.png&w=256&q=75)
🤝 Top Collaborators
🤓 Latest Submissions
Pocketful
Pocketful is a wallet and payments application built by a three-seat software factory in BAND Desktop. Our API Engineer, UI Designer, and independent Reviewer collaborated in one room, handed work to each other, and checked the results before acceptance. Their reusable mandates, full room log, and commit history are included in the public repository so the factory can be inspected and run again. The application supports wallet balances, payments, requests, bill splitting, holds, refunds, and historical corrections. Financial amounts use integer minor units. Transfers are atomic, retries are idempotent, and balances cannot become negative. We delivered separate Docker services for all four hackathon stages and verified the final stage against the supplied harness. The video shows the agents’ handoffs and review alongside a working browser demo. The hosted link shows the team’s live wallet; the repository’s stage-4 folder contains the final staged submission.
6 Oct 2026
ROCmPorter Agent — CUDA to ROCm
ROCmPorter Agent turns CUDA lock-in into a verifiable migration path to AMD ROCm. Most AI and HPC projects are built around NVCC, CUDA headers, nvidia/cuda containers, and CUDA-only Python wheels. Teams that want to move to AMD hardware face two problems: they can't see which files actually block the port, and they can't trust raw LLM-generated migration patches, which routinely hallucinate APIs and break builds. ROCmPorter solves both. The workflow has five reviewable steps. Scan: clone any public or private GitHub repository and detect CUDA/NVIDIA assumptions with a deterministic, evidence-driven scanner — every finding cites a concrete file and line with severity and confidence. Report: get a ROCm portability score, an executive summary, and a migration checklist. Patch: generate a single-file ROCm review artifact using local Ollama with qwen2.5-coder — no paid cloud LLM API, so private code never leaves the machine. Verify: every artifact passes syntax validation, source drift checks, diff replay, artifact hashing, and CUDA/ROCm-aware semantic risk scoring. Apply stays gated until verification returns applyReady=true — the product is honest about what AI output can and cannot be trusted to do. Export: offline HTML/JSON/Markdown bundles, checksummed zips, and GitHub-ready PR review comments with inline suggestions. The proof is tracked in the repo: benchmark run submission-proof-v2 completed 3/3 cases against real repositories (pytorch/extension-cpp, NVIDIA/cuda-samples) with 3 export-ready review artifacts, 0 failures, and 0 high-risk patches. Stack: React + Vite frontend, FastAPI backend, local Ollama. Live demo hosts the production UI — click "Load Sample Scan" for the full offline judge flow. Built by Team Hacker Is Back for the AMD Developer Hackathon ACT II, Unicorn Track.
13 Jul 2026
