Free cloud GPUs for learning CUDA
Purpose-built session recall engine — persistent daemon with BM25 + vector hybrid search
ONNXRuntime Node.js binding
Linux x64 CUDA native binary for @mni-ml/framework (requires NVIDIA GPU + CUDA drivers)
Project-scoped memory layer for Claude Code, Codex, Hermes, MCP, and dashboards
Extension of @isdk/llama-node-linux-x64-cuda - prebuilt binary for @isdk/llama-node for Linux x64 with CUDA support
Node.js client for liblloyal+llama.cpp
Three.js-based 3D Gaussian splat viewer
Node.js Library for Large Language Model LLaMA/RWKV
Cloudflare-hosted MCP server for code indexing, retrieval, and assistant memory with a direct remote MCP endpoint and local stdio bridge.
OpenCodeHub — ONNX-based deterministic text embedder (gte-modernbert-base)
NVIDIA CUDA driver and runtime API bindings
Node bindings for CatBoost library to apply models. CatBoost is a machine learning method based on gradient boosting over decision trees.
TensorFlow.js GPU with native sm_120 (Blackwell) kernels — drop-in replacement for @tensorflow/tfjs-node-gpu
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
Linear algebra library - backed by C++.
Local TTS via Pocket TTS (on-device, Rust/Candle, CPU-capable)
detect GPU on Windows/macOS
Extension of @isdk/llama-node-win-x64-cuda - prebuilt binary for @isdk/llama-node for Windows x64 with CUDA support
Prebuilt binary for node-llama-cpp for Windows x64 with CUDA support
HyperLite native binary for Windows x64 — terminal-native local AI with CUDA GPU acceleration
Benchmark and verify idle compute before it earns. The CLI for IDLE compute providers.
A simple CLI to clone, manage, and link repositories for LLM reference
NVIDIA CUDA™ bindings for Node.js