​Welcome to the Useful Agents Hackathon

​A 24-hour sprint dedicated to building agents that reliably execute tasks and meet concrete performance metrics! Win from a $30k USD prize pool while solving real problems for startup founders while receiving free inference and post-hackathon go-to-market support.

Co-organized by NEAR AI, SF Compute, and Electric Capital 💻

​Eligibility Requirements

• ​Projects must be newly created or have substantial new features added during the hackathon period

• ​All code must be open source and publicly accessible

• ​Teams can consist of 1-4 members

• ​Each participant can only be part of one team

• ​All team members must be registered for the hackathon

​Technical Requirements

• ​Agents must be hosted on the NEAR Agent Cloud

• ​Projects must integrate at least one AI component (LLMs, ML models, autonomous agents)

• ​Code must be hosted in a public GitHub repository

• ​Projects must include quantitative benchmarks for agent performance

​Required Repository Contents

• ​Detailed README.md with project description

• ​Setup and installation instructions

• ​Architecture diagram or technical documentation

• ​Demo video or link to live demo

• ​License file (MIT, Apache 2.0, or similar)

• ​Benchmark suite and evaluation metrics

​Submission Requirements Documentation

• ​Project name and one-line description

• ​Detailed project overview (500 words max)

• ​Problem statement and solution approach

• ​Technical architecture overview

• ​Future development roadmap

• ​Comprehensive benchmark results and methodology

​Technical Deliverables

• ​GitHub repository URL

• ​Deployment instructions

• ​API documentation (if applicable)

• ​Any necessary credentials for testing

• ​List of AI models or blockchain networks used

• ​Benchmark code and test suites

• ​Performance metrics and evaluation results

​Benchmarking Requirements

• ​Defined success metrics for each task the agent performs

• ​Quantitative performance measurements

• ​Reproducible testing environment

• ​Comparison against baseline approaches

• ​Error rate analysis

• ​Task completion time metrics

• ​Resource utilization measurements

​Demo Materials

• ​3-5 minute demo video

• ​Link to live demo (if applicable)

• ​Screenshots/diagrams of key features

• ​Test accounts or sample data (if needed)

• ​Recorded benchmark runs

​Team Information

• ​Team member names and roles

• ​Contact information

• ​Project background/inspiration

• ​Track selection and bounty targets

​Judging Criteria

1. ​Technical Innovation (20%)

   • ​Novel problem-solving approaches

   • ​Implementation quality

   • ​System architecture

2. ​Task Completion & Benchmarks (30%)

   • ​Reliability of execution

   • ​Quality of benchmark methodology

   • ​Performance metrics

   • ​Reproducibility of results

   • ​Comparison to baselines

3. ​User Experience (20%)

   • ​Interface design

   • ​Ease of use

   • ​Documentation quality

4. ​AI/Blockchain Integration (20%)

   • ​Effective use of AI capabilities

   • ​Meaningful blockchain integration

   • ​Technical architecture

5. ​Presentation (10%)

   • ​Demo quality

   • ​Documentation clarity

   • ​Team presentation

​Timeline

• ​Hackathon Begins: March 14 at 10:00 AM PT

• ​Project submissions close: March 14 at 5:00 PM PT

• ​Demo presentations: March 15 at 12:00 PM - 2:00 PM PT

• ​Winners announced: March 15 at 2:00 PM PT

​Disqualification Criteria

• ​Submissions after the deadline

• ​Incomplete documentation

• ​Code plagiarism

• ​Violation of open source licenses

• ​Projects without clear AI and blockchain components

• ​Missing or incomplete demo materials

• ​Lack of quantitative benchmarks

• ​Non-reproducible results