Every Local AI for Business - a curated directory of self-hosted AI tools for document search, team chat, workflow automation, and secure model serving.
Local AI for Business
Self-hosted AI tools for document search, team chat, automation, and secure inference. Your data stays on your infrastructure.
Knowledge & document search
RAGFlow
Open-source RAG engine with deep document understanding for precise question answering.
Onyx
Enterprise-grade AI search and chat over your documents, Slack, Confluence, and internal tools.
AnythingLLM
All-in-one local RAG application - workspaces, document chat, agents, and embeddable widgets, fully self-hosted.
Dify
Open-source LLM app development platform with visual orchestration, built-in RAG, and agent capabilities.
Chroma
The AI-native open-source embedding database designed for simplicity and fast prototyping.
Milvus
Cloud-native vector database for billion-scale AI similarity search with hybrid search capabilities.
Qdrant
High-performance vector search engine written in Rust with rich filtering and full payload support.
Weaviate
Open-source vector database with built-in vectorization, hybrid search, and generative feedback loops.
Team chat & productivity
Open WebUI
The ChatGPT-style web interface for Ollama and any OpenAI-compatible local LLM.
LobeChat
Modern, open-source ChatGPT/Claude UI with plugin ecosystem, multi-model support, and built-in TTS.
NextChat
Lightweight, cross-platform ChatGPT UI that deploys in one click and works with any LLM backend.
LibreChat
Enhanced ChatGPT clone with multi-model, multi-user, and multi-server support for teams.
SillyTavern
Powerful, customizable chat interface for roleplaying with local and remote LLMs with character management.
Workflow automation
n8n
Self-hosted workflow automation with native LLM, vector DB, and agent nodes - the local Zapier for AI pipelines.
Dify
Open-source LLM app development platform with visual orchestration, built-in RAG, and agent capabilities.
Flowise
Drag-and-drop LLM flow builder with LangChain integration for building custom AI agents and chatbots.
Langflow
Low-code visual framework for building multi-agent and RAG applications with any LLM provider.
Mastra
TypeScript agent framework with built-in model routing, agent memory, tools, and observability.
Haystack
Open-source NLP framework for building production-ready RAG pipelines and search systems.
Security & compliance
LocalAI
Self-hosted, OpenAI-compatible API server for LLMs, image generation, audio, and embeddings.
vLLM
High-throughput LLM serving engine with PagedAttention - the gold standard for production local inference.
Hugging Face Text Generation Inference
Production-ready LLM inference server from Hugging Face with optimized hardware and continuous batching.
TensorRT-LLM
NVIDIA's optimized LLM inference engine delivering maximum performance on NVIDIA GPUs.
Ollama
The simplest way to run open-source LLMs locally - pull a model, get an OpenAI-compatible API.