onyx-dot-app/onyx
onyx-dot-app
28.5k
Open Source AI Platform - AI Chat with advanced features that works with every LLM
3.8k|Python
NOASSERTIONenterprise-searchragai-chat
Self-hosted RAG tools
Open source retrieval and knowledge tools for private document AI.
Projects — 19
Updated regularly
Self-hosted RAG
Retrieval tools for private knowledge bases and production AI apps.
Use this page to choose open source RAG building blocks that can run in your own environment: document-chat apps, retrieval frameworks, graph RAG engines, and vector databases.
Split by job
Includes end-user document chat apps, production RAG frameworks, and retrieval storage instead of mixing every adjacent ingestion utility into one list.
Registry-backed
Every recommendation comes from the synced upstream registry, using exact repositories rather than fuzzy keyword matches.
Why it works
Document chat apps
AnythingLLM, Onyx, DocsGPT, Kotaemon, Verba, and RAG Web UI are closer to ready-to-use private knowledge assistants.
RAG frameworks and engines
LlamaIndex, Haystack, R2R, RAGFlow, GraphRAG, LightRAG, and Kernel Memory are better when you are building or customizing the pipeline.
Vector and retrieval storage
Qdrant, Chroma, Weaviate, Milvus, LanceDB, and pgvector cover the storage/search layer behind many private RAG deployments.
Curated repositories
Open source RAG and knowledge tools
Mintplex-Labs/anything-llm
Mintplex-Labs
59k
The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
6.4k|JavaScript
MITraglmstudiolocalai
arc53/DocsGPT
arc53
17.8k
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.
2k|Python
MITaipythonnatural-language-processing
Cinnamon/kotaemon
Cinnamon
25.3k
An open-source RAG-based tool for chatting with your documents.
2.1k|Python
Apache-2.0chatbotllmsopen-source
run-llama/llama_index
run-llama
48.9k
LlamaIndex is the leading document agent and OCR platform
7.3k|Python
MITagentsapplicationdata
deepset-ai/haystack
deepset-ai
25k
Open-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.
2.7k|MDX
Apache-2.0nlpquestion-answeringpytorch
SciPhi-AI/R2R
SciPhi-AI
7.8k
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
627|Python
MITartificial-intelligencelarge-language-modelsretrieval-augmented-generation
infiniflow/ragflow
infiniflow
79k
RAGFlow 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
8.9k|Python
Apache-2.0llm-app
weaviate/Verba
weaviate
7.7k
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
849|Python
BSD-3-ClauseRetrieval-Augmented Generation (RAG) & Knowledge
rag-web-ui/rag-web-ui
rag-web-ui
3k
RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
334|TypeScript
Apache-2.0ailangchainrag
microsoft/graphrag
microsoft
32.5k
A modular graph-based Retrieval-Augmented Generation (RAG) system
3.4k|Python
MITgraphragragllm
HKUDS/LightRAG
HKUDS
34.3k
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
4.8k|Python
MITknowledge-graphlarge-language-modelsretrieval-augmented-generation
microsoft/kernel-memory
microsoft
2.2k
Research project. A Memory solution for users, teams, and applications.
396|C#
MITindexingllmmemory
qdrant/qdrant
qdrant
30.7k
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/
2.2k|Rust
Apache-2.0neural-networksearch-engineknn-algorithm
chroma-core/chroma
chroma-core
27.6k
Data infrastructure for AI
2.2k|Rust
Apache-2.0databaserustrust-lang
weaviate/weaviate
weaviate
16.1k
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
1.3k|Go
BSD-3-Clausesearch-enginesemantic-searchsemantic-search-engine
milvus-io/milvus
milvus-io
44k
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
4k|Go
Apache-2.0annsnearest-neighbor-searchfaiss
lancedb/lancedb
lancedb
10.1k
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
860|HTML
Apache-2.0approximate-nearest-neighbor-searchimage-searchnearest-neighbor-search
pgvector/pgvector
pgvector
21k
Open-source vector similarity search for Postgres
1.2k|C
NOASSERTIONnearest-neighbor-searchapproximate-nearest-neighbor-search
Related pages
Keep browsing
Self-hosted ChatGPT alternatives
Private assistant apps and team chat portals for people who want a familiar front end around local or private models.
Local model runtimes and inference servers
Private inference stacks for running models locally or exposing an OpenAI-compatible endpoint inside your own infrastructure.
Vector databases and retrieval storage
Storage and search layers for embeddings, filtering, persistence, and semantic retrieval at scale.
Agents, workflows, and app builders
Workflow engines, agent systems, and app builders for repeatable internal automation instead of one-off chat.
AI developer tools
Self-hostable coding assistants and repo-aware tools for local or private developer workflows.
Self-hosted AI tools
Browse open source AI tools you can run on your own infrastructure, from local LLM apps to RAG, agents, inference, and production tooling.
FAQ
Questions answered
What is a self-hosted RAG tool?
It is an open source project that helps retrieve private or custom knowledge for language model apps and can run in your own environment as an app, framework, service, or retrieval database.
Do I need a vector database for RAG?
Often, but not always. Many RAG systems use vector search, but smaller or specialized deployments may use hybrid search, full-text search, reranking, or framework-managed indexes.
Should document parsers and crawlers be listed here?
Only when they are part of a broader RAG product. Tools that only parse PDFs, crawl websites, or convert files are useful inputs, but they are not enough for this page's main recommendation set.