Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
-
Updated
Oct 3, 2025 - TypeScript
#
ai-evaluation
Here are 5 public repositories matching this topic...
Repository for benchmark saturation research project.
-
Updated
Sep 17, 2025 - TypeScript
A fully open-source database of AI models with benchmark scores, prices, and capabilities.
-
Updated
Aug 27, 2025 - TypeScript
Plug-and-play Human-In-The-Loop integration of agentic workflows
framework npm-package typescript-library openai quality-assurance workflow-automation ai-pipeline ai-evaluation hitl prompt-engineering ai-workflows anthropic multi-llm google-gemini agent-orchestration content-evaluation human-in-the-loop-ai llm-integrat
-
Updated
Aug 11, 2025 - TypeScript
A production-grade platform to evaluate and compare the performance of Large Language Models (LLMs) like OpenAI, Anthropic, and Google’s PaLM. It features real time analytics, hallucination detection, and cost performance benchmarking using standardized datasets (e.g., GSM8K).
react benchmarking machine-learning typescript frontend backend openai fullstack model-comparison cost-optimization fastapi ai-evaluation large-language-models anthropic google-palm llm-evaluation hallucination-detection llm-testing
-
Updated
Sep 11, 2025 - TypeScript
Improve this page
Add a description, image, and links to the ai-evaluation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ai-evaluation topic, visit your repo's landing page and select "manage topics."