MCP servers and skills: search, filter by where they run, and compare.
Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure Ope
OfficialSkillMIT★ 40k in collectionNo key
LLM Skills
SkillMIT★ 3Few starsNo key
Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation after user confirmation. Use when the use
OfficialSkillMIT★ 40k in collectionNo key
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training method
OfficialSkillLink only★ 11k in collection
Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and cont
OfficialSkillMIT★ 40k in collectionNo key
LLM outputs validation factuality checker
SkillLink only★ 9
LLM inference latency, token usage and cost tracer
SkillLink only★ 9
Dynamic LLM router for complexity, latency & token cost optimization
SkillLink only★ 9
LLM observability, cost, and latency trace profiler (Langfuse style)
SkillLink only★ 8
Real-time LLM prompt injection, jailbreak & sensitive extraction firewall
SkillLink only★ 8
Real-time LLM inference throughput profiler & benchmark (Inferock Bench style)
SkillLink only★ 8
Intelligent LLM API cost analyzer, model tier selector & monthly spend optimizer
SkillLink only★ 9
Privacy-first zero-cloud offline LLM inference & local memory runtime (LumiChats style)
SkillLink only★ 11
Visual workflow canvas orchestrator for modular LLM pipelines (Dify style)
SkillLink only★ 9
Multi-criteria automated LLM judge scoring engine & rubric evaluator (Braintrust)
SkillLink only★ 8
Schema-enforced structured LLM extraction engine with validation retries (Instructor style)
SkillLink only★ 8
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.
OfficialSkillApache-2.0★ 40k in collectionNo key
Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), Wa
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Auriko LLM API spot price routing optimizer
SkillLink only★ 9
Multi-provider serverless AI model inference router (DigitalOcean style)
SkillLink only★ 9
Real-time token consumption monitor & cost budget governor
SkillLink only★ 9
Session tokens count and budget tracking helper
SkillLink only★ 9
Who stands behind it
