Skip to content

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.

docs(huggingface): use the glb_url field the /api/3d/look endpoint actually accepts

nirholased9112b6c9aa
diff --git a/docs/huggingface-agent-feedback-loop.md b/docs/huggingface-agent-feedback-loop.md
index c56c4f22e..a718b2e54 100644
--- a/docs/huggingface-agent-feedback-loop.md
+++ b/docs/huggingface-agent-feedback-loop.md
@@ -38,7 +38,7 @@ Three ways in, because different consumers want different shapes:
```bash
curl -s -X POST https://three.ws/api/3d/look \
-H 'content-type: application/json' \
- -d '{"src":"https://three.ws/avatars/cesium-man.glb"}'
+ -d '{"glb_url":"https://three.ws/avatars/cesium-man.glb"}'
```
What changes is not the quality of any single generation. What changes is that the agent can now **judge** one, which means it can decide to refine, and every refinement is its own version with its own artifacts. Generate, look, judge, refine, look again.