Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
docs(guardian): drop the SHORT_SHA substitution from the worker's submit command, which this config never uses
nirholas5a7b8d3a6516
diff --git a/workers/granite-guardian/README.md b/workers/granite-guardian/README.mdindex bb6b4d4b1..54e10e659 100644--- a/workers/granite-guardian/README.md+++ b/workers/granite-guardian/README.md@@ -16,7 +16,7 @@ The Granite Guardian integration was written against watsonx.ai, and with no IBM```bashgcloud builds submit --config workers/granite-guardian/cloudbuild.yaml \--region europe-west4 --project aerial-vehicle-466722-p5 \- --substitutions=SHORT_SHA=manual$(date +%s) --no-source+ --no-source```The build stages the pinned weights into `gs://three-ws-model-weights/granite-guardian-3.3-8b/` on first run (about 16 GB; later runs skip it when `REVISION` matches), mirrors the vLLM image, and deploys. Then point the API at it:diff --git a/workers/granite-guardian/cloudbuild.yaml b/workers/granite-guardian/cloudbuild.yamlindex 4ea4dae95..e99ef6415 100644--- a/workers/granite-guardian/cloudbuild.yaml+++ b/workers/granite-guardian/cloudbuild.yaml@@ -8,7 +8,7 @@## gcloud builds submit --config workers/granite-guardian/cloudbuild.yaml \# --region europe-west4 --project aerial-vehicle-466722-p5 \-# --substitutions=SHORT_SHA=manual$(date +%s) --no-source+# --no-source## Region: europe-west4 holds an L4 grant nothing else uses, so a warm pin here# does not starve the 3D lanes in us-central1 (see docs/ops/gcp-credits-plan.md).