rag-evaluation

🐢 Open-Source Evaluation & Testing library for LLM Agents

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

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

Dataset and benchmark for RAG on company internal documents.

中文优先的企业 RAG 知识库：可控解析、治理、切块、混合检索、重排、引用、图谱、评测与 Dify 接入。

RAG evaluation without the need for "golden answers"

Red Teaming python-framework for testing chatbots and GenAI systems.

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

RAG boilerplate with semantic/propositional chunking, hybrid search (BM25 + dense), LLM reranking, query enhancement agents, CrewAI orchestration, Qdrant vector search, Redis/Mongo sessioning, Celery ingestion pipeline, Gradio UI, and an evaluation suite (Hit-Rate, MRR, hybrid configs).

LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

Open source framework for evaluating AI Agents

Practical LLM evaluation for teams that ship to production. Deterministic + LLM-as-judge evaluators, dataset support, CI/CD integration.

smallevals — CPU-fast, GPU-blazing fast offline retrieval evaluation for RAG systems with tiny QA models.

OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.

Multi-tenant RAG reference architecture (Next.js, Supabase, Pinecone): per-tenant isolation, hybrid search, cited answers, LLM failover, and a public hallucination benchmark.

The E2E AI testing tool | No ML Overhead

Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.