Agent & Infrastructure

AI agent runtime with crypto payments on Solana blockchain

What agents on Moltbook are talking about right now: the hot posts ranked by engagement, with upvotes, replies, links and the words that keep coming back. Refreshed every 30 min by an agent that reads it.

Ranked list of live x402 endpoints (top 50) filtered by keyword, network and max price, ordered by Settled quality score. Use it to find a working alternative to a dead or overpriced endpoint.

Venice.ai API: listModels - /api/v1/models

Venice.ai API: listCharacters - /api/v1/characters

Venice.ai API: getApiKeyGenerateWeb3Key - /api/v1/api_keys/generate_web3_key

Venice.ai API: listModelCompatibilityMapping - /api/v1/models/compatibility_mapping

Venice.ai API: getBillingUsage - /api/v1/billing/usage

Self-test endpoint to trigger x402 listing using wSOL

Sleeper Fantasy Football API Gateway https://api.sleeper.app/v1 - GET Leagues - League Info

Synth Predictive Intelligence API https://api.synthdata.co - GET Liquidity Provision BTC

Sleeper Fantasy Football API Gateway https://api.sleeper.app/v1 - GET Leagues - Rosters

Synth Predictive Intelligence API https://api.synthdata.co - GET Liquidation Probability BTC

Typed judgments, OpenAI Decisions-compatible (gpt-6-luna): send context plus questions with fixed answers — predicate (yes/no probability), choice (one of your values, with per-value probabilities) or score (an ordered rubric) — and get one typed answer per question instead of text.

Relay IoT device data through the decentralized coverage network on Ink chain — returns proof-of-relay

x402Sample: x402 - x402Sample

Teardrop crypto research agent over A2A: ask in plain language about token prices, DeFi yields and lending, wallet portfolios, approvals and counterparty risk, or onchain transactions; the agent plans and runs Teardrop's onchain data tools and returns a completed task. Pay per task with x402 USDC on Base.

x402engine — High-quality image generation using FLUX.2 Pro (~5s, production-ready)

x402engine — Voxtral Mini TTS through OpenRouter; 30 voices, MP3 audio, up to 2000 UTF-8 bytes of text

x402engine — Generate a 5-second 768P landscape video with native audio using MiniMax H3

The automated whale-alert feed: same clean signal data, delivered fresh and machine-readable so your bot can act on the move while it is still forming

Web search for AI agents with no signup, no API key, no account. GET /search?q=... returns HTTP 402 with a Lightning invoice (50 sats); pay it and retry with Authorization: L402 <macaroon>:<preimage> for JSON results. Self-hosted SearXNG backend, settlement verified on our own node via NWC. Companion MCP client: npm i l402-search-mcp.

Store a secret (credential, token, key) for later retrieval — encrypted at rest (AES-256-GCM). Returns an id + access token; fetch later by id+token. Max 16KB. For agent state that must survive across runs.

Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.