
NodeArchitect AI Agent
AI Agent for Houdini VFX software
4 followers
AI Agent for Houdini VFX software
4 followers
I was looking for an AI tool to help with my Houdini projects, but what I found was priced out of reach for me. So I built NodeArchitect, an AI agent designed specifically for Houdini. It’s free for non-commercial use, so new artists can use it without barriers. NodeArchitect is a Houdini plugin that gives you an AI Agent that actually understands your scene. It doesn’t just respond with generic advice, it reads your node graph, interprets context, and works directly with what you’ve built.
This is the 2nd launch from NodeArchitect AI Agent. View more
NodeArchitect AI Agent
Launching today
NodeArchitect is an AI agent and MCP server for Houdini that reads your live node graph, parameters, and connections. Ask it to explain a network, debug an error, write VEX/Python, or build an HDA — grounded in your actual scene, not guesses. v2.3.1 adds ChatGPT/Codex login, Plan Mode, HDA Composer and Copernicus support. v2.4.0 adds Houdini 22 support.



Payment Required
Launch Team

Last time I posted here, NodeArchitect was a much smaller tool — basically a chat window bolted onto Houdini. Since then it's had a full rework (2.0) and a run of updates since, and it's a genuinely different product now:
What changed since we last posted:
— Houdini 22 Support
— UI overhaul. The interface used to be built natively in Houdini's Python/Qt — it's now a web-based UI instead, which gives much better text rendering (proper markdown, code blocks, syntax highlighting) and makes the whole thing easier to iterate on.
— Full scene-aware agent. It reads your node graph, parameters, and connections directly, so answers are grounded in what's actually in your file instead of generic Houdini advice.
— Built-in MCP server, no separate setup. External clients like Claude Desktop and Cursor can also connect to your live Houdini session if you want them to.
— Per-tool consent. The agent asks before anything mutates your scene — nothing happens silently in the background.
— Multi-provider support, not locked to one LLM.
— Persistent chat sessions with AI-generated titles, so you can pick a conversation back up later.
— HDA Building — describe a tool in plain English, get a Python build script.
And what's new in the latest release (v2.3.1):
— ChatGPT/Codex login via the Codex CLI. You can try it with an existing ChatGPT or Copilot sub instead of setting up a separate API key — this was the biggest friction point before.
— Plan Mode. The agent reads your live scene and puts together a full plan before it changes anything. You review, edit, or bin it before a single node moves.
— HDA Composer. Same idea as HDA Building, but plan-first with rollback if something breaks partway through.
— First Copernicus support — 23 tools for COP node inspection, image planes, diagnostics, and exporting comps. Early days for this part, more coming.
— Project memory across sessions, cook-time profiling, undo-safe edits.
I build VFX pipelines for a living, so this is built around how I'd actually want an agent to behave inside a scene I can't afford to break — plan first, ask before mutating, stay grounded in what's actually there instead of hallucinating node names.
Happy to answer anything — Codex auth flow, Plan Mode internals, Copernicus roadmap, what the 2.0 rework actually involved, whatever.