Start Your AI Journey
Explore practical AI workloads, model inference, and the tools behind an open compute experiment.
Putting overlooked GPUs to work. Boats N Hoes is an open-source experiment exploring useful AI compute, starting with two Radeon GPUs and a mission to make distributed computing practical, transparent, and verifiable.
EARLY-STAGE PROTOTYPE · HARDWARE VALIDATION IN PROGRESS
Explore practical AI workloads, model inference, and the tools behind an open compute experiment.
Help test how accessible hardware can participate in coordinated compute jobs. Worker onboarding is on the roadmap. Check your GPU →
Inspect the source, follow development, reproduce tests, and help us publish real performance results.
Boats N Hoes explores a small, auditable path from local GPU inference to coordinated useful-compute jobs. We publish what works, what breaks, and what remains unproven.
Reported setup: Ryzen 5 5600X, 32 GB RAM, Ubuntu, and two RX 470 cards with different VRAM capacities.
Test a small Vulkan-capable workload on each GPU independently. Measure memory, speed, temperature, and output quality.
Validate task outputs, reject duplicate jobs, and independently audit selected results before recording accepted work.
This is the intended design, not a claim that a distributed network is already running.
No fake live counters. These labels reflect the current documented state of the repository.
Milestones are deliberately ordered to prove the hardware before adding infrastructure or token complexity.
Capture Ubuntu, kernel, PCI IDs, drivers, Vulkan devices, and permissions.
Complete a small Vulkan smoke test on each card and record benchmark results.
Registration, signed job retrieval, execution, receipts, retries, and logs.
Job lifecycle, deterministic checks, duplicate rejection, audit sampling, SQLite ledger.
Run both GPUs independently; test restarts, malformed jobs, and throughput.
Calculate hypothetical credits from accepted work. No real payouts.
Only after the compute prototype works: capped test token, tests, and independent review.
Read the hardware notes, run the checks, and publish reproducible results.
Read the prototype notes, inspect the code, and help turn the first hardware test into a reproducible result.