RAG Evaluation

开源 AI 应用评测平台，支持 RAG、AI Agent、多轮对话、LLM-as-Judge、接口评测、评测报告和人工盲测。Open-source AI evaluation platform for RAG, AI Agents, multi-turn conversations, LLM-as-Judge, endpoint evaluation

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Learn AI Engineering! Learn it. Build it. Ship it for others.

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns.

A quality-gated League of Legends post-game coaching agent built on deterministic match data, RAG, and LLM evaluation.

AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

AI equity research agent with resilient workflows, evidence-grounded RAG, versioned reports, and automated quality evaluation.

Distributed multi-agent retrieval-augmented generation (RAG) architecture with specialized router, sub-question planner, and evaluator nodes.