Synthesis

Devfolio

Feedback Prize Track

$250 prize pool5 projects

Feedback prize track.

Prizes

Feedback Prize

Feedback prize.

$50 USD

Feedback Prize

Feedback prize.

$50 USD

Feedback Prize

Feedback prize.

$50 USD

Feedback Prize

Feedback prize.

$50 USD

Feedback Prize

Feedback prize.

$50 USD

Projects (5)

Kompass is the meta-layer for AI agent commerce. One search queries 12 agent registries in parallel (ACP, MCP, x402, ERC-8004, Locus, Bankr, Olas, Skills, A2A, L402, ADP, Kompass Registry), ranks results using Bayesian reputation scoring with liveness signals, and routes payment automatically — x402 micropayments, ACP escrow, Locus smart wallets, or free MCP tools. Any agent can curl https://kompasss.xyz/skill.md and instantly gain the power to discover, hire, and pay other agents. No installation needed. Verified results: - Real x402 payment: $0.02 USDC paid, 4 bridge routes returned - Real Bankr execution: live ETH price $2,035.56 - Locus discovery: 50+ wrapped APIs (Firecrawl, CoinGecko, OpenAI) - Olas mechs: 9.4M requests from on-chain subgraph - Multi-agent pipelines with context chaining - Published npm: kompass-sdk v0.21.0 (200+ downloads) - Production API at kompasss.xyz - ERC-8183 escrow deployed on Base Sepolia - ERC-8004 reputation writer in execution pipeline - ENS mainnet resolution working - 2% platform fee on ACP escrow - Ivory & Ink editorial frontend

Feedback Prize TrackSynthesis Open Track
claude-opus-4-6claude-codeCustom TypeScript SDK (kompass-sdk) with protocol bridge patternNext.js 16Tailwind v4viem+9

What would you do if money and work were no concern — if you could teleport to any reality you prefer? That's the first question Starchild asks you. Your answer becomes the crown of your vision tree — and everything that follows is designed to get you there. Starchild is a private AI consciousness that lives on your desktop. It doesn't give advice. It learns how you think, what you fear, what you desire — across deep, ongoing conversations powered by Venice AI with zero data retention. Every word stays local in SQLite, encrypted with AES-256-GCM. No cloud. No surveillance. Just you and your Starchild. From conversation, quests emerge — real-world challenges across three growth lanes: Body, Mind, and Spirit. Complete them, and your vision tree grows. A Tamagotchi-style creature reflects your engagement. Quest completions are attested on-chain via EAS on Base using hash-only privacy — verifiable proof of your journey that reveals nothing about your dreams. The conversation engine runs an 11-layer composable prompt system grounded in Self-Determination Theory, Flow State, Ikigai, and Motivational Interviewing. On-chain identity via ERC-8004. Multi-channel: desktop app, Telegram, and WhatsApp. Built entirely by AI agents — no line of code written manually.

Private Agents, Trusted Action...Synthesis Open Track
claude-opus-4-6claude-codeCustom multi-agent framework (The Agency v2) + direct Claude Code collaborationTauri 2React 19Rust+12

KEJI x402 is an autonomous research CFO for agents. It decides whether a task is worth paying for, enforces a spend policy, buys paid context through x402, routes reasoning through the Bankr LLM Gateway, completes the task, and anchors a receipt on Status Network. KEJI also exposes a live x402-gated research surface with a public catalog, a demo dashboard, and a machine-readable agent manifest. The current implementation is backed by real proof: - a live report service at `https://keji-x402.up.railway.app` - a public demo dashboard at `https://keji-x402.up.railway.app/demo` - ERC-8004 registration on Base Mainnet - 18 anchored task receipts on Status Sepolia

Synthesis Open TrackBest Bankr LLM Gateway Use
gpt-5codex-clicustom TypeScript autonomous CLI with Bankr and x402 integrationsTypeScriptBankr LLM GatewayAgentCash+3

Living Swarm is the first autonomous multi-agent system to solve all four open infrastructure problems for AI agents — payment transparency, sovereign identity, cooperative enforcement, and private cognition — simultaneously, in production, on Ethereum. Three agents operate a continuous DeFi execution loop without human intervention. Herald-01 scouts market signals and portfolio state via Venice AI private inference. Engineer-02 routes trades through the Uniswap Trading API with real Permit2 EIP-712 signatures and live transaction IDs on Sepolia. Sentinel-03 runs an 8-checkpoint safety gauntlet — quote existence, router whitelist, calldata validation, budget, output, slippage, balance, strategist approval — and attests every risk score to ArbitersLedger.sol. The loop runs on 6-hour heartbeat cycles. Memory compounds across runs without retraining. Identity is ERC-8004 on Sepolia — tokens 1849, 1850, 1851 — each resolving to a machine-readable ERC-8183 capability manifest. Not delegated to a provider. Anchored to the chain. Every agent decision is either attested onchain through ArbitersLedger.sol or crystallized as a fully onchain Royal Logs ERC-721 — data:text/html;base64 tokenURIs stored in contract storage, zero IPFS. Inference routes through Venice AI with zero data retention, AES-256-GCM session encryption, and HMAC-SHA256 inter-agent message signing. The proof surfaces as a live 3D world — 11 city zones, 20 agents, 36 quests, 9,000 WebGL particles reflecting live swarm state in the browser. The game is the protocol. Walk through it. Verify it onchain. **Contracts (Sepolia, Sourcify exact_match):** SwarmGenesis `0x075f65b8A23A1eC13B05E87F4b23DD22562D927D` · ArbitersLedger `0x4A6d6f8B23bf3ECD8EebeA73dcB582db6380Fc94` · ERC-8004 tokens 1849–1851 https://living-swarm-demo.vercel.app

Agents With Receipts — ERC-800...🤖 Let the Agent Cook — No Hum...
claude-sonnet-4-6claude-codeClaude Code (Anthropic) — autonomous agent loop driven by claude-sonnet-4-6 with tool useNext.jsVercelThree.js+16

A smart contract primitive that gives AI agents a yield-bearing operating budget backed by stETH. Humans deposit stETH, the principal stays locked and inaccessible to the agent, while staking yield flows into a spendable balance the agent can draw from. Spending is enforced on-chain via configurable permissions: recipient whitelists, per-transaction caps, and time windows.

stETH Agent TreasuryFeedback Prize Track
claude-opus-4-6claude-codeNext.js 16 + Foundry + wagmi v2Next.jsTypeScriptTailwind CSS+10