PyPI · npm100Exceptionalhealth index
deepset-ai/haystackOpen-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.
Python★ 26.5KSep 16, 2026
npm · PyPI98Exceptionalhealth index
TypeScript★ 544↓ 67.2K/moOct 21, 2026
PyPI97Exceptionalhealth index
Python★ 424↓ 2.8M/moAug 27, 2026
PyPI · npm96Exceptionalhealth index
HKUDS/LightRAG[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Python★ 39.7KSep 17, 2026
PyPI · Go · npm95Exceptionalhealth index
infiniflow/ragflowRAGFlow 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
Go · Python · TypeScript★ 90.8KSep 16, 2026
npm · PyPI95Exceptionalhealth index
pipeshub-ai/pipeshub-aiPipesHub is an open-source platform for securely connecting enterprise knowledge to AI. Give AI agents trusted context and your team permission-aware search with verified citations across your business systems.
Python · TypeScript★ 3,757Sep 19, 2026
PyPI93Exceptionalhealth index
neuml/txtai💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Python★ 13KSep 20, 2026
PyPI93Exceptionalhealth index
qdrant/fastembedFast, Accurate, Lightweight Python library to make State of the Art Embedding
Python · Jupyter Notebook★ 3,193↓ 5.2M/moSep 10, 2026
PyPI · npm90Excellenthealth index
Marker-Inc-Korea/AutoRAGAutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.
TypeScript · Python★ 5,073↓ 2,320/moSep 15, 2026
npm90Excellenthealth index
TypeScript · Go · MDX★ 2,178↓ 464.7K/moSep 15, 2026
PyPI · npm89Excellenthealth index
cdeust/CortexCross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
Python★ 71↓ 2,447/moSep 5, 2026
crates.io88Excellenthealth index
Rust★ 1,007↓ 621.2K/moSep 9, 2026
npm · PyPI87Excellenthealth index
Python · TypeScript★ 6,567↓ 6,678/moAug 28, 2026
PyPI · npm87Excellenthealth index
lyonzin/knowledge-ragLocal RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.
Python★ 290↓ 2,794/moOct 4, 2026
PyPI84Excellenthealth index
Python★ 39.1K↓ 118K/moOct 12, 2026
PyPI · RubyGems83Excellenthealth index
swirlai/swirl-searchAI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge across 100+ apps while keeping data secure. Deploy in minutes, not months.
Python★ 3,047Oct 12, 2026
superlinear-ai/raglite🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
Python★ 1,200↓ 644/moSep 17, 2026
nevenincs/vaultspec-ragSearch code and feature records by meaning through the command line or Model Context Protocol (MCP). Inference runs on your GPU.
Python★ 1↓ 9,576/moSep 14, 2026
Python · Jupyter Notebook★ 12.2KSep 17, 2026
mgd43b/maniculeSelf-hosted retrieval infrastructure for AI assistants. MCP-first search and grounded answers over a private corpus, with citations that resolve to a real location in a real document — a page, a heading, a line, a cell.
Python★ 0Sep 18, 2026
JetXu-LLM/llama-githubLlama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Solutions to conduct Agentic RAG from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.
Python★ 292↓ 513/moSep 12, 2026
JavaScript★ 0↓ 6,430/moOct 14, 2026
npm · PyPI · crates.io +165Goodhealth index
muthuishere/citenexusEvidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/
Python · Go · Rust★ 0↓ 409/moOct 21, 2026
PyPI63Moderatehealth index
4R9UN/mcp-kql-serverKusto and Log Analytics MCP server help you execute a KQL (Kusto Query Language) query within an AI prompt, analyze, and visualize the data.
Python★ 23↓ 480/moOct 4, 2026
PyPI63Moderatehealth index
antonyrag/ragleap-coreProduction-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.
Python · Java★ 12↓ 745/moSep 13, 2026
Packagist63Moderatehealth index
PHP★ 1↓ 11.4K/moOct 19, 2026
npm63Moderatehealth index
yoloshii/ClawMemOn-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
TypeScript★ 210↓ 737/moSep 13, 2026
PyPI60Moderatehealth index
Python★ 0↓ 3,069/moOct 20, 2026
jmurray2011/loreAuditable RAG from the command line: grounded, cited answers over your own documents, with faithfulness verification and retrieval eval you can gate CI on.
Go★ 0Sep 20, 2026
PyPI54Moderatehealth index
Python★ 0↓ 4,147/moAug 23, 2026