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(3d-api): point the catalog links at the browsable routes

nirholasef30aecffb81
diff --git a/data/pages.json b/data/pages.json
index 782519042..c3c78b2e7 100644
--- a/data/pages.json
+++ b/data/pages.json
@@ -4815,7 +4815,7 @@
},
{
"path": "/tutorials/connect-ai-brain",
- "title": "Tutorial · Connect Anthropic or OpenAI as the brain",
+ "title": "Tutorial · Connect Anthropic, OpenAI, or xAI as the brain",
"description": "Plug your own model provider into the agent loop. Bring your API key, choose your model, control cost and latency.",
"priority": 0.8,
"changefreq": "monthly",
diff --git a/docs/3d-api.md b/docs/3d-api.md
index e20491884..0d553d7db 100644
--- a/docs/3d-api.md
+++ b/docs/3d-api.md
@@ -11,9 +11,10 @@ Base URL: `https://three.ws`
> This page documents the **free** 3D endpoints. Higher-quality generation and
> rigging are paid: **Forge Pro** (quality tiers) at [`/api/x402/forge`](https://three.ws/api/x402/forge)
> and **Rigged Avatars** (animation-ready skeletons) via `POST /api/forge?action=rig`.
-> Both of those links are openable catalogs: `/api/x402/forge` lists the per-tier
-> USDC prices, and [`/api/forge?catalog`](https://three.ws/api/forge?catalog) lists
-> the path / tier / backend matrix. The rig action itself is POST-only.
+> The rig action is POST-only, so there is nothing to open at `/api/forge` itself;
+> for a browsable view of what the forge can do, open
+> [`/api/forge?catalog`](https://three.ws/api/forge?catalog) (the path / tier /
+> backend matrix).
Prefer a browsable landing page? See [three.ws/3d](https://three.ws/3d) — hero,
live endpoint table, a runnable inspection console, an embedded 3D viewer, and the
diff --git a/public/changelog.json b/public/changelog.json
index 54992012f..dc487c3a1 100644
--- a/public/changelog.json
+++ b/public/changelog.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-08-15T06:53:35.614Z",
+ "generated_at": "2026-08-15T06:57:50.640Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json",
"site": {
"name": "three.ws",
@@ -59,6 +59,17 @@
"fix"
]
},
+ {
+ "date": "2026-08-15",
+ "type": "update",
+ "title": "Eight build tutorials now match what the platform actually does",
+ "summary": "An audit of eight tutorials found instructions that could not work. The AI-brain tutorial described a model line-up that had been superseded: it never mentioned the Claude 5 family (Sonnet 5, Opus 5, Fable 5), which are live and selectable, and it recommended Sonnet 4.6 as the default. It also sent you to screens that do not exist, telling you to add API keys under a gear icon in My Agents and to change models, sampling knobs, and streaming under a Brain menu. Provider keys actually live in the AI Provider Keys panel on your account page, the model is a field on the agent's embed policy, and streaming has no off-switch. The promised usage tab with token charts and threshold emails did not exist either; the tutorial now documents the real per-agent usage read and points at the monthly quota and per-minute rate limit, which are the controls actually enforced before your money is spent. It also now explains that a visitor can never escalate your agent onto a paid model. The custom-GLB tutorial was worse for anyone following along: it linked a Studio address that no longer resolves, and four of its commands invoked gltf-transform subcommands that have never existed, so converting an FBX, renaming animation clips, and the full Mixamo walkthrough all failed at the first step. Those are replaced with the converter the platform itself uses and a clip-renaming script that was run against a real avatar to confirm it works. Its Draco flag was wrong, its upload path pointed at the wrong page, and it still warned that an avatar without an idle clip would stand frozen in a T-pose, which stopped being true when animation retargeting became universal. Finally, the page-events tutorial listed the wrong fallback order for emote animations.",
+ "link": "/tutorials/connect-ai-brain",
+ "tags": [
+ "docs",
+ "fix"
+ ]
+ },
{
"date": "2026-08-15",
"type": "update",
diff --git a/public/features.json b/public/features.json
index b25ea1a08..ee9dd9b33 100644
--- a/public/features.json
+++ b/public/features.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-08-15T06:53:35.314Z",
+ "generated_at": "2026-08-15T06:57:50.370Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json",
"site": {
"name": "three.ws",
diff --git a/public/llms-full.txt b/public/llms-full.txt
index dca9610f4..469f43696 100644
--- a/public/llms-full.txt
+++ b/public/llms-full.txt
@@ -3779,7 +3779,7 @@ URL: https://three.ws/tutorials/upload-custom-glb
Bring your own model: any glTF 2.0 .glb from Blender, three.ws Studio, or any other source. Get it validated, fixed, and live.
-### Tutorial · Connect Anthropic or OpenAI as the brain
+### Tutorial · Connect Anthropic, OpenAI, or xAI as the brain
URL: https://three.ws/tutorials/connect-ai-brain
diff --git a/public/llms.txt b/public/llms.txt
index f916bdb65..a3c4e09ad 100644
--- a/public/llms.txt
+++ b/public/llms.txt
@@ -664,7 +664,7 @@ Docs, tutorials, and reference.
- [Tutorial · Build a site concierge from the building blocks](https://three.ws/tutorials/build-a-site-concierge): How the Concierge widget is assembled: the talking avatar, the streaming chat, the tool calls, and how to point the same parts at your own backend over Server-Sent Events.
- [Tutorial · Trigger the agent from page events](https://three.ws/tutorials/trigger-from-page-events): Make your agent react to clicks, scrolls, form submits, and route changes: turn it into a real co-pilot, not a chat widget.
- [Tutorial · Upload a custom GLB avatar](https://three.ws/tutorials/upload-custom-glb): Bring your own model: any glTF 2.0 .glb from Blender, three.ws Studio, or any other source. Get it validated, fixed, and live.
-- [Tutorial · Connect Anthropic or OpenAI as the brain](https://three.ws/tutorials/connect-ai-brain): Plug your own model provider into the agent loop. Bring your API key, choose your model, control cost and latency.
+- [Tutorial · Connect Anthropic, OpenAI, or xAI as the brain](https://three.ws/tutorials/connect-ai-brain): Plug your own model provider into the agent loop. Bring your API key, choose your model, control cost and latency.
- [Tutorial · Create, enhance & edit agent memory](https://three.ws/tutorials/create-and-edit-memory): Five ways to teach an agent a fact that sticks between sessions: the dashboard, the agent itself, MCP tools, the REST API, and a skill. Plus how to sharpen, edit, and forget.
- [Tutorial · Place your agent in the real world (IRL)](https://three.ws/tutorials/place-agent-irl): Use camera passthrough, a joystick, and tap-to-place to drop your 3D agent into your physical space: and understand how location privacy works.
- [Tutorial · Give your agent a voice with lipsync](https://three.ws/tutorials/voice-and-lipsync): Add real-time text-to-speech with synchronized mouth movement: pick or clone a voice, drive visemes from audio, and wire it into a live agent.
diff --git a/public/sitemap/index.html b/public/sitemap/index.html
index 8166ea3bb..904ec6092 100644
--- a/public/sitemap/index.html
+++ b/public/sitemap/index.html
@@ -4585,7 +4585,7 @@
</li>
<li>
<a href="/tutorials/connect-ai-brain">
- <span class="sm-title">Tutorial · Connect Anthropic or OpenAI as the brain</span>
+ <span class="sm-title">Tutorial · Connect Anthropic, OpenAI, or xAI as the brain</span>
<span class="sm-path">/tutorials/connect-ai-brain</span>
<span class="sm-desc">Plug your own model provider into the agent loop. Bring your API key, choose your model, control cost and latency.</span>
</a>
diff --git a/public/tutorials-manifest.js b/public/tutorials-manifest.js
index 718a37d3a..d44957158 100644
--- a/public/tutorials-manifest.js
+++ b/public/tutorials-manifest.js
@@ -365,7 +365,7 @@
{
slug: 'connect-ai-brain',
tier: 'middle',
- title: 'Connect Anthropic or OpenAI as the brain',
+ title: 'Connect Anthropic, OpenAI, or xAI as the brain',
blurb: 'Plug your own model provider into the agent loop. Bring your API key, choose your model, control cost and latency.',
builds: 'An agent powered by the model you choose, billed to your account',
time: '30 min',