No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by aws-samples · LLM Plugin · ★ 65
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is bedrock-kb-rag-workshop safe to install? View the security audit →
Retrieval Augmented Generation using Amazon Bedrock This repository provides sample code for implementing a question answering application using the Retrieval Augmented Generation (RAG) technique with Amazon Bedrock. A RAG implementation consists of two parts: A data pipeline that ingests that from documents (typically stored in Amazon S3) into a knowledge base i.e. a vector database such as Amazon OpenSearch Service Serverless (AOSS) so that it is available for lookup when a question is received. An application that receives a question from the user, looks up the knowledge base for relevant pieces of information (context) and then creates a prompt that includes the question and the context and provides it to an LLM for generating a response. The data pipeline represents an undifferentiated heavy lifting and can be implemented using Amazon Bedrock Agents for knowledge Base. We can now connect an S3 bucket to a vector database such as AOSS and have a Bedrock Agent read the objects (html, pdf, text etc.), chunk them, and then convert these chunks into embeddings using Amazon Titan Embeddings model and then store these embeddings in AOSS.
| Stars | 65 |
| Forks | 12 |
| Language | HTML |
| Category | LLM Plugin |
| License | MIT-0 |
| Quality Score | 58.5236945689901/100 |
| Open Issues | 3 |
| Last Updated | 2026-07-14 |
| Created | 2023-10-02 |
| Platforms | claude-code |
| Est. Tokens | ~16k |
These tools work well together with bedrock-kb-rag-workshop for enhanced workflows:
Looking for a bedrock-kb-rag-workshop alternative? If you're comparing bedrock-kb-rag-workshop with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
This repo covers LLM, Agents, MCP Tools, Skills concepts with sample codes: LangChain & LangGraph, AWS Strands
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG.
langchain 工具,流程设计组件,服务,代理以及相关学习文档的合集(agent,service,tutorials,flow-design)
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP
A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.
Build, deploy, and orchestrate event-driven agents natively on Apache Flink® and Apache Kafka®
Explore other popular llm plugin tools:
bedrock-kb-rag-workshop is Bedrock Knowledge Base and Agents for Retrieval Augmented Generation (RAG). It is categorized as a LLM Plugin with 65 GitHub stars.
bedrock-kb-rag-workshop is primarily written in HTML. It covers topics such as amazon-bedrock, bedrock, claude2.
You can find installation instructions and usage details in the bedrock-kb-rag-workshop GitHub repository at github.com/aws-samples/bedrock-kb-rag-workshop. The project has 65 stars and 12 forks, indicating an active community.
bedrock-kb-rag-workshop is released under the MIT-0 license, making it free to use and modify according to the license terms.
The top alternatives to bedrock-kb-rag-workshop on Agent Skills Hub include Fast-LLM-Agent-MCP, lucid-memory, awesome-langchain-zh. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: