ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
Python ai-agentsamdcomfyuidockerllama-cppllmlocal-ain8nnvidiaopen-webuiragself-hostedspeech-to-textstrix-halotext-to-speechworkflow-automation
{
"repository": "https://github.com/JannisX11/blockbench",
"license": "GPL-3.0-or-later",
"image": "nginx:1.28-alpine@sha256:a8b39bd9cf0f83869a2162827a0caf6137ddf759d50a171451b335cecc87d236",
"build_image": "node:24.16.0-alpine3.22@sha256:191c9f0080fcbbc6547a85dc0ff7988072214a355aabdc1d2ec55a7dae5eea8a",
"registry_checked_at": "2026-09-20",
"platforms": [
"linux/amd64",
"linux/arm64"
],
"runtime_validation": "pending",
"source_commit": "2569d0245d600030760cf0b8429b1b0017b871f1",
"source_sha256": "f520c672a2295b342b1f29dc203914240fb92b2abec6936d7ac549fdbf782751",
"notes": "v5.2.0 web target, not Electron. npm lifecycle scripts disabled except explicit esbuild rebuild. Complete pinned upstream source archive served under /source/; ODS recipe files alongside it. Client-side WebGL, browser storage and explicit model exports; no server project volume."
}