From transactions to audits, here are 10 noteworthy Cookie DeFAI hackathon projects

Author: 0xJeff , Crypto KOL

Compiled by: Felix, PANews (This article has been edited)

The Cookie DeFAI hackathon has concluded, showcasing the transformative potential of AI in financial innovation. More than 80 projects were submitted to the hackathon, covering 6 competitive verticals, and a total of 18 projects were awarded. These projects demonstrated excellence in many aspects:

Cross-chain interoperability design
New AI applications in DeFi
Performance optimization solutions

Unfortunately, projects with tokens were disqualified, even though they had more mature products than just concepts. Hopefully, the next Cookie DeFAI hackathon will allow for a wider range of participants, including those with tokens.

Back to the topic, as can be seen from the list of winners, most of the winning projects are brand new projects. This article will introduce 10 interesting projects that appeared in the hackathon - starting with the disqualified projects and then introducing the winning projects.

AlphaSwarm

AlphaSwarm is a Python-powered DeFAI autonomous trading agent toolkit that can be used to build LLM-powered AiFi agents. AlphaSwarm provides building blocks to quickly and efficiently create complex, autonomous financial agents. With AlphaSwarm, users can:

Get data from multiple sources
Develop AiFi Agents using modular strategies and complex planning driven by LLM
Integration with DEX
Interact with users through multiple channels

Edwin

Edwin is a TypeScript-driven infrastructure for AI agents to interact with Defi protocols, supporting the creation of DeFAI agents (LP, lending, cross-chain interaction).

aiymx is the first live LP broker to use Edwin infrastructure.

Homo Memetus

Homo Memetus is a DeFAI ecosystem that tokenizes agent trading strategies and lets them compete with each other (or humans) to identify profitable strategies (through natural selection).

The vision/roadmap for the project is quite interesting, but the project is still in very early stages.

Anti-Rug Agent

Anti-Rug Agent is a comprehensive security tool for Solana that analyzes liquidity, wallets, insiders, bundles, and GitHub through RepoAnalyzer.

Anti-Rug Agent’s AI Safety Score is one of the best tools for conducting due diligence.

BevorAI (formerly CertaiK)

BevorAI (on Virtuals) democratizes smart contract auditing at scale, allowing AI-driven audits to be completed in under 30 seconds.

The team recently launched the latest features of AI Agent Safety Scoring and LARP Analysis.

Honorable Mentions

JailbreakMe (with tokens)

According to the official introduction, JailbreakMe is the first AI security platform launched fairly, where users can get rewards by cracking AI agents. Jailbreak previously won third place in the Solana AI Hackathon.

AgentXYZ

AgentXYZ is a trading terminal with social and on-chain insights. Recently launched AI scoring system to provide buy/sell recommendations.

The following are some of the winning projects (without tokens):

Kudo

Kudo introduces a contract framework that enables complex financial use cases between agents (such as unsecured loans, employment agreements, etc.) through contract NFTs (cNFTs).

Kudo's framework enables self-sovereign AI agents to enter into contracts by minting NFTs that represent their commitments. The integrity of the commitments is ensured by setting up prompt verification and TEE proofs. This unlocks use cases such as allowing AI agents to obtain uncollateralized loans, forming political alliances to achieve common goals, etc.

Egg AI

Egg AI is a copy trading agent with AI research, market analysis and execution capabilities. It combines the SocialFi layer + AI DYOR and execution layer.

Two modes:

Tren Egg (Automatic Copy Trading)
Chad Egg (customizable controls)

Aevia

Aevia is the first agent that helps users preserve their legacy. When a user passes away, information, cryptocurrencies, NFTs, and everything can be programmatically passed to the user's loved ones. The team also has an agent that regularly checks in on users to see if they are okay.