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
The delivery-date agent that proves padding wins — then refuses to do it.
VerdeLab Research Agent is a LangGraph agent designed for non-technical biologists. It helps biologists to manage the full research lifecycle from execution tracking to audit.
Our app addresses gaps in current medical research papers, maps concepts together in creative ways and researches new connections(indirect links) using Spider2's IDC and PanCancers databases.
The query executed. The insight didn't. TrustSQL is AI that verifies SQL against your business question, stress-tests joins & filters on live data, scores confidence & suggests fixes before you ship.
ClinicalxCraft an AI agent that lets clinicians query cancer genomic data in plain English no SQL, no bioinformatician. It investigates like a researcher: hypothesis, real queries, evidence, caveats.
"Ask a cancer research question in plain English — get a matched patient cohort, survival curves, and governed SQL in seconds, not weeks."
Shifting from manual querying to autonomous reasoning over the entire Ethereum schema
Automated workflow for enterprises to fine-tune models via agent traces
"We're all installing AI tools as fast as they ship with zero idea if they're safe. LLM / AI Safety Check gates them — Using CRAFT and Natural Language to ask questions
Audits all your repos for dependcy risks and recommends actionable steps to ensure integrity of your applications.
An autonomous agent that hunts crypto scams on its own. It triages every token, unmasks the operators behind them, and blocks them through a risk API before users get hurt.
Experience the future before you choose it
"Ask an AI how many CVEs a package has and it guesses. Warrent answers with the real query and CVEs, or admits when it can't."
OncoSight AI lets cancer researchers ask plain-English questions across IDC and PanCancer data, then generates SQL, charts, and auditable reports—no coding required.
ClearPath tells you if your product is safe and legal to ship — checking compliance and sanctions before a costly seizure or fine — then shows you exactly which carriers will take it, and where.
ProofGate is a firewall agent for AI agents. It measures the blast radius of every action before execution and blocks catastrophic mistakes with verifiable proof, not promises.
1. "Know what your customer buys next — before they do."2. "Foresight turns raw customer data into next-purchase predictions, churn alerts, and lifetime ."
Ghost Dependencies recovers the actual dependency graph from the data itself
Tilt isn't universal. An agent calibrates behavioral thresholds per operator, a human approves, and the same session scores differently across sportsbook platforms in real time.
TreasuryLens turns 158M on-chain CRYPTO rows into a CFO-ready risk report concentration, chain mix, liquidity, peer percentile, max drawdown, and counterparty exposure
The execution control plane for enterprise AI agents. Agents propose; ARF decides whether they are allowed to act. 147 repos, 63% blast radius – blocked.
1 – 21 of 21
