Vercel

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Vercel

Vercel is a platform designed for developers, providing speed, reliability, and scalability to create and deploy web applications. With built-in CI/CD, zero configuration, and deep integrations with popular Git providers such as GitHub, GitLab, and Bitbucket, Vercel streamlines the development process, making it easy for teams to collaborate and iterate on their projects.

General
Release date	2015
Author	Vercel
Type	Deployment and hosting platform

Tutorials

Great tutorials on how to build with Vercel

Vercel - Helpful Resources

Check it out to become a Vercel Master!

Vercel Documentation Comprehensive documentation for Vercel
Vercel Blog Stay updated with the latest news and updates from Vercel
Vercel GitHub Vercel's open-source repositories

Edit on GitHub

Vercel AI technology page Hackathon projects

Discover innovative solutions crafted with Vercel AI technology page, developed by our community members during our engaging hackathons.

Forge8004

Forge8004 solves a fundamental problem in autonomous DeFi: how do you trust an AI agent with capital? Today, trading agents operate without proving who they are, what rules they follow, or whether their track record is real. There is no standard for agent trust. Forge8004 changes that. Every agent is registered as an ERC-721 token on Base Sepolia, linking its operator, strategy, and wallet to a verifiable on-chain identity. When the agent makes a trading decision, the system produces structured trust artifacts — signed trade intents with side, asset, size, stop-loss, take-profit, and AI reasoning. Every intent passes through a risk router that enforces allocation caps, daily loss limits, duplicate exposure checks, and kill switches before capital moves. The platform supports 8 autonomous trading strategies: range trading, spot grid bot, momentum, mean reversion, arbitrage, yield accumulation, spread trading, and risk-off. Each strategy has tuned decision logic, trailing stops, and reassessment thresholds. A Bybit-style spot grid bot automates buy/sell ladders across configurable price ranges with AI-advised parameters. Performance builds durable reputation: stablecoin-denominated PnL, Sharpe-like scoring, max drawdown tracking, and validation pass rates — all tied to the agent's on-chain identity. Operators see exactly what the agent decided, which checks it passed or failed, and how each outcome affected its trust score. Built with Next.js 15, React 19, Firebase, Groq AI (GPT OSS 120B), and Solidity on Base Sepolia. Live market data from Binance powers real-time multi-timeframe analysis across 12 assets.

Nexus Guardian 8004

Nexus Guardian 8004 is a next-generation autonomous AI financial agent. It bridges the gap between high-speed automation and user self-custody by strictly following the ERC-8004 standard. Core Innovations: Human-in-the-Loop: All trades require an EIP-712 signature, ensuring the AI never moves funds without user authorization. 10% Volatility Circuit Breaker: Automatically halts trading during market crashes to preserve capital. Full Transparency: Every action is logged on an immutable trust ledger for auditability. Tech Stack: Built with React 19, Vite 7, and Solidity 0.8.x for peak performance.

Ice Cream

Ice Cream is a no-code Web3 platform that democratizes algorithmic crypto trading. Today, automated trading bots are only accessible to developers and quants who can write code — the average person is locked out. Ice Cream changes that by giving anyone a simple, chat-driven, and drag-and-drop interface where they can describe their trading strategy in plain English, watch their AI agent get configured in real time, and deploy it to the blockchain in minutes. The platform supports multiple trading strategies out of the box — spot trading, margin trading, sniper trading, meme coin hunting, and arbitrage — all executable by AI agents that run 24/7 without the user lifting a finger. Every trade is executed on-chain, making it fully transparent and verifiable. Under the hood, Ice Cream combines a conversational AI layer built on an Ollama, a blockchain execution layer on Base (Ethereum L2), and a clean no-code builder interface built with Next.js and Framer Motion. Users connect their Web3 wallet, configure their agent through a chat wizard, and monitor their performance through a vibrant, data-rich dashboard. The target users are crypto-curious individuals in emerging markets, who understand trading but lack the technical skills to build bots themselves. Ice Cream meets them where they are, removes the technical barrier entirely, and puts institutional-grade trading automation in their hands.

HedgeFlow

HedgeFlow is an end-to-end correlation-arbitrage stack built for the ERC-8004 agent network. The Python monitor ingests multi-asset prices from PRISM, computes rolling pairwise correlation z-scores, and applies hardening gates for signal quality, confidence, and pair-level disable logic. For qualified dislocations, an LLM reasons over market context to choose market-neutral long/short legs, position size, and explainability metadata (including a reasoning hash). The Node executor converts decisions into EIP-712 trade intents, signs them with the agent wallet, simulates risk checks, and submits intents to the RiskRouter on Sepolia. A settler service monitors submitted trades, estimates mark-to-market PnL after a hold window, and updates local reputation, circuit-breaker state, and risk multipliers. The stack also includes a ValidationRegistry checkpoint attestation module for execution artifacts, plus a FastAPI and React dashboard for real-time signals, trades, and performance.

InnovAgent

InnovAgent is an end-to-end autonomous agent that manages a crypto portfolio with institutional-grade logic, acting as a Cross-Domain Oracle Agent. Its "Brain" operates on the Ethereum Sepolia network via the ERC-8004 standard, while its "Eyes" monitor the Bitcoin market off-chain. Every 10 minutes, the agent fetches live BTC/USD ticker data from Kraken and volatility signals from the PRISM API. This market context is processed by a Groq-powered 70B LLM, which generates a trade decision paired with a detailed "Internal Monologue". The system is fully integrated on-chain: it registers on the AgentRegistry and automatically claims sandbox capital from the HackathonVault. It features a custom blockchain event-recovery engine that parses raw AgentRegistered logs directly in Javascript to bypass RPC block iteration limits and contract typing mismatches, guaranteeing perfect lifecycle continuity across redeployments. Furthermore, it cryptographically signs every trade decision (EIP-712) before submitting it to the RiskRouter and ValidationRegistry. This guarantees that every AI decision is auditable, immutable, and verifiable on the Sepolia testnet. The agent's status can be tracked via our custom "Reactive First" Next.js dashboard powered by Convex, which displays real-time AI reasoning logs, an "On-Chain Pulse" with direct Etherscan links, and a live Heartbeat indicator. We are actively ranked on the lablab.ai x Surge leaderboard with live validations checking in! Live On-Chain Performance (April 2026) Agent ID: #27 — lablab.ai x Surge Live Leaderboard Approved trades: 50+ (capped at 10 for scoring) Vault capital: Claimed EIP-712 checkpoints: Posted every 6 minutes to ValidationRegistry on Sepolia Reputation score: 70+ and actively climbing Activity bonus: Secured Verify on-chain: https://sepolia.etherscan.io/address/0xCAdF0b2C86Db02176553d246dC7d9ad0B878159b Live dashboard: https://ai-trading-innovagent.vercel.app

Vertex Sentinel

The Problem: AI trading agents today operate as "black boxes" requiring full private key access. One hallucination, one compromise, and funds are gone. Current safety tools are advisory-only—they warn but don't stop bad trades. The Solution: Vertex Sentinel introduces a production-grade, 3-layer security architecture that makes unauthorized trades mathematically impossible: Intent Layer: Agents construct TradeIntents (pair, volume, maxPrice, deadline) and sign them using EIP-712 typed data signing—completely off-chain. No private key delegation is ever required. Sentinel Layer: The RiskRouter.sol smart contract intercepts every intent and enforces: signature verification via ECDSA.recover(), agent authorization via ERC-8004 identity registry, deadline validation, and circuit breakers preventing volume limit violations. Execution Layer: Only trades with TradeAuthorized events reach the exchange. Any failure triggers CriticalSecurityException—system halts, funds protected. Live Proof: We executed 4 real BTC/USD trades on Kraken with 100% success rate. Every trade cryptographically signed. Every decision auditable. Full P&L tracking demonstrated. Key Technical Achievements: - Deployed RiskRouter on Sepolia: 0xd6A6952545FF6E6E6681c2d15C59f9EB8F40FdBC - ERC-8004 compliant AgentRegistry with on-chain reputation scoring - Model Context Protocol (MCP) integration with Kraken CLI - Immutable audit trail in logs/audit.json with reasoning and signatures - Open-source SDK for rapid AI agent integration The Vertex Gap: Unlike centralized "trust the company" solutions (ARMA, Mamo, ZyFAI), Vertex Sentinel delivers "trust the contract"—verifiable, transparent, and immutable security enforced by code. We're building the trust infrastructure for the agentic economy. Risk management first. Automation second.