NVIDIA NIM API plugin for ElizaOS

The Scrypted LLM plugin allows connecting to various LLM providers, or running your own locally.

This library provides a collection of reusable functions and classes to **parse**, **validate**, and **verify cryptographic signatures** for attestation report, TPM measurements and calculate measurements across multiple platforms.

Security gate and vulnerability scanner wrapper for npx skills add, powered by NVIDIA SkillSpector.

Track GPU power draw & electricity cost per pi session (NVIDIA GPUs only, via nvidia-smi). pi must run on the same machine as the GPU — it samples the local nvidia-smi and has no remote mode.

Shared TypeScript lifecycle host for NVIDIA NeMo Fabric adapters.

Sweet Search native binaries for Linux x64 (glibc) with NVIDIA CUDA backend (candle-cuda + flash-attn, SM 7.0+)

Multi-Agent AI Coding Assistant with ECHO Protocol

Local-first LLM gateway aggregating free/low-quota model APIs for coding agents

Claude Code 多模型代理 — 一���切换 DeepSeek、Qwen、GLM、商汤商量、NVIDIA 等国产大模型，协议自动转换，零配置即用。安全增强版：API Key 加密存储、Bearer 认证、SHA256 验证、速率限制、TLS 支持。LLM API proxy for Claude Code with security hardening.

Kritya — a lean, provider-agnostic terminal coding agent (NVIDIA, OpenAI, OpenRouter, Groq, Ollama, and more)

EMP CLI - coding agent with full-screen TUI (ink, clickable tool output, mouse, plan mode, markdown, vision) and 18 providers. Runs great on any light PC / weak CPU / old motherboard. Sessions, context, effort, web search, background tasks, revert.

Unified LLM API with automatic model discovery and provider configuration

A fast, cross-platform AI CLI assistant with ask and agent modes for shell tasks, file operations, and cybersecurity workflows.

n8n community node for NVIDIA NIM

Bounded native WebRTC video delivery with hardware encoding and per-viewer congestion control.

Deploy validated NVIDIA AI Cluster Runtime (AICR) recipes for GPU-accelerated Kubernetes clusters.

CLI coding agent powered by Google Gemini

knowing binary for linux-arm64

Production-ready MCP server for NVIDIA NIM models - 50+ LLMs, multimodal, image generation, embeddings, reranking with rich metadata for agent selection