RAG Frameworks, Parsers and Vector Databases

XERJ is a local search engine for developers building AI agents that need to retrieve code, documents or stored knowledge without reading whole files into their context. It runs on a laptop or self-hosted server.

Pathway's Live Data Framework is a Python framework for developers building RAG applications and analytics over changing data. It runs locally or on your own servers, including through Docker. Its incremental engine updates results as data arrives, so applications can work with changing documents and events.

UltraRAG is a self-hosted framework for researchers and developers building AI systems that answer questions using their own documents. Its Python application and Docker deployment provide a browser workspace for knowledge bases, workflow design and evaluation. Generation can use local models through vLLM or Hugging Face. Embeddings can use local Sentence Transformers or a configured OpenAI service; the OpenAI cloud connection sends embedding inputs to that service.

SimpleMem is a memory system for developers building AI agents that need to recall past conversations and stored media without passing the full history to a model each time.

Agent Service Toolkit is a Python template for developers building their own AI agent services. It brings together agent logic, an API and a browser chat interface so you don't have to build each part from scratch.

docTR reads text from PDFs and images for developers building document processing applications and researchers comparing OCR models. It locates individual words and recognizes their text on your own hardware.

AutoFlow is a conversational knowledge base for teams that want visitors to ask questions about their product or documentation. It uses Graph RAG, which combines knowledge graphs with retrieval of relevant content for AI answers.

Polywise is a self-hosted system for people who want AI agents to work with saved research, notes, and project context. It keeps that material available across conversations so you don't have to explain the same work each time.

Text Embeddings Inference is a self-hosted server for developers building semantic search and retrieval applications. It turns text into embeddings through a REST API and can run offline once model weights are downloaded.

Context+ is a local MCP server for developers who want coding assistants to find relevant code and understand the effects of a change across a large project. It works with Claude Code, Cursor, VS Code, Windsurf and OpenCode.

sqlite-vec adds vector storage and search to SQLite for developers building local AI apps or other software that uses embeddings. It keeps vectors and related application data in the same database.

Meilisearch is a search engine for developers adding search and AI retrieval to websites, apps, catalogs or internal data. You can host the engine on your own server or use the separate managed Meilisearch Cloud service.

CocoIndex is an open-source AI indexing framework for developers processing codebases and documents on their own hardware. Its code indexing example uses sentence-transformers for embeddings and writes to pgvector or LanceDB, giving it a concrete role in preparing searchable context for agents and LLM apps.

kotaemon is an open source document chat app for people who want to ask questions across their files and inspect the evidence behind an answer. Developers can also use it to build custom document question-answering applications.

RAG-Anything is a Python framework for developers building question-answering systems over documents that mix prose with visual or structured content. Built on LightRAG, it suits research papers, technical manuals and financial reports where answers depend on figures, tables or formulas.

OpenSearch is a self-hosted search and analytics engine for developers building AI retrieval and document search, and teams analyzing operational data. Its Vector Engine provides a database for machine learning and generative AI applications. You can run the search server and dashboards on your own hardware through Docker on Linux, macOS or Windows.

Khoj is a personal AI assistant for people who want answers from their files and the web. It also supports custom agents and recurring research tasks.

Milvus is a vector database for developers building AI retrieval, image search and other applications that find related content. It stores embeddings alongside metadata for searching text, images and multimodal information.

FlagEmbedding is a Python toolkit for developers building semantic search and retrieval-augmented generation (RAG). It runs embedding models to find relevant text and rerankers to refine the order of retrieved results.

QMD searches Markdown notes, meeting transcripts, documentation and knowledge bases on your own machine. It's for people who want to find material by its wording or meaning, and make that search available to an AI agent.

vllm-mlx is a local LLM inference server for developers who want to connect AI apps and coding assistants to models running on an Apple Silicon Mac. One process exposes both OpenAI-compatible and Anthropic-compatible APIs. It's open source under Apache 2.0 and runs on macOS with at least 8 GB of unified memory.

LangChainGo is a Go implementation of LangChain for developers adding language models to their own applications. It provides reusable components for connecting models to documents, tools, and conversation history.

Palace gives AI coding agents persistent memory of project decisions, conventions and fixes. Developers can carry that context between sessions in Cursor, Claude Code, Codex and Claude Desktop.

SemanticFinder helps readers and researchers find passages by meaning in long documents. It runs the search model in your browser, so you can search your own text without sending it to a model server.

Chroma DB is a search database for developers building AI apps and agents that need to retrieve relevant information from their data. You can run it locally or on your own infrastructure.

olmOCR converts scanned and image-based documents into text for researchers and developers preparing LLM datasets. It handles pages whose layout makes ordinary text extraction difficult.

FlashRAG is an open source Python toolkit for researchers and developers comparing retrieval-augmented generation (RAG) methods or building their own. It combines implemented research methods with prepared benchmark datasets and reported results, so experiments don't have to start with a separate codebase for each approach. It uses the MIT license.

ContextGem is a Python framework for developers extracting structured information from documents such as contracts, invoices and reports. You describe what you need in natural language, and it handles extraction prompts and data modelling for text and image content.

Helix is a paid, self-hosted platform for engineering teams coordinating coding agents. Agents work on separate tasks in parallel, while the team shares a view of their progress and reviews their work.

PaperQA2 is a Python research assistant for researchers and developers who need answers grounded in scientific literature. It searches a local document collection and connects its answers to evidence through in-text citations.

MiniRAG is a Python framework for developers building question-answering tools over their own data with small language models. It targets on-device applications where larger models and heavier retrieval systems are difficult to use.

MonkeyOCR is a local AI document parser for developers and researchers who need to extract content from English and Chinese PDFs or images. It recognizes page structure and reading order alongside the content itself.

Infinity is a search database for developers building retrieval-augmented generation (RAG), question answering and recommendation systems. It lets applications combine matches based on meaning with exact text matches and structured filters.

LazyLLM is a Python framework for developers building applications with multiple AI agents. It brings application workflows, model training and evaluation together so teams can refine a prototype using task-specific data.