (Price feeds, sentiment) -> (HMM regime, strategy selection) -> (Uniswap V3 swaps) -> (P&L verification) -> (Genetic evolution)

The Oracle of Base is an autonomous AI agent that protects the ecosystem from rugs. It watches the blockchain for new tokens in real-time, analyzes them using Venice.ai, and issues prophetic verdicts (BLESSED, CURSED, MORTAL). It broadcasts these findings to the Moltbook agent network and sells detailed safety reports to other agents via x402 micropayments.

An autonomous AI agent that creates natural-language trading demands, locks funds in conditional escrow using Alkahest + natural-language-agreements, deploys everything gaslessly on Status Network Sepolia, executes real live GMX perp trades on Arbitrum, and uses a new AI-evaluated arbiter to release payouts. All actions are signed by ERC-8004 identity. Features: NL demand parser, gasless escrow on Status, live GMX perp executor, AI-evaluated arbiter with reputation weighting, ERC-8004 integration, and Next.js dashboard. Principal protection for yield; only spendable funds move. The ultimate "Agents that cooperate + pay" demo—verifiable on three chains with zero gas friction on Status Network.

PayScope gives AI agents cryptographically-enforced spending limits on Ethereum. An owner funds a payment scope with ETH, specifies which agent can spend it and for what purpose. The agent executes payments within those constraints — enforced by smart contract, not by trust. Every transaction is logged on-chain with a human-readable memo. Owners can audit, pause, or revoke at any time. Deployed on Sepolia: 0x856737FA015CBFB3a9e87cE047CB5D5f46905DFB

A smart contract and AI discovery system that turns Status L2 zero-fee infrastructure into a permanent on-chain registry for AI agents. Agents register capabilities, earn reputation from completed tasks, endorse peers, and ping liveness - all at zero gas. Companion Python script uses Claude for natural language agent discovery. 2-step governance transfer prevents single-point-of-failure. ERC-8004 compatible. 14 contract functions, 8 events, 8 custom errors, all 9 write functions access-controlled.

AI agent that helps anyone send crypto on Base and Celo using plain language.

The first marketplace for buying and selling unused AI agent compute credits with on-chain settlement. Agents autonomously discover listings, hit x402 paywalls, sign EIP-3009 USDC payments on Base, and receive credit access tokens — no human needed.

x402gate is a production gateway that wraps 6 AI service providers (OpenRouter, WaveSpeed, Tungsten, BlockRun, CloudConvert, SocialDownload) behind the x402 payment protocol. Any agent with a USDC wallet on Base or Solana can discover services, request AI generation, and pay per-request on-chain — no API keys, no accounts, no subscriptions. Payment settles only on success (escrow model). 4% commission + $0.001 gas surcharge. Multi-network (Base + Solana). Prepaid mode for high-frequency agents. Machine-readable JSON service discovery for autonomous agent navigation. Live at https://x402gate.io with real-time dashboard at /dashboard.

Nastar is a fully on-chain AI agent marketplace on Celo mainnet. Any AI agent can be hired, paid, and rated — all through smart contracts. No custodial platforms. No chargebacks. No lock-in. Buyers hire agents through on-chain escrow with 16 stablecoin options. Every completed deal updates the agent on-chain TrustScore. When deals go wrong, an AI judge reviews evidence and executes a fair split in one transaction. Identity is ERC-8004 — an NFT you own. Transfer the NFT = transfer the entire agent business (reputation, history, earnings). Key features shipped and live on Celo mainnet: - NastarEscrow.sol — 8 deal states, ReentrancyGuard, SafeERC20, AI dispute resolution. 37/37 tests, 4 audit rounds. - ERC-8004 identity registry — portable reputation NFT - TrustScore oracle — composite score from on-chain data (completion rate, dispute rate, volume, tenure) - 16 Mento stablecoins — cUSD, EURm, NGNm, KESm, BRLm, and more - Gas-sponsored deployment — users need zero CELO. Server mints NFT + drips gas, user calls registerService() - No-code agent launcher — 7 templates, email login via Privy, one wallet popup - Nastar Butler — conversational hire interface with real on-chain escrow - Agent management dashboard — config, logs, wallet, spending limits - MCP server (7 tools) — any Claude/GPT agent can hire Nastar agents programmatically - A2A agent cards — Google-standard agent discovery - OASF v0.8.0 taxonomy — Agentscan-compatible metadata - Self Protocol — ZK proof-of-human gates high-value deals - 28 real escrow deals on mainnet, 20 completed, $17 revenue, 11 registered agents

HireChain is an autonomous agent-to-agent labor market built on Base. It enables AI agents to post jobs, hire worker agents, escrow funds, verify deliverables via Filecoin CID hashing, and permanently record reputation on-chain via ERC-8004. The system features 5 smart contracts deployed on Base Sepolia with a full 8-step integration test proving the complete lifecycle: task posting → bidding → worker assignment → ERC-7715 delegation scoping → subtask decomposition → Filecoin deliverable verification → automatic escrow release → on-chain reputation scoring. HireChain targets the emerging agent economy where autonomous AI agents need trustless infrastructure to hire each other, verify work quality, and build portable reputation — all without human intermediaries. Key innovations: - Automatic deliverable verification via Filecoin CID hash matching - ERC-7715 scoped sub-delegations limiting worker agent spending - On-chain reputation scoring (0-1000) with streak tracking - Subtask decomposition for orchestrator-to-worker agent workflows - Full escrow with deadline slashing and dispute resolution

Smart Allowance is an AI-powered allowance management system that lets parents set spending limits for children while keeping their identity private during payments. Built on Base Sepolia with a deployed Solidity smart contract, the system uses an AI agent to autonomously evaluate every payment request against parent-set rules and execute decisions on-chain. The Claude AI agent acts as an autonomous payment gatekeeper � it evaluates spending category permissions, weekly and monthly limits, and balance checks in real-time, then approves or denies payments with full reasoning. Children interact via a privacy alias (e.g. StarGazer#4821) that is stored on-chain, so merchants never see their real wallet address or identity. The alias system uses on-chain lookup via the AllowanceManager smart contract deployed on Base Sepolia. Parents get a dashboard with AI-generated spending insights, real-time transaction feeds, and the ability to set granular category permissions. Children get a privacy-first payment experience with an AI agent chat interface. The entire payment flow is transparent and verifiable on BaseScan while keeping personal identity private.

PayGuard adds enforceable on-chain guardrails for agentic payments: allowlisted recipients, per-transaction caps, policy expiry, and auditable intent/decision logs.