Open source tools built to bridge creative intent and technical execution.

Optimization

Nemotron 3 hybrid architecture

JetBlock v4

Full Nemotron 3 Optimization

Production-grade optimization for Nemotron 3's hybrid architecture—Mamba-2 state-space models, MoE routing, and attention layers. V2 only handled 12% of layers. V4 optimizes all 52.

GitHub

CONDUIT

Non-Linear Inference Optimizer

Speculative generation with branch pruning: generate 4 candidates, score at checkpoints, keep the best. High-quality output at roughly half the compute cost.

GitHub

RTX4090 Nodes

Hardware-Specific Acceleration

TensorRT auto-conversion, FP8 TensorCore utilization, and memory management tuned for RTX 4090. Includes real-time GPU monitoring and VRAM optimization.

GitHub

Reproducibility

Batch-invariant inference

Deterministic Nodes

Guaranteed Reproducibility

Temperature=0 doesn't guarantee determinism—batch-size variance does. These nodes enforce batch_size=1 with fixed RNG states. Same seed, same prompt, identical output. Always.

GitHub

Framework Ecosystem

ECHO · CSQMF · PRISM

AI framework nodes implementing 4-tier context memory (ECHO), deterministic expert routing (CSQMF), and 6-perspective analysis (PRISM). Built on ThinkingMachines research.

GitHub

VFX Pipeline

Houdini ↔ ComfyUI ↔ RTX Remix

RadiantSuite

AI-Houdini Bridge

Connects AI assistants directly to Houdini sessions. Synapse handles communication, Engram maintains project memory. AI that understands your VFX context.

GitHub

Houdini-ComfyUI

Bidirectional Pipeline

Pass renders from Houdini to ComfyUI for AI enhancement, receive processed results back. Automated batch processing for production pipelines.

GitHub

RTX Remix Nodes

Texture Pipeline Integration

Load captured textures by hash, generate PBR maps, export to mod folders with correct naming. Full RTX Remix asset pipeline in ComfyUI.

GitHub

Interested in collaboration? Get in touch