#evaluation

Yao Meta Skill

YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.

Awesome AI Engineering

The Full-Stack LLM Engineering Playbook. Architectural patterns for Agents (MCP) & RAG, coupled with advanced Post-Training recipes (SFT, DP...

Cowork Bench

Multi-tool LLM agent benchmark: 496 end-to-end MCP tasks, deterministic evaluation, Russian localization

Prometheus LLM

PrometheusLLM is a unique transformer architecture inspired by dignity and recursion. This project aims to explore new frontiers in AI resea...

Crucible

A judgment engine: register a thesis, steelman each claim, measure it against the evidence that could refute it, and refine the weakest axis...

RagScore

⚡️ The "1-Minute RAG Audit" — Generate QA datasets & evaluate RAG systems in Colab, Jupyter, or CLI. Privacy-first, async, visual reports.

Mcplab

MCPLab - Test and evaluate MCP servers with LLMs

Oh My Field

Field-fit agents to real work. Turn tacit know-how into reusable capabilities.

Decibench

The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.

MCP Interviewer

Catch MCP server issues before your agents do.

Promptfoo: LLM Evals & Red Teaming Platform

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepS...