{"name":"gpuworks","repo":"flitai-io/gpuworks","url":"https://midorreal.com/project/flitai-io-gpuworks","repository":"https://github.com/flitai-io/gpuworks","description":"A ~45 MB MaaS platform: one cluster across public and private clouds, on any mix of accelerators.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/flitai-io/gpuworks","checked":"22 Nov 2026"},"language":{"value":"Go","source":"https://github.com/flitai-io/gpuworks","checked":"22 Nov 2026"},"last_release":{"value":"v26.11.4, 18 Nov 2026","source":"https://github.com/flitai-io/gpuworks/releases","checked":"22 Nov 2026"},"releases":{"value":"4","source":"https://github.com/flitai-io/gpuworks/releases","checked":"20 Nov 2026"},"contributors":{"value":"18","source":"https://github.com/flitai-io/gpuworks/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/flitai-io/gpuworks","checked":"22 Nov 2026"}},"stars":231.0,"writeup":{"what_it_is":"GPUWorks is a GPU management and Model-as-a-Service (MaaS) platform, with the control plane and web UI packaged as a 40 MB download. It lets users join GPU servers, cloud instances, containers or Macs to one cluster, deploy models behind an OpenAI-compatible endpoint, and manage the placement of engines such as vLLM and SGLang across NVIDIA, AMD, Ascend, PPU, Hygon and Apple Silicon hardware.","audience":"Teams running self-hosted AI models across mixed GPU hardware and cloud or private infrastructure","claims":[{"kind":"specific","claim":"The whole control plane, web UI included, is a 40 MB download","excerpt":"The whole control plane, web UI included, is a 40 MB download.","status":"not_checked"},{"kind":"specific","claim":"Supports NVIDIA, AMD, Ascend, PPU, Hygon and Apple Silicon accelerators in one cluster","excerpt":"NVIDIA, AMD Instinct and Ryzen AI Max, Huawei Ascend, T-Head PPU, Hygon DCU and Apple Silicon run side by side in the same cluster.","status":"not_checked"},{"kind":"specific","claim":"Built-in catalog ships 1,235 launch specs for 392 models","excerpt":"The built-in catalog ships 1,235 launch specs for 392 models","status":"not_checked"},{"kind":"specific","claim":"One server ran 1,003 rented GPU machines across 7 regions in a drill on Alibaba Cloud","excerpt":"one server ran 1,003 rented GPU machines across 7 regions","status":"not_checked"},{"kind":"specific","claim":"Server and agent are each one static binary built with CGO_ENABLED=0","excerpt":"The server and the agent are each one static binary (`CGO_ENABLED=0`)","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-20"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":91,"reality":78,"gap":14,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-18T06:40:36+00:00","text":"Latest release v26.11.4","source":"https://github.com/flitai-io/gpuworks/releases"},{"date":"2026-11-04T03:40:36+00:00","text":"First release","source":"https://github.com/flitai-io/gpuworks/releases"},{"date":"2026-10-22T22:17:35+00:00","text":"Repository created","source":"https://github.com/flitai-io/gpuworks"}],"cite":"gpuworks is a GitHub project at https://github.com/flitai-io/gpuworks written mainly in Go, described there as \"A ~45 MB MaaS platform: one cluster across public and private clouds, on any mix of accelerators\".","attribution":"Data from Mid or Real, https://midorreal.com/project/flitai-io-gpuworks, checked 22 November 2026. Attribution with a link is required.","still_real":null}