RAG and search

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

79,185 stars+553 this week

An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.

1,297 stars+60 this week

World's first open-source enterprise world model.

8,698 stars+37 this week

Local-first search across your workspace, built for humans and AI agents.

4,294 stars+83 this week

Own the flow: one open-source AI platform for your knowledge, models and channels – web, WhatsApp, email, Outlook, Nextcloud & ownCloud. Local and cloud models side by side, with the cost on every answer.

766 stars+286 this week

Search Claude Code, Codex, Pi, OpenCode, Github Copilot & Cursor transcripts. Resume sessions. Track tokens.

308 stars+9 this week

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

93,808 stars+442 this week

LlamaIndex is the document processing platform for AI

52,852 stars+68 this week

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

46,614 stars+55 this week

企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景，从 0 到 1 完整工程实现。

4,442 stars+33 this week

The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.

3,233 stars+11 this week

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

15,701 stars+33 this week

An open-source, single-operator business command center: run a one-person operated company as AI-assisted departments (comms, funnel, social, finances, agents, and a knowledge graph) from one live dashboard.

1,392 stars+73 this week

AI desktop app for chat, RAG, Skills, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM, Gemini, OpenRouter)

541 stars+2 this week

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

13,184 stars+122 this week

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

30,251 stars+115 this week

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/

35,479 stars+93 this week

The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 50+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.

4,057 stars+159 this week

Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW classifier routing: 89% right note vs 62%, 2.1× faster ingest, 68% fewer tokens.

254 stars+4 this week

大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。

1,595 stars+53 this week

A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.

2,817 stars+174 this week

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

40,617 stars+134 this week

Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.

629 stars0 this week

为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.

668 stars+11 this week

Open-source inference server and production cluster for all the models your agent needs.

3,479 stars+21 this week

Open-source AI workspace for legal document work: reviewable AI edits as tracked changes, linked sources, project history. Desktop app + plugin SDK. 开源法律 AI 文档工作台

171 starsThis week: Not stated

A decision-model-based ontology & knowledge-graph builder — builds governed knowledge graphs from your documents, every fact gated and traceable to its evidence.

239 stars+238 this week

GitaViśva (गीताविश्व): the Bhagavad Gita as a living knowledge graph. Explore all 700 verses in 3D, read 20 classical commentaries, listen to recitations, ask a GraphRAG companion with your own free API key, and keep a private journal. Works offline.

72 stars+61 this week

推量牛 BullFlow — 开源企业级 RAG 解决方案：从企业知识库、营销内容自动化生产到全域内容分发 | Open-source enterprise RAG solution: knowledge base → automated marketing content → omnichannel publishing. 知识库全链路本地开源模型，无需付费模型；AI Agent 创作图文 / 图片 / 视频，一键发布抖音、小红书、公众号、LinkedIn、YouTube 等 17 个平台。Commercial-grade, multi-tenant, billing & admin built in. MIT

417 stars+120 this week

Open-source NotebookLM alternative. Local-first research notebook: ask questions about your PDFs, books, web pages, YouTube videos and recordings, and get answers with every quote checked against its source. Any model, plain-file notebooks, local OCR, search and speech. Linux, Windows, Android, web.

13 stars+10 this week

多模态检索实战：意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。

129 stars+129 this week

The IQ Series is a hands-on learning experience for Microsoft IQ: Microsoft's unified intelligence layer for the enterprise, spanning Foundry IQ, Work IQ, and Fabric IQ. The series includes video episodes, Jupyter notebooks, and Azure deployment templates.

407 starsThis week: Not stated

A self-hosted retrieval-augmented search API: web search, content extraction, embeddings, and answer generation.

51 starsThis week: Not stated

网文平台资源配置决策助手：GraphRAG 两阶段检索 + ReAct Agent + 规则引擎兜底，方案合法率 60%→100%

27 stars0 this week

Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access.

1,445 stars+853 this week

RAG over GitHub issues, with a hand-reviewed eval set and an audit of the judge itself. Reports the interval, not just the best number.

164 stars+163 this week

LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.

13,372 stars+26 this week

Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files.

5,409 stars+148 this week

XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation

612 stars+2 this week

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

40,264 stars+318 this week

A lightweight, lightning-fast, in-process vector database

16,215 stars+48 this week

Fast local-first Markdown knowledge base for Windows with live preview, search, graph, Dataview, book reader, and MCP

281 stars+5 this week

The AI Governance Platform for Agents, Knowledge, and Context

2,902 stars+30 this week

基于 Spring Boot 4.1、Java 25、Spring AI 2.0、React、PostgreSQL/pgvector、Redis 和 RustFS 构建的开源 AI 面试平台，支持简历智能分析、模拟面试、语音面试和知识库 RAG。

3,481 stars+27 this week

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

13,783 stars+30 this week

Ontology-Augmented Generation for AI agents.

803 stars+101 this week

Interactive desktop app with 58 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.

252 stars+9 this week

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

3,287 stars+13 this week

The AI search platform

7,164 stars+6 this week

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

152 stars+9 this week

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

4,762 stars+11 this week

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

1,159 stars+7 this week

NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

1,971 stars+12 this week

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

6,574 stars+12 this week

全流程 智能招投标 Agent：标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档，全流程 AI 自动化。

438 stars+7 this week

Your entire engineering context, deeply understood

1,460 stars+3 this week

Semantic Search & Call Graphs for AI Agents (100% Local)

1,946 stars+13 this week

HelixDB is an OLTP graph database with native vector and full-text search built in Rust on Object Storage.

6,275 stars+12 this week

ParseBench - A Document Parsing Benchmark for AI Agents

627 stars+2 this week

SparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across Agent sessions, route tasks to the right models, and extend the workspace with custom tools and apps. Reviewable, steerable, reversible runs on macOS, Windows and Linux.

121 stars0 this week

BISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.

12,197 stars+97 this week

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

1,762 stars+18 this week

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

3,369 stars+8 this week

All-in-one intelligent assistant powered by LlamaIndex — RAG, GraphRAG, NL2SQL, Skills & Memory with multimodal support.

455 stars0 this week

Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.

12,994 stars+29 this week

Open-source, real-time collaborative AI canvas - notes, mini-apps, and agents on one infinite board.

199 stars+4 this week

A modular graph-based Retrieval-Augmented Generation (RAG) system

36,600 stars+76 this week

Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning—all in one SQLite file.

477 stars+2 this week

中文优先的企业 RAG 知识库：可控解析、治理、切块、混合检索、重排、引用、图谱、评测与 Dify 接入。

594 stars+8 this week

Apache Pinot: a real-time analytics database for low-latency SQL and vector search, serving user-facing and agent-facing applications

6,171 stars+1 this week

「摘星」· 微信助手 — AI Agent 智能助手 / AI 群聊摘要 / 关键词即时提醒 / 公众号摘要与文章实时推送 / RAG 语义检索 / 聊天、朋友圈归档 / 收藏导出 。本地运行，数据不出本机。

140 stars+4 this week

Incremental engine for long horizon agents 🌟 Star if you like it!

11,832 stars+21 this week

Redis Vector Library. The AI-native Python client for Redis.

434 stars+2 this week

Rust library for generating vector embeddings and reranking locally!

1,051 stars+2 this week

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

18,366 stars+15 this week

Open-source AI customer support system. AI-first support, human-ready operations.

297 stars+5 this week

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

806 stars+7 this week

EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation

2,297 stars+4 this week

On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.

655 stars+5 this week

Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.

311 stars+19 this week

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

429 stars+1 this week

LLPhant - A comprehensive PHP Generative AI Framework using OpenAI GPT 4. Inspired by Langchain

1,722 stars+1 this week

按问题复杂度自动分流的电商客服 RAG：简单问题直接回答；复杂问题经过多跳检索并自我纠错；查单、退改通过工具调用完成，且高风险写操作必须先经人工确认。基于 FastAPI 和 LangGraph，混合检索并附带引用，内置离线评测与 Prometheus 指标。涵盖简历写法和项目面试拷打

234 stars+25 this week

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.

92,460 stars+315 this week

AI System Design - Learn how to design AI systems built on LLMs, RAG, and AI Agents step by step.

845 stars+24 this week

Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.

522 stars+3 this week

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

4,368 stars+53 this week

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

5,347 stars+39 this week

Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.

303 stars+6 this week

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code health, fast grep/glob, bash compression, background tasks, PTY.

334 stars+2 this week

Context Graph for AI Native SDLC

5,793 stars+10 this week

⚡️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

5,735 stars+10 this week

High accuracy RAG for answering questions from scientific documents with citations

9,568 stars+33 this week

JVector: the most advanced embedded vector search engine

1,757 stars+1 this week

OnCo: total information dominance on cancer. A public, cited knowledge graph of oncology with a website, JSON API, MCP server and CLI: one page per cancer, treatment, target, trial, institution, person and idea.

245 stars+1 this week

Not stated

480 stars+2 this week

Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253

274 stars+4 this week

Established strong JEV based natural language to SQL performance and well-covered semantic operators for PostgreSQL with optimized cost and latency. Reusable evidence, with native execution, parallel plans and explainable embeddings in development preview.

261 stars+1 this week

Forward videos from IM to transcript, Markdown, and your knowledge base — with raw and skill-updated outputs.

158 stars+2 this week

A prior-art search for your code ideas — has this dev tool already been shipped?

563 stars+4 this week

TAgent 是一个基于 Java 17、Spring Boot、Spring AI 和 DDD 分层构建的 AI Agent 工程实践项目。 它不是只封装一次模型调用，而是覆盖了一次 Agent 请求从接入、路由、运行时装配、规划执行、RAG、记忆、MCP 工具治理、人工审批、执行中干预，到 SSE 流式输出和全链路观测的完整过程。

198 stars+4 this week

Retrieval and Retrieval-augmented LLMs

12,304 stars+13 this week

CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.

279 stars+86 this week

Fast, streaming indexing, query, and agentic LLM applications in Rust

803 stars+1 this week

OpenKB: Open LLM Knowledge Base

4,860 stars+17 this week

Not stated

241 stars0 this week

A Fork of Rikkahub with an overhauled UI and feature additions

399 stars+7 this week

AI 应用平台（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | AI application platform (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)

1,392 stars+5 this week

AI Powered Knowledge Graph Generator

3,136 stars+4 this week

Semantic codebase indexing and search for OpenCode, Claude, Codex, Pi, Jcode, and MCP hosts. Powered by Rust and tree-sitter.

230 stars+3 this week

Research project on bilingual Urdu-English retrieval-augmented generation for Pakistani government and legal documents, with OCR, hybrid retrieval, citation grounding, and evaluation.

129 stars+1 this week

基于 RAG（免微调）从聊天记录唤起语气与回忆：让曾经对话的温度，延续为往后的陪伴。 | Zero-finetuning RAG to revive tone and memories from chat logs: Let the warmth of past conversations continue into companionship.

327 stars+1 this week

基于LangChain、LangGraph、FastAPI和React的RAG项目，主分支为基于知识图谱的知识管理平台，base-rag分支为完整的向量RAG项目供学习使用

485 stars+3 this week

轻量、自托管的多入口 AI Agent 机器人｜QQ 官方 / OneBot 11 / NapCat / 微信｜Rust｜Memory / RAG / Todo / Tool Calling

130 stars+2 this week

The Kubernetes operator for K8ssandra

243 stars0 this week

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

655 stars+9 this week

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space

608 stars+2 this week

Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟

1,034 stars+2 this week

local-first semantic code search engine

1,321 stars+5 this week

Full-featured DAW, DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Suno API, Chimera track fusion, Demucs stems, MIDI generate/notate, img > spectrogram > music, drawing > music, VST3 & .gan plugins, automix & key-lock, GLSL shaders, volumetric video, Quest 3 XR interface, MIDI auto-map, RAG assistant

236 stars+8 this week

本地化 AI 小说精修工作台🚀。内置 RAG 长时记忆🧠、三模态协作（作家/主编/助手）🖋️、卡片流式编辑器⚡。支持酒馆卡导入、全书自动化精修与扩写🎭。AI小说加料 小说精修 AI文本修改 小说扩写 小说总结

257 stars0 this week

Agentic memory infra for AI agents

203 stars+1 this week

NestJS Helper + AI Chatbot Development

2,180 stars0 this week

Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.

289 stars+27 this week

Local-first memory, decision engine, and governance harness for AI agents — portable across IDEs. Own the state. Rent the intelligence.

621 stars+1 this week

Official Python SDK for the Pinecone vector database

456 stars0 this week

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.

584 stars+3 this week

Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.

208 stars0 this week

Claude forgets everything. This fixes that. 🔗 www.npmjs.com/package/claude-self-reflect

230 stars+1 this week

Chat with your documents to create and refine editable architecture diagrams. Local workspace, Excalidraw canvas, optional Tavily search.

160 stars+1 this week

This repository contains examples for customers to get started using the Amazon Bedrock Service. This contains examples for all available foundational models

1,532 stars+2 this week

A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.

58,723 stars+16 this week

Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.

172 stars0 this week

企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。

678 stars+3 this week

Local code search for AI agents: cheaper, faster and sweeter. Because maybe grep isn't all you need... 🍬

115 stars+26 this week

Graph-native code intelligence that replaces embedding-based RAG with deterministic program understanding.

162 stars0 this week