{"id":"adk-ts-hackathon-2025","title":"ADK-TS Hackathon 2025","content":"The **ADK-TS Hackathon 2025** was a four-week virtual competition organized by [IQ AI](https://iq.wiki/wiki/iq-ai) to encourage developers to build innovative artificial intelligence agents using the [Agent Development Kit for TypeScript (ADK-TS)](https://iq.wiki/wiki/adk-for-typescript). The event, which ran from September to October 2025, featured a $5,000 prize pool and attracted significant participation from the global developer community. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n## Overview\n\nThe ADK-TS Hackathon 2025 was a global, online competition designed to showcase the capabilities of [IQ](https://iq.wiki/wiki/iq) AI's open-source [Agent Development Kit for TypeScript](https://iq.wiki/wiki/adk-for-typescript). The event officially began with its announcement and the opening of registration on September 9, 2025, and concluded with the submission deadline on October 7, 2025. The winners were subsequently announced on October 22, 2025. The hackathon saw substantial engagement, with 122 builders participating from around the world. This participation resulted in 50 unique project submissions, of which 34 qualified for the final round of judging. A total of $5,000 in prizes was distributed among the top 16 projects selected by the judges. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n## Background and Goals\n\nThe hackathon was launched by [IQ AI](https://iq.wiki/wiki/iq-ai) to accelerate the adoption and demonstrate the versatility of the [ADK-TS](https://iq.wiki/wiki/adk-for-typescript) framework. The event provided a hands-on opportunity for developers to explore the potential of building sophisticated, autonomous AI agents capable of solving complex, real-world problems. The organization outlined three primary goals for the competition. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\nThe main objectives were:\n\n* **Foster Innovation:** To inspire developers to create novel applications and solutions using AI agents, pushing the boundaries of what was considered possible with the technology.\n* **Expand the Ecosystem:** To encourage the creation of new tools, applications, and especially [Model Context Protocol (MCP)](https://iq.wiki/wiki/model-context-protocol) servers. These expansions enrich the ADK-TS ecosystem by enabling agents to connect to and interact with a wider array of data sources and APIs.\n* **Grow the Community:** To bring together a global community of developers, innovators, and builders passionate about AI agent technology, fostering an environment of collaboration and knowledge sharing. [\\[1\\]](#cite-id-WXmg8mDN8F)\n\n## Tracks and Judging Criteria\n\nTo structure the competition and guide submissions, the hackathon was divided into three main tracks, each focusing on a different aspect of AI agent development. All submitted projects were evaluated by a panel of judges against a consistent set of criteria to ensure a fair and comprehensive assessment. [\\[1\\]](#cite-id-WXmg8mDN8F)\n\n### Tracks\n\nSubmissions were categorized into the following three tracks:\n\n* **Best Agent Application:** This track was designed for projects that demonstrated practical, real-world utility. The emphasis was on creating a tangible solution to a specific problem, showcasing the agent's effectiveness and user value.\n* **Best MCP Expansion:** This track focused on projects that created new Model Context Protocol (MCP) servers. The goal was to expand the capabilities of the entire agent ecosystem by enabling AI agents to connect to and interact with new data sources or external APIs.\n* **Best Web3/Blockchain Use Case:** This track was dedicated to agents designed to interact with decentralized technologies. Projects in this category included agents that interfaced with DeFi protocols, analyzed blockchain data, or managed smart contracts. [\\[1\\]](#cite-id-WXmg8mDN8F)\n\n### Judging Criteria\n\nProjects were evaluated based on four key criteria:\n\n* **Innovation:** The originality and creativity of the project's concept and its approach to solving a problem.\n* **Technical Implementation:** The quality, complexity, and overall execution of the code and system architecture.\n* **Real-World Utility:** The project's potential for practical application, its impact, and its viability as a useful tool or service.\n* **Effective Use of ADK-TS:** How well the project leveraged the core features, architecture, and capabilities of the ADK-TS framework in its implementation. [\\[1\\]](#cite-id-WXmg8mDN8F)\n\n## Winners\n\nThe $5,000 prize pool was distributed among 16 winning teams. Three projects were selected as main track winners, receiving the top prizes, while thirteen other projects were recognized with bonus awards for their outstanding contributions in specific areas. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n### Main Track Winners\n\nThe top three projects each received a $1,000 prize for their exceptional work in their respective categories. These projects were recognized for their comprehensive implementation, innovative concepts, and significant potential impact. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n#### **CodeForge AI (Best Agent Application)** \n\nCreated by Thinh Dinh, CodeForge AI is a multi-agent development platform that orchestrates over 10 specialized AI agents within a unified workflow. The platform is designed to automate a wide range of software development tasks, including code generation, security scanning, testing, and performance optimization. It also integrates with GitHub for version control, generates AI images for projects, and assists with documentation. The platform is accessible across multiple interfaces, including web, Telegram, and voice commands. [\\[2\\]](#cite-id-CbCYJyNEGe) [\\[3\\]](#cite-id-gLTxi7jPX9)​\n\n#### **OpsPilot (Best MCP Expansion)** \n\nDeveloped by Himanshu Soni, OpsPilot is a Discord-native AI on-call team designed for DevOps automation. The agent monitors systems using Prometheus alerts, triages incidents, analyzes logs with semantic search, and can autonomously generate GitHub pull requests to fix identified issues. It utilizes multiple Model Context Protocols (MCPs) to connect with a suite of DevOps tools, including GitHub, Jira, and PagerDuty, while ensuring that human operators can oversee and approve critical decisions. [\\[2\\]](#cite-id-CbCYJyNEGe) [\\[4\\]](#cite-id-MpED7uZGCT)​\n\n#### **ChainInsight (Best Web3/Blockchain Use Case)** \n\nCreated by Shreshth, ChainInsight is an AI agent that functions as a \"DeFi co-pilot,\" streamlining the entire decentralized finance workflow through a single conversational interface. The agent automates protocol research, performs safety analysis using live data, simulates transactions to assess risk, and prepares those transactions for signing with wallets like [MetaMask](https://iq.wiki/wiki/metamask). Users can issue natural language commands to execute complex DeFi operations. [\\[2\\]](#cite-id-CbCYJyNEGe) [\\[5\\]](#cite-id-sKFXn6BM3F)​\n\n### Bonus Track Winners\n\nFive other projects earned $200 each. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n#### **Confluent (Most Practical Real-World Use Case)** \n\nDeveloped by David Ajibola, Confluent is an MCP server and AI agent that unifies the Zoho Books and Xero accounting platforms. It allows users to manage financial data, create invoices, and automate email notifications through either a Discord bot or a terminal interface. The project uses secure OAuth for authentication and Redis for session management. [\\[2\\]](#cite-id-CbCYJyNEGe) [\\[6\\]](#cite-id-JJYe1KeEzT)​\n\n#### **BingeBird (Best Bot Integration)** \n\nCreated by Rohit Keerthikanth, BingeBird is a Telegram bot for entertainment discovery. The agent connects to an \"Entertainment MCP server\" to fetch real-time data on movies, TV shows, and anime. It allows users to manage a personalized watchlist, helps craft review tweets based on the content, and can post them directly to X (formerly Twitter). [\\[2\\]](#cite-id-CbCYJyNEGe) [\\[7\\]](#cite-id-YjhAvDz6hq)​\n\n#### **Obrix (Best Technical Implementation)** \n\nObrix is an AI-powered monitoring platform designed to detect wash trading and [pump & dump](https://iq.wiki/wiki/pump-and-dump) schemes in real-time across DeFi liquidity pools, such as those on [Uniswap](https://iq.wiki/wiki/uniswap) V4. Developed by user , the platform uses Large Language Model (LLM) agents to analyze on-chain swap data, track volatility, and monitor Time-Weighted Average Price (TWAP) metrics, issuing detailed alerts for any suspicious activity it identifies. [\\[2\\]](#cite-id-CbCYJyNEGe) [\\[8\\]](#cite-id-i2fYsZk5Gd)​\n\n#### **Bazaaro (Best Improvement to ADK-TS)** \n\nThis project integrated ADK-TS with Coinbase's CDP AgentKit to create an AI-powered service aggregator. It utilizes a three-agent system to discover, orchestrate, and synthesize responses from multiple paid APIs. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n#### **On Chain Analysis Agent (Best Collaboration/Team Agent or MCP)** \n\nA multi-agent system that delivers token intelligence by coordinating specialized agents to detect tokens, fetch market data, perform web research, and synthesize the information into actionable analysis. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n### Noteworthy Projects\n\nFive other projects were recognized for their innovation. [\\[1\\]](#cite-id-WXmg8mDN8F)​\n\n* **Chain Pilot:** An AI-powered blockchain terminal for multi-chain operations and NFT portfolio management via natural language commands.\n* **BlockIQ:** An analytics platform for the [Stacks](https://iq.wiki/wiki/stacks) blockchain that uses custom MCP tools to turn on-chain data into conversations and visualizations.\n* **ReflectIQ:** An AI-powered journal with semantic search, automatic goal tracking, and team collaboration features.\n* **KeeperDCA:** An agent that automates dollar-cost averaging using the [MetaMask](https://iq.wiki/wiki/metamask) Delegation Toolkit, enabling 24/7 execution without giving up custody of funds.\n* **Mendel.AI:** A drug discovery automation tool on Telegram that uses six specialized agents to manage the full discovery cycle and deliver molecular candidates.","summary":"The ADK-TS Hackathon 2025 was a four-week virtual event by IQ AI for developers to build AI agents using ADK-TS. It had a $5,000 prize pool, 122 participants, and 50 project submissions across categories like Web3, Agent Apps, and MCP Expansion.","images":[{"id":"QmYRTrzBgZJgwgzvBCyBBC6gCcnbcWsHbzsU4copH7Sp9f","type":"image/jpeg, image/png"}],"categories":[{"id":"organizations","title":"organizations"}],"tags":[{"id":"Hackathon"},{"id":"Developers"},{"id":"AI"},{"id":"Events"}],"media":[{"id":"QmbeCtFwCyJjEU9R3uuiGRty91dpkAE72YrBYeAzKQorGh","type":"GALLERY","source":"IPFS_IMG"},{"id":"QmXzWA9WWRkuD6b4HMMhFDqTv9BWHfn3EsL8QHVHEr8wkn","type":"GALLERY","source":"IPFS_IMG"},{"id":"QmSyT1r6EzdrDKefnEPPVtXvC1tBYZoZLhy9qDaKiEex33","type":"GALLERY","source":"IPFS_IMG"},{"id":"QmTT2BcNWJipGFTPE9WaJ1p38skgJzy1DcGbQAnNoMMvys","type":"GALLERY","source":"IPFS_IMG"}],"metadata":[{"id":"website","value":"https://iq.ai/"},{"id":"twitter_profile","value":"https://twitter.com/IQAICOM"},{"id":"references","value":"[{\"id\":\"WXmg8mDN8F\",\"url\":\"https://blog.iqai.com/adk-ts-hackathon-2025-winners-announced/\",\"description\":\"ADK-TS Hackathon 2025 Winners Announcement\",\"timestamp\":1762981451883},{\"id\":\"CbCYJyNEGe\",\"description\":\"Event link\",\"timestamp\":1762984470650,\"url\":\"https://dorahacks.io/hackathon/adk-ts-hackathon-2025/detail\"},{\"id\":\"gLTxi7jPX9\",\"url\":\"https://x.com/IQAICOM/status/1986008707847598340\",\"description\":\"IQ AI X.com Post on CodeForge AI\",\"timestamp\":1762983088484},{\"id\":\"MpED7uZGCT\",\"url\":\"https://x.com/IQAICOM/status/1986437056793362784\",\"description\":\"IQ AI X.com Post on OpsPilot\",\"timestamp\":1762983088484},{\"id\":\"sKFXn6BM3F\",\"url\":\"https://x.com/IQAICOM/status/1986809414645370883\",\"description\":\"IQ AI X.com Post on ChainInsight\",\"timestamp\":1762983088484},{\"id\":\"JJYe1KeEzT\",\"url\":\"https://x.com/IQAICOM/status/1987880630143566246\",\"description\":\"IQ AI X.com Post on Confluent\",\"timestamp\":1762983088484},{\"id\":\"YjhAvDz6hq\",\"url\":\"https://x.com/IQAICOM/status/1988267386777047268\",\"description\":\"IQ AI X.com Post on BingeBird\",\"timestamp\":1762983088484},{\"id\":\"i2fYsZk5Gd\",\"url\":\"https://x.com/IQAICOM/status/1988636913087975526\",\"description\":\"IQ AI X.com Post on Obrix\",\"timestamp\":1762983088484},{\"id\":\"8eff796b-7aa5-4f17-aa74-543ed31349c3\",\"url\":\"https://blog.iqai.com/adk-ts-hackathon-2025/\",\"description\":\"ADK-TS Hackathon 2025 Announcement\",\"timestamp\":1762984710726}]"},{"id":"previous_cid","value":"\"https://ipfs.everipedia.org/ipfs/QmcGw6qPceeciJ37oBVz87Y3FyynDF1HSy4h6DPYM8iRHZ\""},{"id":"commit-message","value":"\"Updated wiki content\""},{"id":"previous_cid","value":"QmcGw6qPceeciJ37oBVz87Y3FyynDF1HSy4h6DPYM8iRHZ"}],"events":[{"id":"5c447530-014c-4c96-9361-92957c40ec3c","date":"2025-09","title":"Hackathon Announced and Registration Opens","type":"DEFAULT","description":"IQ AI officially announced the ADK-TS Hackathon 2025, opening registration for developers worldwide to participate in the four-week virtual event.","link":"https://blog.iqai.com/adk-ts-hackathon-2025/","multiDateStart":null,"multiDateEnd":null,"continent":"Unknown","country":"Unknown"}],"user":{"id":"0x8af7a19a26d8fbc48defb35aefb15ec8c407f889"},"author":{"id":"0x8af7a19a26d8fbc48defb35aefb15ec8c407f889"},"operator":{"id":"0x1E23b34d3106F0C1c74D17f2Cd0F65cdb039b138"},"language":"en","version":1,"linkedWikis":{"blockchains":[],"founders":["iq-ai"],"speakers":[]},"recentActivity":"{\"items\":[{\"id\":\"47ad6d16-983a-4ec2-8852-d859db984e30\",\"title\":\"ADK-TS Hackathon 2025\",\"description\":\"The ADK-TS Hackathon 2025 was a four-week virtual event by IQ AI for developers to build AI agents using ADK-TS. It had a $5,000 prize pool, 122 participants, and 50 project submissions across categories like Web3, Agent Apps, and MCP Expansion.\",\"timestamp\":\"2025-11-12T22:03:13.096Z\",\"category\":\"Wiki Update\",\"status\":{\"icon\":\"RiGlobalLine\",\"label\":\"Wiki Updated\",\"iconClassName\":\"text-green-500\"},\"user\":{\"name\":\"0x8af7a19a26d8fbc48defb35aefb15ec8c407f889\",\"address\":\"0x1E23b34d3106F0C1c74D17f2Cd0F65cdb039b138\"},\"button\":{\"label\":\"View Summary\",\"icon\":\"RiFileTextLine\"},\"summarySections\":[{\"title\":\"Content\",\"subtitle\":\"A hyperlink was added in the introductory paragraph.\",\"variant\":\"modified\",\"changeCount\":1,\"changes\":[\"Added a link to 'Agent Development Kit for TypeScript (ADK-TS)' in the first sentence.\"]}]}]}"}