Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Google Agent Development Kit (ADK). Code-first Python toolkit for building, evaluating, and deploying AI agents. Multi-agent orchestration, tool integration, built-in evaluation, and deployment to Vertex AI.
Guardrails AI — LLM output validation and guardrails. Define guardrails as XML/JSON specs, validate outputs against structural and semantic constraints, correct/retry on failure, and audit model behavior.
Standard API for single-agent reinforcement learning environments (Gymnasium). Provides Classic Control, Box2D, Toy Text, MuJoCo, and Atari environments with a unified env.step()/env.reset() interface. For multi-agent RL, use PettingZoo. For algorithm implementations, use stable-baselines3 or CleanRL.
All-in-one LLM evaluation toolkit (HuggingFace LightEval). 1000+ tasks with multi-backend support: Accelerate, vLLM, SGLang, Nanotron, TGI, LiteLLM, inference providers, and custom models. Sample-by-sample result exploration, custom task/metric creation. Used by HuggingFace's Leaderboard and Evals team. For pure GPT-style model eval, also consider lm-evaluation-harness.
LLM evaluation framework (EleutherAI lm-evaluation-harness). Unified benchmark evaluation for language models with 200+ tasks, support for HuggingFace transformers, vLLM, SGLang, OpenAI API, GGUF, and custom models. Used by HuggingFace Open LLM Leaderboard. Covers MMLU, HellaSwag, ARC, GSM8K, HumanEval, BBH, TruthfulQA, and more.
NVIDIA NeMo Guardrails — programmable guardrails for LLM applications. Colang-based dialog management, topical rails (fact-checking, moderation), safety rails, and security rails for production AI.
OpenAI Agents SDK — build agentic workflows with handoffs, guardrails, and tool integration. Single-agent to multi-agent orchestration. Tracing and observability. Python-first SDK from OpenAI.
LLM evaluation framework and registry (OpenAI Evals). Framework for evaluating LLMs and LLM-based systems with a registry of community-contributed eval templates. Supports model-graded evals, classification, simple completion matching, and custom completion functions. Use for systematic LLM quality testing, regression detection, and prompt engineering validation.
Multi-agent reinforcement learning environment API (PettingZoo). Standard API for multi-agent RL extending Gymnasium with Agent Environment Cycle (AEC) and Parallel APIs. Includes Atari, Butterfly, Classic, MPE, and SISL environments. For single-agent RL, use Gymnasium. For algorithm implementations, use stable-baselines3 or CleanRL.