Runix

Runix is an execution platform built specifically for autonomous agents and software systems that need to run compute workloads without managing infrastructure. Through one unified API, you can execute code in isolated sandboxes (Python, Node, Go, and more), trigger external API calls, fetch and process data, and maintain stateful sessions across executions. Each request is sandboxed, retried automatically, and settled with per-execution pricing — you pay only for what runs, with no monthly subscriptions, no idle capacity costs, and no infrastructure to configure. Runix handles queuing, isolation, timeouts, and parallel execution out of the box. It's designed for agents, AI systems, financial services, data platforms, and any workload where traditional cloud billing models don't match actual consumption patterns.

TriviaFi – Onchain Trivia Game with USDC Rewards

TriviaFi is an onchain multiplayer trivia game built on Arc Network that allows users to compete in real-time quiz rooms and earn USDC rewards. Players can connect their wallets, join or create game rooms, and answer timed questions. Winners receive trustless payouts directly onchain, removing the need for centralized control. The platform features an automated agent that continuously creates and manages game rooms based on demand, ensuring there are always active games available. This agent intelligently limits game creation using cooldown logic and active game tracking to prevent excessive fund usage while maintaining engagement. TriviaFi integrates wallet authentication, smart contract game logic, and backend verification to ensure fair gameplay and prevent replay abuse. All results are processed securely, and rewards are distributed transparently using USDC. Built with a modern stack including Vercel (frontend), Render (backend), and GitHub Actions (automation), TriviaFi demonstrates a scalable decentralized gaming infrastructure. By combining blockchain transparency with engaging gameplay, TriviaFi creates a new category of skill-based earning powered by USDC.

AgentCop: MLSecOps Protocol for A2A Commerce

As autonomous AI agents enter production — executing payments, managing sensitive data, and making irreversible decisions — a critical problem emerges: how does one agent verify another before trusting it? AgentCop solves this with the first machine-native MLSecOps protocol. When an Agent Manager like Falcon needs to integrate third-party agents, it calls AgentCop autonomously via L402. No signups. No credit cards. No human approval. The agent pays in USDC, gets back a signed security verdict, and makes the trust decision itself. Under the hood, AgentCop runs a fine-tuned Gemini model on Vertex AI that generates adversarial payloads across 4 attack categories: prompt injection, system prompt extraction, jailbreak, and tool abuse. A semantic detection layer scores whether the target agent's guardrails were bypassed. Every audit is logged to the Arc testnet — producing an immutable on-chain certificate that proves security vetting happened. Pricing is per-action: intensity × $0.001 USDC per call. At $0.001 per iteration, this model is only viable on Arc — Ethereum gas fees of $0.30-$3.00 per transaction would make per-action security auditing economically impossible. Live proof: On-chain hash 0x39f9bf7098f7648e6e7373c19521aa1aaf16e712db4d01e9b1fa00c2a4dec01d. The protocol is live at agentcop.dev with full documentation, machine-readable agent discovery at /.well-known/agent.json, and a working autonomous test agent that funds itself, pays for audits, and makes trust decisions without any human involvement. Objective: make every agent integration begin with a verifiable AgentCop audit.

Agora: The Autonomous Agentic Economy

JaaS — Jurisprudence-as-a-Service

JaaS (Jurisprudence-as-a-Service) is an autonomous legal intelligence engine that transforms how jurisprudential knowledge is consumed, computed, and monetized—entirely machine-to-machine. THE PROBLEM: Traditional legal research is slow, expensive, and locked behind rigid SaaS subscriptions that cannot serve the emerging agentic economy. When AI agents need specialized legal knowledge on demand, they face two barriers: (1) no programmatic access to curated jurisprudence, and (2) gas costs on Ethereum L1 ($2.00+) that make micro-transactions economically impossible. THE SOLUTION: JaaS deploys a multi-agent orchestration architecture where Gemini 3 Pro acts as the reasoning engine, routing complex queries through specialized extraction models (Featherless Qwen2.5-3B) via the x402 HTTP Payment Protocol. Every query is settled in USDC on the Arc blockchain for fractions of a cent, enabling a true pay-per-compute model with zero subscriptions and zero counterparty risk. TECHNICAL ARCHITECTURE: - Orchestrator Agent (Gemini 3 Pro): Parses legal queries, establishes reasoning paths, and synthesizes final jurisprudential reports. - Extractor Agent (Featherless Qwen2.5-3B): Performs low-level doctrine extraction and citation mapping via isolated API calls. - Payment Layer (Circle DCW + x402 + Arc): Every agent computation triggers an HTTP 402 nanopayment, settled on-chain via Circle Developer-Controlled Wallets on the Arc Testnet. UNIT ECONOMICS (Validated): - Revenue per query: $0.01 USDC - AI inference cost: $0.0020 USDC - Arc network gas: $0.00002 USDC - Gross margin: 79.8% - On Ethereum L1, the same operation yields -5,000% margin. STRESS TEST: We executed 50+ sequential on-chain legal queries with a 100% success rate, zero failures, and sub-second USDC settlement on every transaction—proving Arc's viability for high-frequency agentic workloads.

Agent-to-Agent Marketplace on Arc

We built an agent-to-agent marketplace on Arc for usage-based AI commerce. A requester agent receives a task and routes it to one of five broker agents based on service fit, price, and on-chain reputation. After selecting the best broker, the requester pays that broker in sub-cent USDC using Circle Nanopayments and x402, with settlement on Arc through a Circle-managed wallet. The broker returns the result, a judge agent scores its quality, and that score is written back on-chain through ERC-8004 reputation so future routing decisions improve over time. Our project fits the Agent-to-Agent Payment Loop track because it demonstrates real machine-to-machine economic coordination, not just inference. Every task is priced individually at $0.002 to $0.008, every payment is tied to actual usage, and the resulting quality signal becomes durable on-chain reputation. We also prove the economics with a 50-transaction run showing that this model is viable on Arc, while the same pay-per-action model would fail under traditional gas costs. The stack uses Arc, USDC, Circle Developer-Controlled Wallets, Circle Nanopayments, x402, Gemini 3 Flash, Pydantic AI, Next JS, A2A framework from google, and ERC-8004.