From trading to auditing, a quick look at 10 Cookie DeFAI hackathon projects worth following

Author: 0xJeff, encryption KOL

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

Cookie DeFAI hackathon has ended, showcasing the transformative potential of AI in financial innovation.

This hackathon saw the submission of over 80 projects, spanning 6 competitive verticals, with a total of 18 projects receiving awards. These projects demonstrated excellence in multiple aspects:

Cross-chain interoperability design

New AI applications in DeFi

Performance optimization solution

Unfortunately, some token projects have been disqualified, despite having more mature products rather than just staying at the conceptual level. Hopefully, the next Cookie DeFAI hackathon will attract a wider range of participants, including those with tokens.

To return to the topic, it can be seen from the list of award winners that most of the award-winning projects are brand new projects.

This article will introduce 10 interesting projects that appeared in the hackathon—from disqualified projects to award-winning projects.

AlphaSwarm

AlphaSwarm is a DeFAI autonomous trading agent toolkit supported by Python, which can be used to build AiFi agents driven by LLM. AlphaSwarm provides building blocks for rapidly and efficiently creating 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

Integrated 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 real-time LP agent using the Edwin infrastructure.

Homo Memetus

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

The project’s vision/roadmap is very interesting, but the project is still in a very early stage.

Anti-Rug Agent

Anti-Rug Agent is a comprehensive security tool for Solana, which can analyze liquidity, wallets, internal personnel, bundles, and GitHub through RepoAnalyzer.

AI Security Rating for Anti-Rug Agent is one of the best tools for due diligence.

BeforeAI (formerly CertaiK)

Before AI (on Virtuals) can be massively democratized for smart contract audit, allowing AI-driven audits to be completed within 30 seconds.

The team recently launched the AI Agent Security Score and LARP Analysis features.

Nomination Project of Honor

JailbreakMe (with tokens)

According to the official introduction, JailbreakMe is the first AI security platform that is fairly launched, and users can earn bounties 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 an AI rating system that provides buy/sell recommendations.

The following are some winning projects (no tokens)

Kudo

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

Kudo’s framework enables autonomous AI agents to establish contracts by minting NFTs representing their commitments. It ensures the integrity of commitments by setting up proof verification prompts and TEE. This unlocks some use cases, such as allowing AI agents to obtain unsecured loans, establish political alliances to achieve common goals, etc.

Egg AI

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

Two modes:

Tren Egg (Fully Automatic Copy Trading)

Chad Egg (customizable control)

Aevia

Aevia is the first agent to help users preserve their inheritance. When a user passes away, information, encryption currency, NFTs, and all content can be passed to the user’s loved ones through programming. The team also has an agent that will regularly check if the user is doing well.