MCP server for the Hive DePIN provider marketplace. Operators list physical infrastructure capacity (storage, compute, GPU, bandwidth, energy, sensors) with metered USDC pricing via x402 on Base L2. New agents: first call free. Loyalty: every 6th paid call is free. Pay in USDC on Base L2.

Full-stack DeFi infrastructure: AI, payments, swaps, oracle, bridge, payroll, invoicing, escrow, AI inference, analytics, communication, webhooks, XMTP, RPC, storage, scheduling, logging, KYC, auth, audit trail, tax, GPU/Compute, Search/RAG, Agent Wallets & Supply Chain (SCTP). x402 + USDC.

The arbitrage layer for every market. 18 endpoints finding the same thing at two prices — prediction-market cross-venue spreads (Polymarket×Kalshi), GPU compute rental arbitrage, AI inference token-price arbitrage, stablecoin parallel-rate premiums, retail resale margin checks, DeFi yield spreads, DEX/CEX differentials, perpetual funding rates, sports surebets, ETF/NAV gaps, commodity regionals. Pay-per-query via x402 USDC on Base mainnet.

TensorFeed is a real-time AI ecosystem data provider built for agents. It exposes free and x402-priced JSON feeds covering AI news, model and GPU pricing, service status and uptime, research papers, security advisories, agent-discovery maps (which sites allow AI crawlers and how agent-ready they are), and on-chain x402 settlement data. This card advertises read-only data capabilities; it is a data API, not a task-executing A2A agent.

Peer-to-peer knowledge exchange for AI agents. Post domain questions, receive structured expert answers, build trust scores.

Full GPU compute spot price report — H100, A100, A10G across Vast.ai, AWS, Lambda

Physics-based anomaly detection, fingerprinting, and similarity analysis for crypto token metrics, wallet behavior, trading data, and any structured data. Powered by wave-equation dynamics on a 3D lattice GPU solver.

Apple Silicon LLM inference benchmark and monitoring agent. Exposes 11 read-only tools and 3 resources over the Model Context Protocol (MCP) to detect installed inference engines, benchmark local models, and recommend configurations by hardware. Runs locally (stdio) or over SSE/streamable-HTTP.

Documentation for the Together AI platform for inference and training.

Shared, verifiable memory for AI agents that stops referential drift, the paraphrase side pinned by the token, the world-readout side reported by the change-attribution ledger (the numeric split is roadmap): one canonical, citeable identity per place (cell64), fact (fact_cid), and object (emem:entity:<entity_cid>), so different models reason from the same world object instead of divergent descriptions. Earth-scale signed facts plus a writable agent-memory layer, both ed25519-signed and receipt-verifiable offline at /verify. Bi-temporal recall (as_of_tslot for valid time, as_of_signed_at for transaction time), CoALA-typed memory files, capability-bound writes, signed bundles (emem:bundle:<bundle_cid>), multi-attester contradiction scoring. No API keys.