RAG

WeKnora is an open-source, LLM-powered framework designed for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning. It features a ReAct agent for complex multi-step tasks and a Wiki mode that distills raw documents into a structured, interlinked knowledge base. The platform supports multi-source data ingestion, various LLM integrations, and flexible deployment options to ensure complete data sovereignty.

RAG-Anything is a comprehensive framework designed to process and query diverse document types including text, images, tables, and mathematical equations. Built on LightRAG, it provides an end-to-end pipeline that integrates multimodal content into a unified knowledge graph for intelligent retrieval. This system eliminates the need for multiple specialized tools by offering a single, cohesive interface for complex document analysis.

AgentKit Code Workshop is an AI Agent development platform sample repository launched by Volcengine, designed to help developers quickly master the construction and deployment of intelligent agents. The project provides a variety of code examples ranging from basic introductions to complex scenarios, covering core functions such as multi-agent collaboration, RAG retrieval enhancement, and tool invocation. Developers can use these tutorials to gain an in-depth understanding of the AgentKit development toolchain and integrate it efficiently into various business applications.

OpenDataLoader PDF is a high-performance, open-source parser designed to convert PDF documents into structured formats like Markdown, JSON, and HTML for AI and RAG pipelines. It features a hybrid processing mode that combines deterministic local parsing with AI-driven analysis to achieve industry-leading extraction accuracy for complex tables, formulas, and scanned documents. Additionally, the project provides automated accessibility solutions, including end-to-end Tagged PDF generation compliant with international standards.

AutoFlow is an open-source knowledge base tool that utilizes graph RAG technology built on TiDB Vector, LlamaIndex, and DSPy. The platform provides a Perplexity-style conversational search experience powered by an advanced built-in website crawler. Users can also integrate a customizable search widget into their own websites using a simple JavaScript snippet.

GBrain provides a persistent, self-wiring knowledge graph that enables AI agents to store and retrieve complex information across meetings, emails, and documents. The system automatically extracts entity relationships and maintains a structured timeline, allowing agents to answer queries that standard vector search cannot reach. By utilizing a durable job queue and modular skill system, it ensures that agents become smarter and more reliable over time.

Memvid is a database-free, single-file memory layer designed to provide AI agents with instant retrieval and long-term memory capabilities. Through an innovative "smart frame" design, it encapsulates data, embeddings, and indexes into a single file, achieving efficient compression and parallel reading. The system is model-agnostic and requires zero infrastructure dependencies, supporting persistent memory in various offline or online scenarios.

MemPalace is a local-first AI memory system that stores conversation history as verbatim text for high-accuracy semantic retrieval. It utilizes a structured indexing approach with pluggable backends to organize content into wings, rooms, and drawers without requiring external API calls. The platform also features a temporal knowledge graph, MCP tools, and agent-specific diaries to provide comprehensive context management.

Onyx is a feature-rich open source AI platform designed to provide an easy-to-deploy application layer interface for large language models. The platform supports RAG, deep research, code execution, and various AI agent capabilities, while remaining compatible with mainstream self-hosted and proprietary LLMs. Users can deploy via the standard or lightweight versions to meet different needs ranging from personal use to enterprise-level collaboration.

LLM Wiki is a cross-platform desktop application that transforms your documents into an organized, interlinked knowledge base using an incremental LLM-driven pipeline. It features a sophisticated two-step ingestion process, a persistent knowledge graph, and deep research capabilities to maintain and expand your personal library. The system ensures high-quality output through source traceability, human-in-the-loop review, and seamless integration with tools like Obsidian.

QMD is an on-device search engine that indexes markdown notes, documentation, and transcripts for efficient local retrieval. It utilizes a hybrid approach combining BM25 full-text search, vector semantic search, and LLM-based re-ranking to deliver high-quality results. The tool is designed for agentic workflows, offering both a command-line interface and an MCP server for seamless integration with AI agents.

Endee is a high-performance, open-source vector database specifically engineered for AI search, RAG pipelines, and semantic retrieval workloads. It is implemented in C++ and optimized for modern CPU architectures to ensure production-grade performance and low-latency results. The platform supports flexible deployment options, including Docker and local builds, while providing advanced features like hybrid search and metadata-aware filtering.

DeepTutor is an agent-native platform designed to provide personalized, intelligent tutoring through a unified chat workspace and multi-agent architecture. It features advanced capabilities like a Book Engine for interactive learning, an AI Co-Writer, and persistent memory to tailor the experience to individual user profiles. Users can deploy the system easily via a guided CLI setup or Docker, supporting a wide range of LLM and embedding providers.

The Claude Cookbooks provide a comprehensive collection of code snippets and guides to help developers integrate Claude into their own applications. The repository covers a wide range of topics including tool use, multimodal capabilities, and advanced techniques like prompt caching. These resources are designed to be easily adaptable for various programming languages and project requirements.

jcode is a high-performance coding agent harness designed for multi-session workflows and extreme resource efficiency. It features a sophisticated memory system that uses semantic vector embeddings to recall relevant information without excessive token usage. The platform supports native agent collaboration through a swarm architecture and integrates with a wide range of LLM providers via OAuth or custom configurations.