No Python. No Excuses. Build AI Agents with Mastra
Hosted on UnstopFetched about 3 hours ago
Saturday, June 13, 2026
to Saturday, August 1, 2026
•
2 months long
Student only
This hackathons is only open to students. Double check the event page for more information as this may mean only those from a particular university/country are eligible.
Event Type
in person
159
Participants
14
Est. Projects
HiDevs × Mastra Hackathon
No PPT. Just Agents.
The first AI agent hackathon built exclusively for TypeScript developers.
Python was never the gate. It was just the key everyone assumed you needed.
For years, the AI agent ecosystem has been dominated by Python-first frameworks. If you wanted to build production-grade agents, you were expected to learn Python before writing your first workflow. Meanwhile, millions of TypeScript developers watched the agent revolution from the sidelines.
That changes now.
HiDevs × Mastra is a flagship AI agent-building hackathon designed for developers who want to build real, production-ready AI systems using TypeScript from end to end.
Over multiple rounds, participants will design, architect, and ship autonomous agent systems that solve real-world problems across hiring, finance, legal intelligence, education, incident response, and open innovation.
This is not a hackathon for slide decks, mockups, or AI wrappers.
Every submission must be a working agent.
Event Timeline:
The hackathon unfolds across four key milestones, taking participants from architecture design to building and showcasing production-grade AI agents.
13 June – 19 June 2026 | Registrations Open
Register through Luma, Unstop, and the HiDevs Platform. Participants gain access to resources, referral programs, and hackathon updates.
20 June 2026 | Round 1 Begins (Online)
Participants receive the problem statements and begin designing their solution architecture using HiDevs Architecture Copilot. The focus of Round 1 is creating a robust agent architecture built around Mastra, Qdrant, and Enkrypt AI.
2 July 2026 | Round 1 Results
The top 300 submissions advance to Round 2. Shortlisted participants will receive feedback on their architecture and begin building their solution based on the architecture submitted in Round 1.
4 July – 11 July 2026 | Build Sprint
Qualified teams will work remotely to transform their approved architecture into a fully functional AI agent using Mastra, Qdrant, and Enkrypt AI. During this phase, participants will build, test, refine, and prepare their solutions for the Grand Finale.
12 July 2026 | Grand Finale (Offline)
The top 300 builders will participate in a 12-hour offline hackathon at OJone, Bengaluru, from 10:00 AM to 10:00 PM.
Participants will complete final development, receive mentorship, network with fellow builders, and present their working AI agents to judges from Mastra, Qdrant, and Enkrypt AI.
Projects will be evaluated on technical implementation, innovation, problem impact, agent capabilities, and effective integration of the mandatory technology stack.
Winners will be announced at the conclusion of the event.
Prizes, Swags & Recognition:
Compete for a ₹50,000 Cash Prize Pool, exclusive sponsor swags, books, and community rewards.
₹50,000 Cash Prize for the Top 5 teams in the Final Round
Exclusive Swags from Mastra, Qdrant, and Enkrypt AI
Mastra Book for all participants qualifying for Round 2
Top 10 Social Media Awards – ₹2,000 reward and recognition from HiDevs & Mastra
Referral Program – ₹3,000 reward pool for the Top 20 referrers
Total confirmed rewards: ₹50,000 Cash Prize + Qdrant Swags + Enkrypt AI Swags + Mastra Books + Community Recognition.
Mandatory Technology Stack:
Every submission must integrate all three technologies as core components of the solution. These are not optional integrations or bonus points—they form the foundation of the entire hackathon experience.
Mastra — Agent Orchestration Layer
Mastra powers the intelligence and execution layer of your agent. It is responsible for orchestrating workflows, managing tool calls, routing memory, handling branching logic, enabling human-in-the-loop interactions, and coordinating multi-step agent behavior.
Participants are expected to leverage Mastra to build agents that can reason, plan, execute, and adapt across complex workflows rather than relying on isolated prompts.
Qdrant — Memory & Retrieval Layer
Qdrant serves as the long-term memory system for your agent. It enables semantic search, vector storage, contextual retrieval, retrieval-augmented generation (RAG), and persistent memory across sessions.
Whether you're building a hiring copilot, a finance advisor, or an incident response system, your agent should be able to remember, retrieve, and reason over historical information to deliver context-aware experiences.
Enkrypt AI — Safety & Evaluation Layer
Enkrypt AI ensures that every agent remains reliable, trustworthy, and production-ready. Participants must use Enkrypt AI to evaluate outputs for hallucinations, bias, toxicity, safety violations, and other potential risks before information reaches the end user.
The future of AI is not just intelligent—it must also be safe, transparent, and accountable.
Hard Requirement
All three technologies—Mastra, Qdrant, and Enkrypt AI—must be integrated into every submission.
Any project missing even one of the required technologies will be automatically disqualified before judging begins.
What You'll Build:
Participants can choose to solve one of several high-impact, real-world challenges designed around autonomous AI agents and production-grade workflows.
AI Hiring Copilot:
Build an end-to-end recruitment agent capable of analyzing job descriptions, ranking candidates, generating interviews, evaluating responses, and producing recruiter-ready hiring recommendations.
Personal Finance & Debt Advisory Agent:
Create an intelligent financial advisor that understands spending behavior, analyzes debt obligations, models future financial scenarios, and delivers personalized financial guidance.
Legal Document Intelligence Agent:
Develop a legal analysis system capable of understanding contracts, identifying risky clauses, answering legal questions, benchmarking against standard practices, and generating safer alternatives.
Student Doubt-Solving & Learning Agent:
Build a personalized AI tutor that adapts explanations to individual learning levels, tracks weak concepts over time, and provides intelligent academic support across multiple sessions.
Incident Response & Post-Mortem Agent:
Design an engineering copilot that can analyze logs, detect anomalies, retrieve historical incidents, recommend remediation steps, and automatically generate post-mortem reports.
Open Innovation Challenge — Build Your Own Agent:
Have an idea that doesn't fit a predefined category? Build an original AI agent that solves a meaningful real-world problem using the mandatory technology stack.
Across every challenge, participants will design autonomous workflows, retrieval systems, long-term memory architectures, safety evaluation pipelines, and intelligent agent experiences that resemble real production software rather than simple chatbot demos.
What Makes This Different:
TypeScript-first AI agent development
Real production architectures instead of prompt demos
Long-term memory powered by Qdrant
Agent orchestration with Mastra
Safety and evaluation using Enkrypt AI
Industry-standard judging focused on engineering depth
Direct access to engineers and mentors from the ecosystem
Judging Criteria:
Projects will be evaluated on:
Mastra Integration Depth (25%)
Qdrant Integration Quality (20%)
Enkrypt AI Coverage (20%)
Agent Output Quality (20%)
Problem Impact & Novelty (15%)
The Challenge:
Build an AI-native system that can think, retrieve, remember, evaluate, and act.
Not a chatbot.
Not a demo.
An agent.
Because the future of software will be built by interconnected ecosystems of autonomous agents—and this is where those builders start.
Hosted By:
HiDevs is a Builder Intelligence Platform for the Agentic Era We help developers transform ideas into production-grade AI agents through personalized guidance, intelligent evaluation, continuous feedback, and contextual memory. By combining specialized AI agents with developer intelligence, HiDevs understands each builder's goals, tracks their progress, and provides the insights needed to accelerate their journey. Through 100+ community experiences, builder initiatives, and ecosystem collaborations, HiDevs has engaged 15,000+ developers and is building the infrastructure that powers the next generation of AI builders.
AIHouse is the community layer powering this ecosystem. Built for founders, researchers, engineers, students, and AI enthusiasts, AI House creates a space where people consistently learn, share, collaborate, and grow together. Through initiatives like 100 Days of AI House, community gatherings, founder conversations, knowledge-sharing sessions, and industry collaborations, AI House has built a thriving network of 15,000+ community members who are actively shaping the future of AI. More than a community, AI House is where meaningful relationships, opportunities, and ideas are created every day.
Together, HiDevs and AI House are building one of the fastest-growing AI ecosystems where ideas turn into products, builders become founders, and collaborations turn into impact.