Announcing the Winners of Kong Agentic AI Hackathon

We’re thrilled to announce the winners of the 5th Annual Kong Hackathon, held in conjunction with API Summit 2025. 

We challenged solo hackers and full-stack teams worldwide to create projects that don’t just react, they think, adapt, and act autonomously. Clearly, this year's theme was agentic AI: solutions that take initiative, make decisions, and solve real-world problems without being told what to do at every step.

The hackathon participants built projects that connected intelligent agents with real-world infrastructure through the Kong AI Gateway, creating solutions that were innovative, practical, and production-ready.

The results are in! The top three projects listed below impressed the judges for creativity, technical depth, impact and use of Kong. Each one shows how agentic AI and API infrastructure are shaping the next wave of intelligent automation.

1st place: Session history plugin

By: Abhishek Chauhan and Preesha Gehlot

The Session History Plugin extends the Kong AI Gateway with persistent session objects that preserve conversation history across requests using the x-ai-session-id header.

By integrating MongoDB for storage and implementing context summarization for efficient state management, the plugin enables scalable, context-aware conversational AI sessions.

It’s a thoughtful solution to one of the most common challenges in AI-driven applications: maintaining relevant context without sacrificing performance.

2nd place: AgenticAI-MCP-client

By: Satyajit Sial, Prema Namasivayam, Ritik Bhola, Akash Acharya, and Ashal Pearl Dsouza

The AgenticAI-MCP-Client plugin brings seamless Model Context Protocol (MCP) integration to Kong.

Connected to the Mongo MCP Server, it accepts natural language input, processes it through an LLM-powered agent, and converts it into structured queries.

By centralizing MCP connections within the Kong Gateway, the plugin reduces operational overhead, streamlines observability, and helps minimize the attack surface; it’s a big step forward in safely operationalizing AI systems.

3rd place: Kong auto rollback AI agent

By: Andrew Kew

The Kong auto rollback AI agent is an autonomous Site Reliability Engineering (SRE) tool designed to monitor gateway configurations for failures and automatically roll back misconfigurations.

This agentic approach to infrastructure management ensures rapid recovery and operational resilience — a practical example of using AI to strengthen DevOps workflows.

 Special awards

• Best Agentic Project: Customer Support Agent
  By: Shaik Mohammed Zakeer, Jayant Acharya, and Tanmaiyee Vadloori
• Most Creative Project: kongversation-plugin
  By: Mani Saurabh, Navjot K, Shailesh Ghaisas & Vinita Dargan
• Best Solo Project: Autonomous Security Auditor Agentic AI
  By: Sachin Ghumbre

What made these projects stand out?

While each project took a unique approach, the winning entries shared a few common traits:

• They solved real-world problems. Each team tackled something concrete, from gateway reliability to conversational memory.
• They built systems that take initiative. These weren’t passive tools; they were autonomous teammates that observed, decided, and acted.
• They shipped. Every winning entry had a working demo. Real code. Real impact.

Stay tuned for the Kong Hackathon 2026

Congratulations to all the winners and participants on making this year’s hackathon successful.

These projects demonstrated creativity and technical excellence which truly manifests the innovative spirit of Kong’s developer community. 

We especially thank the mentors, judges, and contributors for their support.

That’s a wrap on the Kong Annual Hackathon 2025. See you next year!