
Generate Terraform alert policies for AI agent latency, errors, cost and quality
- Open source
- 24.4K GitHub stars
- Cloud and infrastructure

Generate Terraform alert policies for AI agent latency, errors, cost and quality

Build custom evaluation metrics that grade your AI agent the way you do

Deploy Model Garden models to Agent Platform endpoints with cost checks and cleanup

Evaluate and iteratively improve AI agents on Google Cloud with an eval flywheel

Call Gemini, open models and custom endpoints on Google Cloud; debug 429 and 404 errors

Search, upload and manage skills in the Gemini Enterprise Agent Platform Skill Registry

Fine-tune open models or Gemini on Google Agent Platform, from dataset to endpoint

Turn a REST API on Google Cloud API Gateway into a remote MCP server

Deploy SageMaker endpoints with autoscaling, alarms, tags and smoke tests built in

Choose the right SageMaker serving container and current image URI for a model

Run local evals on Hugging Face models with inspect-ai or lighteval and pick a backend

Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF

Guides an agent through building LLM eval pipelines with datasets, evaluators and pixie

Generates and edits images through OpenRouter's Gemini 3 Pro Image model

Puts an Apigee proxy in front of an agent's LLM calls to meter tokens and screen prompts

Compiles, benchmarks and packages LiteRT models for Google Tensor Pixel TPUs

Publish, index, link and claim research papers on the Hugging Face Hub

Builds reusable shell and Python scripts that fetch and process Hugging Face API data

Fine-tunes object detection, image classification and SAM segmentation models on Hugging

Guides an agent through training sentence-transformers embedding, reranker and sparse

Generates, extends and edits videos with Gemini Omni 1.2 Flash via the google-genai SDK

Builds or adapts NVIDIA FastGen experiment configs for a network, task and method

Guides an agent through generating and inspecting NVIDIA FastGen teacher and student

Guides an agent through running, resuming and debugging NVIDIA FastGen training jobs

Recommends an LLM serving runtime and memory flags for NVIDIA Jetson devices

Benchmarks LLM and VLM serving speed on Jetson devices with structured JSON results

Guides an agent through improving NVIDIA Riva/NeMo speech recognition for a domain

Guides an agent through deploying and testing NVIDIA Nemotron Speech ASR, TTS and NMT

Finetunes NV-Segment-CT VISTA3D on your CT NIfTI image and label datasets

Runs a guarded agent loop that tunes an existing NVFLARE federated job for a metric
See every kind of AI for ai models and llm tooling: tools, agents, MCP servers and skills.Ranked: the best AI for ai models and llm tooling.