Self-hosted AI tools

Self-hosted AI tools

Open source AI stack map for local, private, and own-infrastructure deployments.

Projects — 33
Updated regularly
All projectsSuggest a project

Self-hosted AI directory

A broad stack map for AI projects you can run without sending every workflow to a hosted vendor.

Use this page when you want the complete self-hosted AI map: chat interfaces, runtimes, RAG systems, retrieval databases, agent/workflow builders, and coding tools.

Stack map, not mega-list

The recommendations are exact registry-backed projects across the main self-hosted AI layers instead of a fuzzy keyword dump.

Choose the right layer

Use chat apps for users, runtimes for local models, RAG tools for private knowledge, vector databases for retrieval, and agents/dev tools for automation.

Why it works

  • Chat and local inference

    Open WebUI, LobeChat, LibreChat, AnythingLLM, Onyx, Jan, Ollama, LocalAI, llama.cpp, and vLLM cover the user interface and model-serving layers.

  • Private knowledge and retrieval

    DocsGPT, Kotaemon, LlamaIndex, Haystack, R2R, RAGFlow, Qdrant, Chroma, Weaviate, Milvus, LanceDB, and pgvector cover RAG applications and retrieval infrastructure.

  • Agents, workflows, and code

    Dify, CrewAI, AutoGen, the n8n starter kit, Tabby, Continue, and Aider cover self-hosted app building, automation, and developer workflows.

Curated repositories

Self-hosted open source AI tools

33 projects
open-webui

open-webui/open-webui

open-webui

134.1k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

19k|Python
NOASSERTION
ollamaollama-webuillm
danny-avila

danny-avila/LibreChat

danny-avila

36k

Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active.

7.4k|TypeScript
MIT
aichatgptclone
Mintplex-Labs

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
MIT
raglmstudiolocalai
onyx-dot-app

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
NOASSERTION
enterprise-searchragai-chat
janhq

janhq/jan

janhq

42.2k

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

2.8k|TypeScript
NOASSERTION
llamacpplocalaiself-hosted
ollama

ollama/ollama

ollama

170k

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

15.8k|Go
MIT
llamallmllms
mudler

mudler/LocalAI

mudler

45.8k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

4k|Go
MIT
llamaaillm
ggml-org

ggml-org/llama.cpp

ggml-org

106.6k

LLM inference in C/C++

17.4k|C++
MIT
ggml
vllm-project

vllm-project/vllm

vllm-project

78.2k

A high-throughput and memory-efficient inference and serving engine for LLMs

16.1k|Python
Apache-2.0
gptllmpytorch
arc53

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
MIT
aipythonnatural-language-processing
Cinnamon

Cinnamon/kotaemon

Cinnamon

25.3k

An open-source RAG-based tool for chatting with your documents.

2.1k|Python
Apache-2.0
chatbotllmsopen-source
run-llama

run-llama/llama_index

run-llama

48.9k

LlamaIndex is the leading document agent and OCR platform

7.3k|Python
MIT
agentsapplicationdata
deepset-ai

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-2.0
nlpquestion-answeringpytorch
SciPhi-AI

SciPhi-AI/R2R

SciPhi-AI

7.8k

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

627|Python
MIT
artificial-intelligencelarge-language-modelsretrieval-augmented-generation
infiniflow

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-2.0
llm-app
weaviate

weaviate/Verba

weaviate

7.7k

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

849|Python
BSD-3-Clause
Retrieval-Augmented Generation (RAG) & Knowledge
rag-web-ui

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-2.0
ailangchainrag
microsoft

microsoft/graphrag

microsoft

32.5k

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

3.4k|Python
MIT
graphragragllm
HKUDS

HKUDS/LightRAG

HKUDS

34.3k

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

4.8k|Python
MIT
knowledge-graphlarge-language-modelsretrieval-augmented-generation
microsoft

microsoft/kernel-memory

microsoft

2.2k

Research project. A Memory solution for users, teams, and applications.

396|C#
MIT
indexingllmmemory
qdrant

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-2.0
neural-networksearch-engineknn-algorithm
chroma-core

chroma-core/chroma

chroma-core

27.6k

Data infrastructure for AI

2.2k|Rust
Apache-2.0
databaserustrust-lang
weaviate

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-Clause
search-enginesemantic-searchsemantic-search-engine
milvus-io

milvus-io/milvus

milvus-io

44k

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

4k|Go
Apache-2.0
annsnearest-neighbor-searchfaiss
lancedb

lancedb/lancedb

lancedb

10.1k

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

860|HTML
Apache-2.0
approximate-nearest-neighbor-searchimage-searchnearest-neighbor-search
pgvector

pgvector/pgvector

pgvector

21k

Open-source vector similarity search for Postgres

1.2k|C
NOASSERTION
nearest-neighbor-searchapproximate-nearest-neighbor-search
langgenius

langgenius/dify

langgenius

139.2k

Production-ready platform for agentic workflow development.

21.8k|TypeScript
NOASSERTION
aigptllm
crewAIInc

crewAIInc/crewAI

crewAIInc

49.9k

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

6.9k|Python
MIT
agentsaiai-agents
microsoft

microsoft/autogen

microsoft

57.4k

A programming framework for agentic AI

8.7k|Python
CC-BY-4.0
chatgptllm-agentllm-framework
n8n-io

n8n-io/self-hosted-ai-starter-kit

n8n-io

14.7k

The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.

3.7k|Unknown
Apache-2.0
ailow-codeself-hosted
TabbyML

TabbyML/tabby

TabbyML

33.5k

Self-hosted AI coding assistant

1.7k|Rust
NOASSERTION
aicodegencoding-assistant
continuedev

continuedev/continue

continuedev

32.8k

⏩ Source-controlled AI checks, enforceable in CI. Powered by the open-source Continue CLI

4.4k|TypeScript
Apache-2.0
open-sourcedeveloper-toolsai
Aider-AI

Aider-AI/aider

Aider-AI

43.9k

aider is AI pair programming in your terminal

4.3k|Python
Apache-2.0
chatgptclicommand-line

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.

Self-hosted RAG tools

Document search, connectors, and knowledge assistants for private corpora and retrieval-heavy AI products.

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.

FAQ

Questions answered

What counts as a self-hosted AI tool?

A self-hosted AI tool is an open source project that can reasonably run on local hardware, private servers, containers, or your own cloud account as part of an AI workflow.

Are all open source AI projects automatically self-hosted?

No. Some repositories are models, examples, API clients, or low-level libraries. This page favors projects that form a useful self-hosted stack layer: interface, runtime, RAG system, retrieval store, agent platform, or coding tool.