Local AI
Run LLMs locally
16 tools in this category
Ollama
Go • MIT
Run LLMs locally — one command, any model
LM Studio
TypeScript/Python • Proprietary (free personal)
Desktop app for local LLMs — discover, download, chat
LocalAI
Go • MIT
Drop-in OpenAI replacement — run LLMs locally
KoboldCPP
C++ • AGPL-3.0
LLM inference for gamers — one-click, GPU-optimized
Text Generation WebUI
Python • AGPL-3.0
Web interface for LLMs — notebooks, chat, API
Open WebUI
TypeScript + Python • MIT
Self-hosted ChatGPT alternative — supports all major LLMs, RAG, and multi-user
AnythingLLM
JavaScript • MIT
Private AI assistant — documents, agents, multi-user
Jan
TypeScript • Apache-2.0
Open-source ChatGPT alternative — 100% local, privacy-first
Msty
TypeScript • Proprietary
Desktop app for local LLMs — model management, RAG, and chat in one polished interface
llama.cpp
C++ • MIT
LLM inference engine in C/C++ — powers Ollama, LM Studio, and the local AI stack
Xinference
Python • Apache-2.0
Run any LLM with one line of code — unified inference API
Faraday.dev
Python • GPL-3.0
AI-powered security operations — SOAR platform
Ollama UI
TypeScript • MIT
Web interface for Ollama — chat with local LLMs
GPT4All
C++ • MIT
Run LLMs locally — no API key, no internet required
LM Studio
TypeScript/Python • Proprietary (free personal)
Desktop app for local LLMs — discover, download, chat
AnythingLLM
JavaScript • MIT
Private AI assistant — documents, agents, multi-user