RAG & Knowledge
Retrieval-augmented generation and knowledge bases.
MemVid
Memory layer for AI Agents — replace complex RAG pipelines with a serverless, single-file memory layer
AnythingLLM
Private document chat (RAG)
Fess
Self-hosted enterprise search & site search with AI-powered semantic search, web crawling, and document indexing
OpenContracts
The open document intelligence platform — build collaborative knowledge bases that humans and AI agents can work with together
Vald
Cloud-native distributed vector search engine for high-dimensional similarity search
Infinity
The AI-native database built for LLM applications — incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text for RAG pipelines
DB-GPT
Open-source agentic AI data assistant — connect to databases, ask questions in natural language, and let AI write SQL, analyze data, and generate reports and insights autonomously
Graphiti
Build real-time temporal knowledge graphs for AI agents — hybrid semantic, keyword, and graph-based retrieval with automatic fact invalidation
DocsGPT
Private AI platform for agents, assistants and enterprise search with built-in Agent Builder
Cognee
Open-source AI memory platform for agents with persistent long-term memory across sessions
WeKnora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
FastGPT
Open-source knowledge base platform with RAG retrieval, AI workflow orchestration, and MCP support
RagApp
The easiest way to use Agentic RAG in any enterprise — deployable in your own cloud infrastructure using Docker
Jina
Build multimodal AI applications with a cloud-native stack — search, embed, rerank, and serve at scale with Jina
DeepWiki Open
AI-Powered Wiki Generator for any GitHub, GitLab, or BitBucket repository
Airweave
Open-source context retrieval layer that connects AI agents to your data sources — documents, databases, APIs, and more.
Trieve
All-in-one platform for search, recommendations, RAG, and analytics
LLM-Ware
Unified enterprise RAG framework with small, specialized models
Apache Doris
Real-time analytics database with hybrid vector search and full-text search for AI agents
LanceDB
Developer-friendly embedded vector database for multimodal AI. Search More; Manage Less.
SeekStorm
Lightning-fast hybrid search engine — vector, lexical, and semantic search in one.
SAG
SAG — A new SOTA for RAG. An original retrieval architecture and open-source knowledge base for humans and agents.
UltraRAG
UltraRAG is a low-code MCP framework from OpenBMB for building complex, innovative RAG pipelines with a visual chat interface.
AutoRAG
Agentic RAG platform that automatically optimizes retrieval pipelines so your AI agent can find anything in your documents.
HelixDB
OLTP graph-vector database in Rust on object storage — one engine for graph, vector, and document workloads in AI applications.
Memanto
The long-term memory layer that AI agents love — semantic memory, chat history, and knowledge for CrewAI, LangChain, and RAG.
CodeGraph RAG
CodeGraph RAG turns your monorepo into a queryable knowledge graph — ask questions, understand architecture, and edit multi-language codebases with AI.
Semantica
Graph-native infrastructure for context and accountable AI systems
OpenMemory
Local persistent memory for your LLM applications — Claude Desktop, GitHub Copilot, Codex and more.
LEANN
RAG on Everything. Index millions of documents on your laptop with 97% storage savings, zero accuracy loss, and complete privacy — no cloud, no telemetry.
EdgeQuake
High-performance GraphRAG framework in Rust — turn documents into intelligent knowledge graphs for superior retrieval and generation.
txtai
All-in-one embeddings, semantic search, and RAG framework for AI applications
Khoj
Your AI second brain — chat with your docs, get answers from the web, custom agents
RAGFlow
Open-source RAG engine fusing retrieval-augmented generation with agent capabilities for LLMs
Quivr
Opinionated RAG framework to build your AI second brain — works with any LLM and any file type
Qdrant
Vector similarity search engine and database for the next generation of AI applications
Chroma
AI-native open-source embedding database — the simplest way to build Python or JS LLM apps with memory
Meilisearch
Lightning-fast search engine with AI-powered hybrid and vector search
Typesense
Fast, typo-tolerant open-source search engine with vector search capabilities
Milvus
High-performance cloud-native vector database for scalable ANN search
Weaviate
Open-source vector database combining vector search with structured filtering for AI applications
Marqo
Open-source neural search engine powered by deep learning
OpenSearch
Open-source distributed search and analytics suite with vector database capabilities for AI
Vespa
The AI search platform for fast, accurate RAG and recommendations
PrivateGPT
Chat with your documents privately using LLMs — 100% local, no data leaks
Dragonfly
High-performance in-memory data store with Redis/Memcached compatibility and vector search for AI
R2R
Production-ready AI retrieval system with agentic RAG and RESTful API
RedisStack
Redis with integrated modules for vector search, JSON, and search capabilities
Haystack
Open-source AI orchestration framework for production-ready RAG and agents
Supabase
Open-source Postgres platform for AI apps with vector search, realtime subscriptions & built-in dashboard
pgvector
Open-source vector similarity search for PostgreSQL
TestTool
test
RediSearch
Full-text search and vector similarity search engine for Redis
Verba
Open-source RAG chatbot powered by Weaviate - chat with your data
LangChain
Build context-aware reasoning applications powered by LLMs
LlamaIndex
Open-source data framework for building LLM-powered RAG applications
Guardrails AI
Add guardrails to your LLM applications — validate inputs, detect risks, and enforce policies
Microsoft GraphRAG
Modular graph-based Retrieval-Augmented Generation system from Microsoft Research
LangChain-Chatchat
Local knowledge base Q&A with LangChain, ChatGLM, Qwen and Llama models
LightRAG
Simple and Fast Retrieval-Augmented Generation