Agentic Rag Pattern With Context Engineering

via “retrieval-augmented generation (rag) with configurable engines and semantic search”

Multi-agent software company simulator — PM, architect, engineer roles collaborate on projects.

Unique: Implements a pluggable RAG system with support for multiple retrieval engines (vector, BM25, hybrid) and per-role/per-action configuration. RAG is integrated into the action framework, enabling agents to automatically augment prompts with retrieved context before LLM invocation.

vs others: More flexible than single-engine RAG systems because it supports multiple retrieval strategies and allows fine-grained configuration per role/action. Compared to external RAG pipelines, MetaGPT's RAG is tightly integrated with the agent framework and automatically handles context injection.

via “rag-enabled context augmentation with semantic search and embeddings”

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration

Unique: Integrates RAG as an automatic context augmentation layer that runs transparently during agent execution rather than requiring explicit retrieval calls. Uses RuVector for embeddings with support for multiple backends and retrieval strategies, enabling agents to discover relevant context without knowing what to search for.

vs others: Provides automatic context augmentation rather than requiring agents to explicitly query a knowledge base — improves agent decision quality by ensuring relevant historical context is always available.

via “rag-enhanced agent context with semantic search”

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration

Unique: Integrates RAG with agent orchestration by automatically retrieving and ranking context based on task type and agent role, rather than requiring agents to explicitly query knowledge bases

vs others: More integrated than standalone RAG systems by tightly coupling retrieval with agent execution lifecycle, enabling context to be automatically augmented at task start rather than requiring agents to manage retrieval

via “rag-optimized text generation with 128k context window”

Cohere's efficient model for high-volume RAG workloads.

Unique: Cohere's RAG optimization focuses on citation-aware generation with built-in source attribution, allowing the model to explicitly reference retrieved documents in its output. This is achieved through training that emphasizes grounding responses in provided context rather than relying on parametric knowledge, reducing hallucination in retrieval scenarios. The 128K context window is specifically tuned for RAG workloads rather than general long-context tasks.

vs others: Delivers RAG-specific optimizations (citations, grounding) at lower cost than GPT-4 Turbo or Claude 3 Opus while maintaining enterprise-grade quality, making it ideal for cost-sensitive high-volume retrieval pipelines where citation accuracy matters.

via “retrieval-augmented generation (rag) engine with agentic capabilities”

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

Unique: RAGFlow uniquely combines deep document parsing with a visual agent workflow builder, allowing users to create complex AI applications seamlessly.

vs others: Unlike other RAG solutions, RAGFlow offers a comprehensive agentic workflow framework that enhances document processing and contextual understanding.

via “retrieval-augmented generation (rag) pattern library with multiple retrieval strategies”

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

Unique: Provides 8+ distinct RAG patterns (basic, corrective, hybrid, database routing, agentic, autonomous, reasoning-enhanced) with working implementations for each, allowing developers to compare trade-offs between retrieval quality and latency. Most RAG tutorials show only basic vector search; this library treats RAG as a design space with multiple valid solutions.

vs others: More comprehensive RAG pattern coverage than LangChain's built-in RAG examples; more practical than academic RAG papers with runnable code for each pattern

via “foundational-rag-pipeline-implementation”

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Unique: Provides a unified pedagogical pipeline architecture that all 40+ techniques build upon, with dual-framework implementations (LangChain and LlamaIndex) showing how the same logical pipeline maps to different frameworks, enabling developers to understand RAG concepts independent of framework choice

vs others: More comprehensive than single-technique tutorials because it shows the complete pipeline context and how techniques compose, whereas most RAG guides focus on isolated techniques without showing integration points

via “rag-powered knowledge retrieval and context injection”

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

Unique: Integrates RAG as a first-class agent capability rather than a preprocessing step, allowing agents to dynamically decide when to retrieve context, what queries to issue, and how to synthesize retrieved information with reasoning

vs others: More flexible than static RAG pipelines because agents can iteratively refine retrieval queries and combine multiple knowledge sources, but requires more LLM calls and latency than pre-computed context

via “agentic rag with alfred: document-aware agent reasoning and synthesis”

This repository contains the Hugging Face Agents Course.

Unique: Treats document retrieval as an active agent decision rather than a passive preprocessing step, allowing agents to reason about which documents to retrieve and how to synthesize information. Alfred example demonstrates how agents can ask follow-up questions to refine retrieval and handle contradictory information.

vs others: More flexible than passive RAG for complex information synthesis because agents can reason about retrieval decisions; more accurate than pure LLM reasoning because agents actively manage document context.

via “two-phase rag pipeline assembly with lcel orchestration”

Everything you need to know to build your own RAG application

Unique: Uses LangChain Expression Language (LCEL) to declaratively compose indexing and query phases into a single reusable chain expression, eliminating boilerplate control flow and enabling runtime chain introspection and modification

vs others: Simpler than building RAG from scratch with raw vector store APIs, and more transparent than black-box RAG frameworks because LCEL makes each pipeline step explicit and swappable

via “agentic-rag-pattern-with-context-engineering”

12 Lessons to Get Started Building AI Agents

Unique: Frames RAG as an agentic decision (agents decide when to retrieve) rather than a static pipeline, and explicitly teaches context engineering techniques like chat summarization and scratchpad management to handle token constraints — most RAG tutorials treat retrieval as a fixed preprocessing step.

vs others: Covers the full context lifecycle (types, management, summarization) rather than just retrieval mechanics, making it more applicable to long-running agent conversations where context budgets are critical.

via “research paper indexing and agentic rag paper collection”

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

Unique: Separates agentic RAG papers from general agent papers, reflecting the emergence of agentic RAG as a distinct research area; provides context on paper relevance to practical development

vs others: Curated for agent development relevance rather than comprehensive; includes emerging agentic RAG research that general paper collections may not prioritize

via “rag pipeline with retrieval-augmented generation and context injection”

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

Unique: RAG pipeline is tightly integrated with embeddings database, enabling zero-copy retrieval and automatic context injection; supports hybrid retrieval (sparse + dense) and metadata filtering before context injection, reducing irrelevant context in prompts

vs others: More integrated than LangChain RAG because retrieval and generation are co-optimized in the same system; simpler than building custom RAG because context injection, prompt templating, and result handling are built-in

via “retrieval augmented generation (rag) technique documentation with architecture patterns”

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

Unique: Positions RAG within the broader prompt engineering landscape, showing how it complements other techniques (CoT, few-shot prompting) and contrasts with alternatives (fine-tuning, in-context learning) rather than treating RAG in isolation

vs others: More comprehensive than vendor-specific RAG tutorials because it covers architectural principles independent of particular vector databases; more practical than academic RAG papers because it includes implementation patterns and integration strategies

via “single-agent rag architecture with integrated retrieval and generation”

Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.

Unique: Unifies retrieval and generation within a single agent's reasoning loop, enabling tight coupling where retrieval decisions are informed by generation context and vice versa, rather than treating retrieval and generation as separate pipeline stages.

vs others: Simpler to implement and debug than multi-agent systems, and more efficient than rigid retrieval-then-generation pipelines by enabling adaptive retrieval based on generation progress.

via “contextual agentic pattern application”

Agentic Engineering Patterns

Unique: Integrates contextual examples tailored to user-defined scenarios, enhancing the relevance of the patterns provided.

vs others: Offers a more tailored approach than generic pattern applications, ensuring relevance to specific user projects.

via “rag context retrieval and synthesis integration”

A rag component for Convex.

Unique: Orchestrates the complete RAG loop within Convex functions, maintaining document/embedding/LLM state in a single transactional context and enabling atomic updates to conversation history and retrieved context without external workflow engines

vs others: More integrated than LangChain's RAG chains (no separate orchestration layer), but less flexible than frameworks like LlamaIndex for complex retrieval strategies or multi-stage reasoning

via “rag pipeline orchestration”

Mind engine adapter for KB Labs Mind (RAG, embeddings, vector store integration).

Unique: Encapsulates the entire RAG workflow as a declarative pipeline with pluggable stages, allowing developers to define document ingestion and retrieval logic through configuration rather than imperative code

vs others: More opinionated than LangChain's modular approach, reducing boilerplate for standard RAG patterns but with less flexibility for non-standard workflows

via “dynamic context injection for rag-powered llm applications”

** - Integrate real-time [Scrapeless](https://www.scrapeless.com/en) Google SERP(Google Search, Google Flight, Google Map, Google Jobs....) results into your LLM applications. This server enables dynamic context retrieval for AI workflows, chatbots, and research tools.

Unique: Enables on-demand web search integration into RAG pipelines without requiring pre-indexed web documents, allowing LLMs to access current information for time-sensitive queries while maintaining local knowledge base for stable, domain-specific data

vs others: More flexible than static RAG with pre-indexed documents; simpler than building custom web crawling and indexing infrastructure; trades freshness guarantees for latency compared to real-time search engines

via “rag context assembly and prompt injection prevention”

Retrieval Augmented Generation (RAG) support for NestJS AI

Unique: Implements prompt assembly as NestJS services with built-in injection prevention (sanitization, escaping), token counting, and context window management, rather than leaving these concerns to application code or generic templating engines

vs others: More security-focused than LangChain's prompt templates — includes injection prevention and token counting out-of-the-box, with explicit context window management strategies