RAG

An open-source agentic RAG framework, built on Alibaba Cloud's PAI platform, that combines knowledge-base management, multimodal document understanding, a ReAct agent and MCP tool integration for enterprise question answering.

• RAG

A hybrid retrieval-augmented generation system combining vector search, a knowledge graph and cross-encoder reranking, with document parsing, image and table captioning, and inline citations.

• RAG

A local-first desktop app that converts PDFs, Office documents and other file formats into clean, AI-ready Markdown, with OCR for scanned pages and batch processing for a whole folder.

• RAG

A list of recent developments in retrieval-augmented generation for large language models, tracking accepted papers by conference and year along with common evaluation datasets.

• RAG
• Curated lists
• Papers

A dataset and benchmark of more than 500,000 simulated company documents and 500 questions for evaluating retrieval-augmented generation systems on realistic enterprise data.

• RAG
• AI evals

A modular Rust implementation of GraphRAG that builds knowledge graphs from documents and answers natural-language questions over them, with server-only, WASM-only and hybrid deployment options and optional GPU acceleration through WebGPU.

• RAG

patent is a command-line tool that searches package registries, GitHub and Hacker News for prior art on a plain-English dev-tool idea, then ranks matches by semantic similarity and summarizes the landscape as Open, Crowded or Saturated.

• RAG
• CLI tools

An open-source extension of the AWS Cloud Development Kit that provides sample, well-architected constructs for common generative AI patterns, such as retrieval-augmented generation, summarization and question answering on AWS.

• RAG
• Hosting

A relation-free graph-construction method for GraphRAG that eliminates LLM token costs during indexing, making graph-based retrieval-augmented generation faster over large corpora.

• RAG

A retrieval-augmented generation system that builds a hierarchical knowledge index over a document corpus, described in an EMNLP 2025 Findings paper.

• RAG
• Papers

A Go library for embedded vector search and semantic embeddings, with an exact cosine-similarity index and optional local (llama.cpp) or cloud (OpenAI-compatible) embedding providers.

• RAG
• Libraries

Research code from Meta that jointly pretrains a retrieval-augmented sequence-to-sequence language model, combining a dense passage retriever with an encoder-decoder model for few-shot question answering and other tasks.

• RAG
• Papers

EmbedJs is an open-source Node.js framework for building retrieval-augmented generation and other LLM applications, handling data chunking, embedding generation and vector-database storage so responses can be grounded in a user's own data.

• RAG

BiliSum generates AI summaries, transcripts and a searchable knowledge base from Bilibili, YouTube and local videos, usable from a desktop app, a command-line tool, or as a skill an AI coding agent can call.

• RAG

Kwipu turns a folder of Markdown notes, including an Obsidian vault, into a local property-graph retrieval-augmented generation index that can be queried from a terminal, a 3D web interface, or an MCP client.

• Agent memory
• RAG

Sycamore is an open-source document processing engine that partitions, enriches and chunks unstructured documents such as PDFs and presentations for search, retrieval-augmented generation and analytics, using an AI model trained specifically for document layout.

• RAG
• Data engineering

Nexus Agent is a Chinese-language enterprise AI agent platform combining conversational chat, document question-answering, web search, retrieval-augmented generation, MCP tool calling and skills extensions behind a layered execution architecture.

• Agent frameworks
• RAG

SkillCorpus is an open-source pipeline that turns scattered SKILL.md files from public repositories into a curated, retrieval-ready corpus of agent skills, with safety and license gating, quality evaluation, and task-specific skill matching built in.

• Agent skills
• RAG

RAGLight is a lightweight, modular Python framework for Retrieval-Augmented Generation that lets a developer plug in different LLMs, embedding models and vector stores, with built-in MCP integration for external tools and data sources.

• RAG

RAG Me Up is a simple, extensible framework for building Retrieval-Augmented Generation applications quickly, with a Docker Compose stack covering a Postgres database, a Node.js API server, a React UI and a Python RAG server.

• RAG

Moss is a semantic search runtime that embeds directly in an application, built for conversational AI agents that need retrieval latency under 10 milliseconds without running a separate vector database.

• RAG
• Databases

Rankify is a Python toolkit for retrieval, re-ranking and retrieval-augmented generation, integrating 40 pre-retrieved benchmark datasets, more than 7 retrieval techniques, more than 24 reranking models, and multiple RAG methods.

• RAG

SwarmVault is a local-first tool that turns documents, code, transcripts, notes and URLs into a durable markdown wiki plus a local knowledge graph, usable as a RAG knowledge base or as durable memory for AI coding agents.

• Agent memory
• RAG

An offline retrieval-augmented generation tool that ingests local files, GitHub repositories and websites, then answers questions over them using local Ollama models with no third party ever seeing the data.

• RAG