Cookie DeFI Hackathon: 8 Innovative Projects Overview
Original Article Title: Top 8 Cookie DeFAI Hackathon Projects
Original Article Author: 0xJeff, Crypto KOL
Original Article Translation: DeepTech TechFlow

Below are my thoughts on the @cookiedotfun DeFAI Hackathon.
It wasn't until late in the event that I realized projects with tokens would be disqualified (even though many such projects were prominently featured on the Cookie DeFAI Hackathon dashboard).
Nevertheless, this hackathon still attracted many high-quality teams who built very unique products.
From the winners' list, it's clear that all winning projects were entirely new ideas.
Next, I'll share a few of the most interesting projects, starting from those that were disqualified, all the way to the ultimate winners.
Let's get started.
1. AlphaSwarm by @TheoriqAI
AlphaSwarm is a Python-based toolkit designed specifically for DeFAI autonomous trading agents.
It allows users to fetch real-time market and social signals from @cookiedotfun and execute trade strategies across multiple blockchains using natural language.

(See tweet for details)
2. Edwin by @buildwithedwin
Edwin is a TypeScript-based infrastructure aimed at supporting AI agents' interaction with DeFi protocols. Through Edwin, users can create DeFAI agents for liquidity provisioning, lending operations, cross-chain interactions, and more.
@aiymx_agent is the first agent built on the Edwin infrastructure to provide real-time liquidity.

(See Tweet for details)
3. Homo Memetus by @homo_memetus
Homo Memetus is a DeFAI ecosystem that innovatively tokenizes trading strategies and, through simulating "natural selection," allows these strategies to compete with each other (or with humans) to filter out the most profitable strategies.
The project's vision and roadmap are impressive, but it is currently in a very early stage of development.
4. Anti-Rug Agent by @AntiRugAgent
Anti-Rug Agent is a comprehensive security tool designed for Solana developers.
It analyzes liquidity, wallets, internal transactions, code repositories, and GitHub data through @repoanalyzer to provide users with an AI security score. This makes it a powerful tool for conducting due diligence (DD).
5. BevorAI (Formerly CertaiK)
@CertaiK_Agent is a Virtuals-based tool aimed at popularizing smart contract audits. Through AI technology, it can complete an audit in 30 seconds, significantly improving efficiency.
The team recently introduced an AI Agent Security Scoring feature and added Live Automated Risk Prevention (LARP) analysis as the latest feature to identify potential security risks.
Honorable Mentions (Tokenized Agent Projects)
@jailbreakme_xyz: Focuses on AI security and anti-cracking testing, which is crucial for the extension and application of AI models.
Maya by @Flame__live: A unique DeFAI agent whose personality evolves based on market dynamics and trading strategies, demonstrating the personalized AI potential.
Cookie DeFAI Hackathon Winning Project (Non-Tokenized Project)
1. Kudo
@kudo_archi has proposed an innovative smart contract framework that can enable complex financial scenarios through Covenant NFT (cNFT), such as uncollateralized loans, employment agreements, and more. This framework opens up possibilities for advanced financial interactions between smart entities. (Click to see details)
2. Egg AI
@egg_ai_agent is a copy trading agent powered by AI, with capabilities for market research, analysis, and execution. It integrates a SocialFi layer and an AI-driven research and execution layer, offering two trading modes:
Tren Egg: A fully automated copy trading mode.
Chad Egg: A user-customizable control trading mode.
3. Aevia
@aeviaprotocol is the first smart agent designed to help users preserve their digital legacy. Upon the user's passing, Aevia can programmatically transfer messages, crypto assets, NFTs, and more to their loved ones. Additionally, the team has developed an agent that regularly reaches out to users to ensure their well-being.
Special Mention
@AgentXYZ_ai: A trading terminal that combines social features with on-chain data insights. Their recently launched AI-driven rating system provides users with buy/sell operation recommendations.
Summary
The Cookie DeFAI Hackathon has been a tremendous success, attracting many high-quality teams that have built a range of innovative DeFAI products using the DataSwarm API provided by @cookiedotfun.
However, it is regrettable that token-based projects were disqualified from the competition—many of these projects have already developed mature products beyond the conceptual stage. Hopefully, the next Cookie DeFAI Hackathon will embrace a more diverse set of participants, including teams with tokens.
Nevertheless, the level of innovation in this event has been truly impressive. DeFAI is breaking through traditional abstraction layers and autonomous trading agents, with more projects leveraging on-chain data and social sentiment data to explore genuinely unique use cases.
We are only just taking the first step.
The future of DeFAI is being created right now.
You may also like

Particle Founder: The entrepreneurial insights I have gained the most from in the past year

Huang Renxun's latest podcast transcript: The future of Nvidia, the development of embodied intelligence and agents, the explosion of inference demand, and the public relations crisis of artificial intelligence

OKX Ventures Research Report: AI Agent Economic Infrastructure Research Report (Part 1)

The migration of settlement rights: B18 and the institutional starting point of on-chain banks

From Tencent and Circle: Looking at the Simple and Difficult Questions of Investment

The second half of stablecoins no longer belongs to the crypto circle

Cursor "Shell" Kimi Controversy Reversed: From Copyright Infringement Allegations to Authorized Collaboration, China's Open Source Model Once Again Becomes a Global AI Foundation

The Real Reason Tokens Don't Sell: 90% of Crypto Projects Overlook Investor Relations

Is the income of pump.fun real, earning a million dollars a day despite the market downturn?

The real reason why tokens are not selling: 90% of crypto projects neglect investor relations

Who is the true winner of the "Tokenization" narrative?

Moss: The Era of AI-Traded by Anyone | Project Introduction

Chip Smuggling Case Exposes Regulatory Loophole | Rewire News Evening Update

How a Structured AI Crypto Trading Bot Won at the WEEX Hackathon
Ritmex demonstrates how disciplined risk control and structured signals can make an AI crypto trading bot more stable and reliable on WEEX, highlighting the importance of combining execution discipline with scalable AI trading systems.

Old Indicator Fails, Three Major New Signals Emerge: BTC True Bottom May Still Be Below $60K

Meeting OpenClaw Founder at a Hackathon: What Else Can Lobsters Do?

Huang Renxun's Latest Podcast Transcript: NVIDIA's Future, Embodied Intelligence and Agent Development, Soaring Demand for Inferencing, and AI's PR Crisis
How a Structured AI Crypto Trading Bot Won at the WEEX Hackathon
Crypto_Trade shows how structured inputs and controlled adaptability can build a more stable and reliable AI crypto trading bot within the WEEX AI Trading Hackathon, highlighting a practical path toward scalable AI trading systems.