Plugin Builder: Supercharging AI Agents Until today, Loomlay's AI agent workflows have been constrained by a fundamental limitation: agents could only interact with our pre-built plugins. Today, we’re removing this constraint by launching the alpha version of Plugin Builder. It’s here to transform our closed ecosystem into an extensible no-code framework for AI agents. The Technical Foundation Loomlay plugins are standardized API wrappers that enable bidirectional communication between autonomous agents and external services. Each plugin exposes a declarative interface that allows agents to understand and interact with service through natural language processing. This abstraction layer enables agents to execute complex workflows while following natural language instructions. In simple terms: AI agents can execute tasks simply by following plain English instructions, such as telling them to "order my favorite pizza". Opening the Integration Layer The Plugin Builder introduces a composable architecture where developers can create custom data transformers and action handlers. This allows for: • Direct API integration with any service endpoint • Custom data processing pipelines for specialized use cases • Agent-to-agent interfaces enabling collaborative task execution • Event-driven automation triggers based on external conditions Expanding Agent Capabilities By transitioning to an open plugin architecture, we're enabling several key technical advancements: • Agents can now orchestrate multi-step workflows across previously incompatible platforms • Real-time data streams can be processed through custom transformation logic • Complex conditional execution patterns can be implemented through plugin-defined triggers Real-World Applications The Plugin Builder unlocks powerful combinations of existing and custom integrations. Here are some examples: • A research agent combining Bloomberg API data with Zerion's on-chain analytics and DefiLlama TVL tracking to spot institutional money flows • A gaming analytics agent tracking Steam player counts and Twitch viewership, correlated with token price movements through our market data plugins • A news trading agent combining Reuters API with technical analysis from TradingView and executing through Brian's DeFi integrations • An e-commerce agent tracking Amazon prices, correlating with Google Trends data, and managing treasury through our DeFi plugins • A social media agent monitoring TikTok trends, analyzing Instagram engagement, and auto-adjusting marketing budgets via on-chain transactions • A travel industry agent combining flight prices from Kayak with hotel availability and executing payments through crypto payment gateways These examples demonstrate how Plugin Builder enables seamless integration between Loomlay existing capabilities and any external API, creating agents that bridge multiple industries and data sources. Monetization & Cross-Agent Integration (Coming Soon) Currently, plugins can only be published privately, letting developers control which agents can access them. Soon we'll launch public publishing with monetization, enabling developers to earn revenue from their plugins and AI agent terminals. This will also open up integration possibilities with external AI agents built on frameworks like Eliza, allowing them to interact directly with Loomlay agents. All monetization will be handled through our LAY token system for plugin subscriptions. Technical Roadmap Our development pipeline for Plugin Builder focuses on three core capabilities: 1. Development Tooling: We're building comprehensive debugging tools, version control systems, and cURL imports to streamline the development workflow and ensure reliable plugin creation 2. Marketplace & Monetization: The introduction of public publishing alongside LAY token integration will create a sustainable economy for developers to monetize their innovations 3. Agent Coordination Layer: Implementation of a multi-agent coordination protocol will enable seamless communication and task execution between different AI agents, establishing a foundation for complex automated workflows Conclusion This release transforms Loomlay from a closed system into an open framework where developers can create custom integrations bridging Web2, Web3 and AI. At its core, AI development is driven by human creativity - come build with us 🪄

@S4mmyEth @nansen_research @ai16zdao @nansen_ai 👋

@milesdeutscher Lay is the way 🪄

Join our Buildooors club and let's build some cool stuff together 🪄 Please spread it by retweeting! Appreciate! 🙏

@EnsoBuild 🫡 it was our pleasure!

@0xKevlar 🤝

@sebaudet26 Hey Seb! Our agents can already do that via Telegram (and Web Widget next week), but they need more tools 🛠️ Let's connect and find synergies!

@petarq @0xc06 let's connect and discuss all things defai ;)

@0xc06 thank you fren! 🫡

Live in 10minutes! Tune in see some real DeFAI magic 🪄

DeFAI for everyone 🏗️

AI Messenger: Giving Voice to Autonomous Agents The future of AI isn't just about making agents smarter - it's about making them truly autonomous. Today, we're taking a major step toward this future with AI Messenger, a breakthrough that fundamentally changes how AI agents operate, communicate, and create value. The Innovation We've developed a new way for AI agents to communicate. At its core is the 'incoming_message' workflow trigger - a system that lets any platform or user interact directly with Loomlay agents through a messaging endpoint. Direct Interaction Imagine having an AI assistant you can chat with anytime, through any platform - Telegram, your website, or custom interface. Ask "What's happening with $ETH today?" and your agent analyzes market data, checks trading volumes, and gives you a comprehensive update. Your agent maintains context, understanding exactly what you need. Event-Driven Intelligence The power of AI Messenger goes beyond direct communication: ▪️Trading agent executes when whale wallet movements exceed threshold ▪️Research agent alerts when new protocol documentation drops ▪️Analytics agent triggers when volume patterns match historical pumps ▪️Portfolio agent re-balances, when asset allocation hits specified limits This is true automation - agents that act precisely when needed. A New Era of Collaboration We're creating an ecosystem where agents work together seamlessly: ▪️Research agents feed insights to trading agents ▪️analytics agents alert management agents ▪️support agents tap into knowledge agents This isn't just automation - it's an intelligent network where each agent enhances the capabilities of others. B2B Solution Imagine a DEX, where users can ask about liquidity pools, trading pairs, or market trends through a simple chat interface - and get answers from an agent that knows your protocol inside out. Or a lending platform where users chat with an agent that understands their positions and can provide real-time advice. Implementation is seamless - we handle the agent creation and widgets setup,our partners provide the value to their users. The Future of AI Agents This update represents a fundamental shift in how AI agents operate. We're moving from isolated, scheduled tasks to an interconnected ecosystem of responsive, collaborative agents. This is our vision of truly autonomous AI - intelligent systems that communicate, collaborate, and respond to real needs in real-time. Telegram integration is available right now. Below is a sneak peak of what's coming next week 🪄 Because $LAY is the way!

Join us tomorrow for something special 🪄 A live session with Enso team! We will discuss all things DeFAI, as well as demonstrate how our agents execute on-chain actions through @EnsoBuild on @base in real-time. We will also show you our latest alpha - AI Messenger in action! 🔗 📅 Wednesday, Feb 12 @ 14:00 UTC Speakers: @0xdarius Founder, Loomlay @connor_enso Founder, Enso @lindyhan BD Lead, Enso Mark your calendars, it's gonna be fun!

@EnsoBuild @base 🤝🪄

If you are a buildoor or want to become one - join now! Let's do some magic together 🪄

Tutorial No.4: Build a Smart Money Tracking Agent 🎥 Another Monday, another chance to level up your agent building skills! This time we focused on @zerion plugin to analyze high volume traders. Plugins used: Zerion, Birdeye, Telegram, Dexscreener AI Model used: ChatGPT 4o Enjoy! If you still have questions after watching this tutorial, join our Telegrams and ask us any questions you might have: $LAY is the way 🪄

New Monday, new week for building 🏗️ gm everyone!

RT @vasilich_nick: Two AI agents on top of @loomlayai and robust growth strategy make waves live nowadays 6k+ are watching

Time to show you some real magic 🪄In the video below Darius is showcasing our latest updates using our flagship agent @Quantel_ai $QTL. We've just added: ▪️@CieloFinance plugin ▪️Perplexity plugin ▪️and our new innovation - communication solution for AI Agents (sneak peak) You will now be able to chat with your agent like it's your personal assistant via Telegram! ▪️Need market insights? ▪️Portfolio check? ▪️Any token analysis? ▪️Trading ideas? Just ask and get real-time replies! Also, join our Telegram where you can talk to Quantel and experience it right now: Looking forward to your feedback! 🙏