We’re thrilled to announce the winners of the [5th Annual Kong Hackathon](https://konghq.com/blog/news/kong-agentic-ai-hackathon-2025)5th Annual Kong Hackathon, held in conjunction with [API Summit 2025.](https://konghq.com/blog/news/api-summit-2025-recap)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](https://konghq.com/products/kong-ai-gateway)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.
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.
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.
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.
While each project took a unique approach, the winning entries shared a few common traits:
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!
We're thrilled to announce that Kong, the AI connectivity company, has been recognized as a Leader in the Gartner Magic Quadrant for API Management for the seventh year in a row. Plus, Kong was positioned furthest on the Completeness of Vision axis
API management solved a similar problem for developers. Instead of asking a platform team every time they needed an API, developers could go to a Developer Portal, discover what was available to them, and start building — within the governance bound
Traditional applications generally have well-defined boundaries. They interact with a known set of services using credentials provisioned specifically for those connections. Agents are different. Their value comes from their ability to work across s
This post is based on Kong's webinar on token cost management. Watch it below, or keep reading for the breakdown. Token cost management is how a business tracks, controls, and governs what it spends on AI model usage, the same way it already track
Your developer portal was built for a developer scanning docs in a browser: reading a page, copying a curl command, moving on. Increasingly, the thing reading those docs isn't a person. It's an agent, working through an API integration on someone's
