Alternatives

Evalscope alternatives for AI agents.

Compare similar skills by workflow fit, trust score, quality, GitHub adoption, maintenance, and install readiness.

Current skill

Evalscope

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

100
Quality
96
Trust
2.9K
Stars
#1

Graphrag

Similarity 142Trust 95Excellent 100

A modular graph-based Retrieval-Augmented Generation (RAG) system

34K starsJun 16, 2026 pushdataPythonRAG
$ npx skills add microsoft/graphrag
#2

Hello Agents

Similarity 141Trust 87Excellent 100

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

59K starsJun 11, 2026 pushdataPythonRAG
$ npx skills add datawhalechina/hello-agents
#3

Awesome Llm Apps

Similarity 134Trust 95Excellent 100

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

114K starsJun 13, 2026 pushdataPythonRAG
$ npx skills add Shubhamsaboo/awesome-llm-apps
#4

Graphiti

Similarity 134Trust 95Excellent 100

Build Real-Time Knowledge Graphs for AI Agents

27K starsJun 12, 2026 pushdataPythonRAG
$ npx skills add getzep/graphiti
#5

Kotaemon

Similarity 133Trust 95Excellent 100

An open-source RAG-based tool for chatting with your documents.

25K starsJun 9, 2026 pushdataPythonRAG
$ npx skills add Cinnamon/kotaemon
#6

Paper Qa

Similarity 132Trust 97Excellent 100

High accuracy RAG for answering questions from scientific documents with citations

8.7K starsJun 11, 2026 pushdataPythonRAG
$ npx skills add Future-House/paper-qa
#7

AutoRAG

Similarity 131Trust 96Excellent 100

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

4.8K starsJun 12, 2026 pushdataPythonRAG
$ npx skills add Marker-Inc-Korea/AutoRAG
#8

Sparrow

Similarity 131Trust 94Excellent 100

Structured data extraction and instruction calling with ML, LLM and Vision LLM

5.2K starsJun 11, 2026 pushdataPythonRAG
$ npx skills add katanaml/sparrow
#9

ReMe

Similarity 129Trust 93Excellent 100

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

3.1K starsJun 10, 2026 pushdataPythonRAG
$ npx skills add agentscope-ai/ReMe
#10

Fastembed

Similarity 129Trust 93Excellent 100

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

3.0K starsJun 10, 2026 pushdataPythonRAG
$ npx skills add qdrant/fastembed
#11

Promptfoo

Similarity 128Trust 98Excellent 100

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

22K starsJun 15, 2026 pushdataTypeScriptRAG
$ npx skills add promptfoo/promptfoo
#12

Happy Llm

Similarity 127Trust 89Excellent 100

📚 从零开始构建大模型

31K starsMay 6, 2026 pushdataJupyter NotebookRAG
$ npx skills add datawhalechina/happy-llm
#13

Llama Index

Similarity 126Trust 95Excellent 100

LlamaIndex is the leading document agent and OCR platform

50K starsJun 15, 2026 pushdataPythonRAG
$ npx skills add run-llama/llama_index
#14

Onyx

Similarity 126Trust 94Excellent 100

Open Source AI Platform - AI Chat with advanced features that works with every LLM

30K starsJun 13, 2026 pushdataPythonRAG
$ npx skills add onyx-dot-app/onyx
#15

Easy Dataset

Similarity 125Trust 89Excellent 100

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

14K starsMay 1, 2026 pushdataJavaScriptRAG
$ npx skills add ConardLi/easy-dataset
#16

DB GPT

Similarity 125Trust 97Excellent 100

open-source agentic AI data assistant for the next generation of AI + Data products.

19K starsJun 14, 2026 pushdataPythonRAG
$ npx skills add eosphoros-ai/DB-GPT

How to choose

When should you switch?

Use an alternative when it has a clearer install path, higher trust score, fresher maintenance, or better platform fit for your current agent stack. Keep Evalscope if it already passes your workflow test and repository review.

Next step

Compare top candidates side by side

Open the compare page, test the install commands in a sandbox, and check each repository before using a skill in production.