RAG Frameworks

Understanding authentication, rate limits, request shapes, errors, and source attribution.

Required or useful skill for resources in this use case.

Loading, cleaning, chunking, and normalizing documents or structured data.

Required or useful skill for resources in this use case.

Handling private code, prompts, logs, documents, and user data safely.

Skill linked from curated resource requirements.

Shipping static sites, APIs, and background jobs with clear environment boundaries.

Required or useful skill for resources in this use case.

Writing concise setup, usage, troubleshooting, and reference documentation.

Skill linked from curated resource requirements.

Testing LLM quality, retrieval quality, task completion, and regression behavior.

Required or useful skill for resources in this use case.

Building usable interfaces with component systems, routing, and responsive layouts.

Skill linked from curated resource requirements.

Designing data flow, model calls, tools, memory, and evaluation boundaries.

Required or useful skill for resources in this use case.

Structuring instructions, context, and examples for reliable AI outputs.

Required or useful skill for resources in this use case.

General Python programming for automation, data, AI, and backend scripts.

Required or useful skill for resources in this use case.

Connecting LLMs to external knowledge with retrieval, ranking, and grounded responses.

Required or useful skill for resources in this use case.

Running open-source tools locally or on controlled infrastructure.

Required or useful skill for resources in this use case.

Self-hosted workspace and RAG interface for documents and LLM workflows.

Curated tool relationship for future one-stop directory pages.

Open-source Python framework for building conversational AI interfaces.

Curated tool relationship for future one-stop directory pages.

Embedding database commonly used for local and application-level RAG prototypes.

Seeded from manual curation; metadata enriched where possible.

Open-source crawler and scraper designed for LLM-friendly web extraction.

Curated tool relationship for future one-stop directory pages.

Open-source platform for building LLM apps, agents, workflows, and RAG systems.

Curated tool relationship for future one-stop directory pages.

Tool and API for turning websites into LLM-ready markdown or structured data.

Curated tool relationship for future one-stop directory pages.

Low-code visual builder for LLM apps, agent flows, and RAG workflows.

Curated tool relationship for future one-stop directory pages.

Open-source framework for building production-style search, RAG, and NLP pipelines.

Seeded from manual curation; metadata enriched where possible.

Framework ecosystem for building LLM applications, agents, and RAG workflows.

Seeded from manual curation; metadata enriched where possible.

Visual framework for building LLM apps, agents, and RAG pipelines.

Curated tool relationship for future one-stop directory pages.

Framework for building stateful, controllable LLM agent workflows.

Curated tool relationship for future one-stop directory pages.

Framework focused on connecting private or domain data to LLM applications.

Seeded from manual curation; metadata enriched where possible.

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Official GitHub repository metadata fetched where API allowed.

The agent engineering platform.

Official GitHub repository metadata fetched where API allowed.

LlamaIndex is the leading document agent and OCR platform

Official GitHub repository metadata fetched where API allowed.

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/

Official GitHub repository metadata fetched where API allowed.

Search infrastructure for AI

Official GitHub repository metadata fetched where API allowed.

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.

Official GitHub repository metadata fetched where API allowed.

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

Official GitHub repository metadata fetched where API allowed.

Production-ready platform for agentic workflow development.

High-star GitHub discovery seed from query `topic:rag stars:>1000`.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

High-star GitHub discovery seed from query `topic:rag stars:>1000`.

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

High-star GitHub discovery seed from query `topic:rag stars:>1000`.

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

High-star GitHub discovery seed from query `topic:rag stars:>1000`.

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.

High-star GitHub discovery seed from query `topic:rag stars:>1000`.