Search private knowledge

Best rag and knowledge skills for AI agents

Use these skills to ingest documents, index knowledge, retrieve relevant context, and make agents better at answering with grounded sources.

Builders choosing skills for index documents and search a knowledge base. Ranked from the OpenAgentSkill index using quality, trust, freshness, adoption, and install readiness.

30
Ranked
611K
Stars
100
Top trust

Workflow

Index documents

Workflow

Search a knowledge base

Workflow

Summarize source material

#1

Qdrant

36 fitTrust 100Excellent 100

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Excellent quality, 32K stars, and a 36 use-case fit score.

32K starsJun 12, 2026 pushProduction candidateRustVector Search
$ npx skills add qdrant/qdrant
#2

Weaviate

35 fitTrust 100Excellent 100

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Excellent quality, 16K stars, and a 35 use-case fit score.

16K starsJun 12, 2026 pushProduction candidateGoSemantic Search
$ npx skills add weaviate/weaviate
#3

Lancedb

35 fitTrust 100Excellent 100

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

Excellent quality, 11K stars, and a 35 use-case fit score.

11K starsJun 12, 2026 pushProduction candidateHTMLSemantic Search
$ npx skills add lancedb/lancedb
#4

Generative AI For Beginners

34 fitTrust 100Excellent 100

21 Lessons, Get Started Building with Generative AI

Excellent quality, 112K stars, and a 34 use-case fit score.

112K starsJun 11, 2026 pushProduction candidateJupyter NotebookSemantic Search
$ npx skills add microsoft/generative-ai-for-beginners
#5

Obsidian Smart Connections

34 fitTrust 100Excellent 100

Find related notes and excerpts while writing. Your link building copilot displays relevant content in graph + list view. A local embedding model powers semantic search. Zero setup. No API key.

Excellent quality, 5.1K stars, and a 34 use-case fit score.

5.1K starsJun 11, 2026 pushProduction candidateJavaScriptSemantic Search
$ npx skills add brianpetro/obsidian-smart-connections
#6

Sentrysearch

34 fitTrust 100Excellent 100

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

Excellent quality, 4.3K stars, and a 34 use-case fit score.

4.3K starsJun 2, 2026 pushProduction candidatePythonSemantic Search
$ npx skills add ssrajadh/sentrysearch
#7

USearch

34 fitTrust 100Excellent 100

Fast Open-Source Search & Clustering engine Γ— for Vectors & Arbitrary Objects Γ— in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram πŸ”

Excellent quality, 4.2K stars, and a 34 use-case fit score.

4.2K starsMay 28, 2026 pushProduction candidateC++Semantic Search
$ npx skills add unum-cloud/USearch
#8

Meilisearch

33 fitTrust 100Excellent 100

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

Excellent quality, 58K stars, and a 33 use-case fit score.

58K starsJun 11, 2026 pushProduction candidateRustSemantic Search
$ npx skills add meilisearch/meilisearch
#9

Mteb

33 fitTrust 100Excellent 100

MTEB: Massive Text Embedding Benchmark

Excellent quality, 3.3K stars, and a 33 use-case fit score.

3.3K starsJun 12, 2026 pushProduction candidatePythonSemantic Search
$ npx skills add embeddings-benchmark/mteb
#10

Examples

33 fitTrust 100Excellent 100

Jupyter Notebooks to help you get hands-on with Pinecone vector databases

Excellent quality, 3.0K stars, and a 33 use-case fit score.

3.0K starsJun 4, 2026 pushProduction candidateJupyter NotebookSemantic Search
$ npx skills add pinecone-io/examples
#11

Sie

33 fitTrust 100Excellent 100

Open-source inference server and production cluster for all the models your agent needs.

Excellent quality, 2.0K stars, and a 33 use-case fit score.

2.0K starsJun 12, 2026 pushProduction candidatePythonSemantic Search
$ npx skills add superlinked/sie
#12

Typesense

33 fitTrust 100Excellent 100

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚑ πŸ” ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

Excellent quality, 26K stars, and a 33 use-case fit score.

26K starsJun 10, 2026 pushProduction candidateC++Semantic Search
$ npx skills add typesense/typesense
#13

Txtai

32 fitTrust 100Excellent 100

πŸ’‘ All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Excellent quality, 13K stars, and a 32 use-case fit score.

13K starsJun 11, 2026 pushProduction candidatePythonAI Agents
$ npx skills add neuml/txtai
#14

Oceanbase

32 fitTrust 100Excellent 100

The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.

Excellent quality, 10K stars, and a 32 use-case fit score.

10K starsJun 12, 2026 pushProduction candidateC++Vector Search
$ npx skills add oceanbase/oceanbase
#15

Databend

31 fitTrust 100Excellent 100

Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. β€” rebuilt from scratch. Unified architecture on your S3.

Excellent quality, 9.3K stars, and a 31 use-case fit score.

9.3K starsJun 12, 2026 pushProduction candidateRustVector Search
$ npx skills add databendlabs/databend
#16

Server

31 fitTrust 100Excellent 100

MariaDB server is a community developed fork of MySQL server. Started by core members of the original MySQL team, MariaDB actively works with outside developers to deliver the most featureful, stable, and sanely licensed open SQL server in the industry.

Excellent quality, 7.7K stars, and a 31 use-case fit score.

7.7K starsJun 12, 2026 pushProduction candidateC++Vector Search
$ npx skills add MariaDB/server
#17

RediSearch

31 fitTrust 100Excellent 100

A query and indexing engine for Redis, providing secondary indexing, full-text search, vector similarity search and aggregations.

Excellent quality, 6.2K stars, and a 31 use-case fit score.

6.2K starsJun 12, 2026 pushProduction candidateCVector Search
$ npx skills add RediSearch/RediSearch
#18

Infinity

31 fitTrust 100Excellent 100

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

Excellent quality, 4.6K stars, and a 31 use-case fit score.

4.6K starsJun 12, 2026 pushProduction candidateC++RAG
$ npx skills add infiniflow/infinity
#19

Crate

31 fitTrust 100Excellent 100

CrateDB is a distributed and scalable SQL database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is PostgreSQL-compatible, and based on Lucene.

Excellent quality, 4.4K stars, and a 31 use-case fit score.

4.4K starsJun 12, 2026 pushProduction candidateJavaVector Search
$ npx skills add crate/crate
#20

Attu

30 fitTrust 100Excellent 100

The Best GUI for Milvus

Excellent quality, 3.0K stars, and a 30 use-case fit score.

3.0K starsJun 11, 2026 pushProduction candidateShellVector Search
$ npx skills add zilliztech/attu
#21

Seekdb

30 fitTrust 100Excellent 100

The AI-native state store for agents. MySQL-compatible, embedded or server, hybrid vector + full-text search, COW sandboxes (FORK/MERGE).

Excellent quality, 2.7K stars, and a 30 use-case fit score.

2.7K starsJun 12, 2026 pushProduction candidateC++RAG
$ npx skills add oceanbase/seekdb
#22

Milvus

30 fitTrust 100Excellent 100

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

Excellent quality, 45K stars, and a 30 use-case fit score.

45K starsJun 11, 2026 pushProduction candidateGoRAG
$ npx skills add milvus-io/milvus
#23

Vearch

30 fitTrust 100Excellent 100

Distributed vector search for AI-native applications

Excellent quality, 2.3K stars, and a 30 use-case fit score.

2.3K starsJun 9, 2026 pushProduction candidateGoRAG
$ npx skills add vearch/vearch
#24

Haystack

30 fitTrust 100Excellent 100

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Excellent quality, 26K stars, and a 30 use-case fit score.

26K starsJun 12, 2026 pushProduction candidateMDXRAG
$ npx skills add deepset-ai/haystack
#25

WeKnora

29 fitTrust 100Excellent 100

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Excellent quality, 16K stars, and a 29 use-case fit score.

16K starsJun 12, 2026 pushProduction candidateGoRAG
$ npx skills add Tencent/WeKnora
#26

Turbovec

29 fitTrust 100Excellent 100

A vector index built on TurboQuant, written in Rust with Python bindings

Excellent quality, 11K stars, and a 29 use-case fit score.

11K starsJun 10, 2026 pushProduction candidatePythonRAG
$ npx skills add RyanCodrai/turbovec
#27

Llm Graph Builder

28 fitTrust 100Excellent 100

Neo4j graph construction from unstructured data using LLMs

Excellent quality, 4.8K stars, and a 28 use-case fit score.

4.8K starsJun 12, 2026 pushProduction candidateJupyter NotebookRAG
$ npx skills add neo4j-labs/llm-graph-builder
#28

Ragflow

28 fitTrust 100Excellent 100

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Excellent quality, 83K stars, and a 28 use-case fit score.

83K starsJun 13, 2026 pushProduction candidatePythonAI Agents
$ npx skills add infiniflow/ragflow
#29

PaddleOCR

28 fitTrust 100Excellent 100

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Excellent quality, 82K stars, and a 28 use-case fit score.

82K starsJun 12, 2026 pushProduction candidatePythonRAG
$ npx skills add PaddlePaddle/PaddleOCR
#30

Chonkie

28 fitTrust 100Excellent 100

πŸ¦› CHONK docs with Chonkie ✨ β€” The lightweight ingestion library for fast, efficient and robust RAG pipelines

Excellent quality, 4.1K stars, and a 28 use-case fit score.

4.1K starsJun 11, 2026 pushProduction candidatePythonRAG
$ npx skills add chonkie-inc/chonkie

Selection method

How this list is ranked

OpenAgentSkill scores each candidate against the workflow keywords, then balances fit with GitHub stars, quality signals, trust profile, maintenance freshness, and whether there is a clear install path.

How does OpenAgentSkill rank rag and knowledge?

The ranking combines workflow fit, quality score, trust profile, GitHub adoption, maintenance freshness, and whether a clear install path exists.

Should I install the top skill immediately?

No. Treat the list as a shortlist, open the skill detail page, inspect the repository and license, then test the install command in a sandbox workflow.

Can my agent consume this ranking through an API?

Yes. Use /api/skills/search with the related task or /api/agent/rankings?slug=best-rag-knowledge-skills to fetch ranked skill data.