Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sort by:
The low bid isn't the price. WebMCP tools let an agent investigate a public contractor's documented cost growth, while recommending, awarding and publishing stay with a human.
An evidence-driven multi-agent engine that investigates technical regressions through hypotheses, experiments, independent evidence, and verified root causes.
A shopping agent that asks before it guesses. Searches 50,000 products with no model, no API, no network - Python standard library only. Scores 0.963 on the organizer's evaluator.
Give AI a high-level mission. It plans, discovers suppliers, makes outbound calls, negotiates prices, and locks in the deal.
Data visualization is designed for humans, making it hard for AI agents to understand what actions are supported in a page. I built Median Viz using LinkedIn demographics to explore a different model
An SRE agent that can be tailored to your organisation's applications, needs and budget. Triages incidents and plans responses for developers. More time in bed for on-call engineers.
An unerasable recording layer for AI agents. Rewind any decision, replay it under new rules, prove sensitive data never leaked, all from a log that can't be edited.
Elevator pitch CodeShift autonomously migrates legacy SAS analytics to verified R—executing, validating, repairing semantic mismatches with Gemini, and producing an auditable evidence pack.
Autonomous, zero-hallucination GovTech agent fleet powered by Gemini 3.5 Flash & Gemma 2 to resolve policy supersessions across 40k+ scanned state orders.
Say the mission. Prove the plan. Gemini interprets intent, Cortex searches the combinations, and independent Python verification decides what may act.
An autonomous AI video-editing orchestrator powered by Gemini that analyzes media assets, generates cinematic visual and audio layers, and builds timeline-ready sequences automatically.
Turn AI-agent boundaries into zero-side-effect adversarial tests, human-gated remediation, and version-bound development attestations.
ShopCopilot is a shopping agent using hybrid search, constraint-aware ranking and smart questions. It handles changing intent safely and scored a technical score of 0.74—7× the Track 4 baseline.
A personal AI tutor that guides students step by step, checks their working, and turns notes into cited summaries, flashcards, and quizzes—powered by NVIDIA Nemotron on Nebius.
An adaptive AI semester companion that automatically replans study schedules as assessments, availability, and learning progress change.
Sports Logistics & Planning for athletes (serving individuals with no team)
ParLLiaMent is an autonomous ML research agent that automates the full iterative experimentation loop for recommender system benchmarks.
Autonomous AI research agent that discovers, tests, and optimises recommendation models and features on real-world user behaviour data
An AI interview coach that pushes back like a real interviewer — and turns every session into a STAR-formatted cheat sheet.
The autonomous operations fleet for the factory floor.
When a wildfire is declared, 8 governed agents decide whether survey drones can safely fly. If they can't establish safety, they refuse to dispatch.
Pharma verification today is a dumb serial-number match no reasoning, no investigation. AnalyzeLab fixes that.
An agentic venture twin that challenges assumptions, stress-tests business ideas, and tells founders what must be true before they commit capital.
Institutions keep a durable record about you. You keep nothing comparable about them. Provenance is the other side of that ledger: obligations as versioned belief over immutable evidence.