Hi everyone,

I've just released a major update to NodeArchitect, a Houdini plugin that brings an AI agent directly into your scene.

NodeArchitect reads selected nodes, parameters, and connections inside Houdini and uses that context to:

- Explain node networks
- Help debug issues
- Generate VEX and Python based on the current scene
- Document networks
- Build HDAs from natural language descriptions
- Expose Houdini through MCP for external AI tools



2.0 update changes:

- Rebuilt agent system using native function calling (more reliable multi-step behaviour)
- New web UI with streaming output and syntax highlighting
- Built-in MCP server (no separate setup required)
- GitHub Copilot login support
- Per-tool consent before scene modifications

Licensing note:
NodeArchitect 2.0 will move to a commercial license at a small price in the future, reflecting the increased scope and quality of the tool. Version 1.0 will remain free for personal/non-commercial use.

Anyone who downloads NodeArchitect before the licensing change will be grandfathered in with access to future updates at no additional cost.

Download [bishopvfx.gumroad.com]

Big update: NodeArchitect has now been updated to v2.3.x


ChatGPT/Codex login is now supported via the Codex CLI. This should make NodeArchitect much easier to try if you already use ChatGPT or Codex.

This release also adds Plan Mode, which is a major change to how the agent works. Before making any changes to your Houdini scene, NodeArchitect now generates a full implementation plan using live scene data. You can review the plan, refine it, or discard it entirely. Nothing executes until you approve it.

There is also a new HDA Composer. The agent can now help create, modify, and validate HDAs from natural language prompts. Like Plan Mode, it works plan-first, with rollback handling if something goes wrong.

Another big addition is early Copernicus / COP support. NodeArchitect previously very little Copernicus integration, so this release increases the COP toolset: 23 tools covering node inspection, image plane queries, error diagnostics, and exporting comps to disk.

Other improvements in v2.3.1 include:

• Project memory - NodeArchitect now retains context scoped to the project file rather than just the user session. Returning to a scene, picks up prior context instead of starting cold.
  
• Cook-time performance profiling - new tool profiles the network and ranks nodes by cook time, surfacing bottlenecks directly without manually digging through Performance Monitor.
  
• Undo-safe AI mutations — every AI-driven scene edit now creates a checkpoint automatically, so changes can be rolled back from the NodeArchitect panel.
  
• Compact conversations — long sessions are automatically summarized before hitting the model’s context limit, while preserving important decisions and exact Houdini paths.
  
• Better model compatibility — text-only models now fall back to text-based validation instead of breaking on viewport requests.
  
• Stability fixes — including cook-deadlock prevention for agent-triggered scene evaluation and other reliability improvements.
  

Overall, this is one of the biggest NodeArchitect updates so far. The focus has been on making the agent safer, easier to get started with, and more useful in real Houdini workflows: ChatGPT/Codex login, plan-first execution, rollback-safe edits, HDA creation, longer sessions, and the first step toward COP/compositing support.