Search

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Turn any LangChain create_agent into a multi-agent workflow orchestrator (Claude Code Workflow, ported).

Say "Hey Claude" and dispatch a Claude Code background agent — a fully local, on-device voice wake word for your Mac.

Text-to-SQL framework with tool-based schema retrieval. Built on LangChain's Deep Agents harness.

Coordinate multi-agent implementation workflows from markdown plans.

Governed agent platform built on EngramPort GraphRAG memory. BB4C — Breath Before Code.

Mistral AI integration for Microsoft Agent Framework.

Turn any LLM into an interactive UI. One line of Python — no React, no frontend setup.

1,026 lazy-loading AI skills for Claude, Gemini, and Scientific agents

JetBrains-native AI agent plugin that actually uses IDE tools instead of wasting tokens on terminal commands

DIKW memory system v3 universal deployment template. 11-step information flow. Any Hermes Agent one-click deploy: 5 min to full memory system (95% coverage) + 6-layer protection + 30 sessions to 98%. A2/B/C 3-range localization + one-click deployment script.

UTHY AGENTIC OS — Autonomous agentic operating system for your terminal. Cyberpunk HUD, 25 themes, chat panel, file upload, persistent memory, knowledge base, 10 core engines (137 methods). By uthuman & co.

An autonomous LLM-powered agent that reviews GitHub Pull Requests fetches diffs, analyzes code changes, and returns structured feedback with severity ratings and interactive visualizations.

Pattern-aware OpenTelemetry tracing for multi-agent LLM systems

Inter-agent message compression and token budget management for multi-agent LLM systems

Difficulty-aware routing and model selection for multi-agent LLM workflows

18 reusable multi-agent orchestration patterns for LLMs

Turn a spec into a frozen acceptance harness enforced via Claude Code Stop hook.