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
A fast, fully offline shopping agent that understands multi-turn intent, preserves constraints, adapts to preference changes, and searches 50,000 products with local semantic reranking.
A conversational shopping agent with a 94% hit rate by asking the right questions, locking learned constraints into BM25, and letting a local LLM make the final call validated across 2,200 sessions.
Making AI agents prove their code works before it ships.
An autonomous AI research agent that builds, tests, and optimizes recommender systems, with auditable evidence for every decision.
CloudTrail for AI agents every action logged, every failure traceable.
Can you tell if an image was made by AI?Real or Fake (ROF) is a model that looks for AI-generated images, even when they've been blurred, resized, cropped, or heavily compressed.
Elevating a privacy-focused, offline product search through field-weighted BM25 indexing, catalog-grounded local vector reranking, and entropy-driven clarification questions.
Trace, inspect, compare, and audit every AI agent run — from model calls to tools, policies, and failures.
11.3× faster transformer inference on a laptop GPU.
Detecting AI-generated images after the internet has had its way with them: compressed, cropped, screenshotted, reposted. 0.98 ROC-AUC clean, never below 0.93 under any transformation we tested.
An LLM agent that autonomously runs the ML research loop on KuaiRand-Pure: observe, diagnose, invent, implement, verify, decide. Beat the official baseline in 374 experiments, unaided.
An ML research agent that runs the whole loop on its own; and never hides a bad result.
A conversational shopping agent that finds your hidden target product in ~3.6 turns using hybrid retrieval, adaptive slot-filling dialogue, and dynamic re-ranking. Fully offline, no LLM API needed.
Our model was trained using a few public source datasets, making AI-image detection simple. In the future, we aim to detect even small sections of an authentic image that have been modified using AI.
Detects AI-generated images using semantic, edge and frequency clues, built to withstand common edits and generalise to unseen generators.
AgentBL: The World's First AI-Driven Autonomous eBL Risk Pricing and Trade Finance RWA Platform, built on Injective.
TechTokers extends the Agent Launchpad with a coherent middleware layer that governs an Agent before execution, contains it during execution, and verifies its filesystem consequences after execution!
PatchProof helps people investigate whether an image may be AI-generated by combining transparent detection with robustness testing and human review using our novel Dino-FaiSR architecture.
An autonomous agent that runs the full ML research loop, train, evaluate, recover from crashes, repeat, on TikTok's KuaiRand recommender challenge, beating baseline with zero human tuning.
Audit and redact sensitive data from AI agent outputs automatically
Shopping Butler finds your dream product in ≤10 chat turns using BM25 phrase-scoring and a gated local LLM, proving smart retrieval beats brute-force LLM use.
An AI sports nutrition coach for TikTok Shop. Snap a photo of your food to instantly track macros using multi-modal AI, and get personalized health product recommendations.
An AI research agent generates ML hypotheses; evolutionary search decides which experiments survive.
A conversational retrieval shopping agent for TikTokTechJam2026
505 – 528 of 614
